License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2018-04-04 01:23:33 +08:00
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
#include <linux/bitops.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/bio.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/page-flags.h>
|
2022-04-07 02:24:18 +08:00
|
|
|
#include <linux/sched/mm.h>
|
2008-01-25 05:13:08 +08:00
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/blkdev.h>
|
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/writeback.h>
|
|
|
|
#include <linux/pagevec.h>
|
2011-05-21 03:50:29 +08:00
|
|
|
#include <linux/prefetch.h>
|
2021-07-01 04:01:49 +08:00
|
|
|
#include <linux/fsverity.h>
|
2021-03-16 18:04:01 +08:00
|
|
|
#include "misc.h"
|
2008-01-25 05:13:08 +08:00
|
|
|
#include "extent_io.h"
|
2019-09-23 22:05:19 +08:00
|
|
|
#include "extent-io-tree.h"
|
2008-01-25 05:13:08 +08:00
|
|
|
#include "extent_map.h"
|
2008-08-20 20:51:49 +08:00
|
|
|
#include "ctree.h"
|
|
|
|
#include "btrfs_inode.h"
|
2011-07-22 21:41:52 +08:00
|
|
|
#include "volumes.h"
|
2011-11-09 20:44:05 +08:00
|
|
|
#include "check-integrity.h"
|
2012-03-13 21:38:00 +08:00
|
|
|
#include "locking.h"
|
2012-06-05 02:03:51 +08:00
|
|
|
#include "rcu-string.h"
|
2013-09-22 12:54:23 +08:00
|
|
|
#include "backref.h"
|
2017-06-23 10:09:57 +08:00
|
|
|
#include "disk-io.h"
|
2021-01-26 16:33:48 +08:00
|
|
|
#include "subpage.h"
|
2021-02-04 18:21:54 +08:00
|
|
|
#include "zoned.h"
|
2021-02-04 18:22:08 +08:00
|
|
|
#include "block-group.h"
|
2021-07-27 20:47:09 +08:00
|
|
|
#include "compression.h"
|
2022-10-19 22:50:51 +08:00
|
|
|
#include "fs.h"
|
2022-10-19 22:51:00 +08:00
|
|
|
#include "accessors.h"
|
2022-10-27 03:08:27 +08:00
|
|
|
#include "file-item.h"
|
2022-10-27 03:08:30 +08:00
|
|
|
#include "file.h"
|
2022-10-27 03:08:36 +08:00
|
|
|
#include "dev-replace.h"
|
2022-10-27 03:08:40 +08:00
|
|
|
#include "super.h"
|
2008-01-25 05:13:08 +08:00
|
|
|
|
|
|
|
static struct kmem_cache *extent_buffer_cache;
|
|
|
|
|
2013-04-23 00:12:31 +08:00
|
|
|
#ifdef CONFIG_BTRFS_DEBUG
|
2022-09-10 05:53:19 +08:00
|
|
|
static inline void btrfs_leak_debug_add_eb(struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&fs_info->eb_leak_lock, flags);
|
|
|
|
list_add(&eb->leak_list, &fs_info->allocated_ebs);
|
|
|
|
spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void btrfs_leak_debug_del_eb(struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&fs_info->eb_leak_lock, flags);
|
|
|
|
list_del(&eb->leak_list);
|
|
|
|
spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags);
|
2013-04-23 00:12:31 +08:00
|
|
|
}
|
|
|
|
|
2020-02-15 05:11:40 +08:00
|
|
|
void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info)
|
2013-04-23 00:12:31 +08:00
|
|
|
{
|
|
|
|
struct extent_buffer *eb;
|
2020-02-15 05:11:40 +08:00
|
|
|
unsigned long flags;
|
2013-04-23 00:12:31 +08:00
|
|
|
|
2020-02-15 05:11:42 +08:00
|
|
|
/*
|
|
|
|
* If we didn't get into open_ctree our allocated_ebs will not be
|
|
|
|
* initialized, so just skip this.
|
|
|
|
*/
|
|
|
|
if (!fs_info->allocated_ebs.next)
|
|
|
|
return;
|
|
|
|
|
2022-03-15 18:01:33 +08:00
|
|
|
WARN_ON(!list_empty(&fs_info->allocated_ebs));
|
2020-02-15 05:11:40 +08:00
|
|
|
spin_lock_irqsave(&fs_info->eb_leak_lock, flags);
|
|
|
|
while (!list_empty(&fs_info->allocated_ebs)) {
|
|
|
|
eb = list_first_entry(&fs_info->allocated_ebs,
|
|
|
|
struct extent_buffer, leak_list);
|
2020-02-15 05:11:42 +08:00
|
|
|
pr_err(
|
|
|
|
"BTRFS: buffer leak start %llu len %lu refs %d bflags %lu owner %llu\n",
|
|
|
|
eb->start, eb->len, atomic_read(&eb->refs), eb->bflags,
|
|
|
|
btrfs_header_owner(eb));
|
2019-09-23 22:05:17 +08:00
|
|
|
list_del(&eb->leak_list);
|
|
|
|
kmem_cache_free(extent_buffer_cache, eb);
|
|
|
|
}
|
2020-02-15 05:11:40 +08:00
|
|
|
spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags);
|
2019-09-23 22:05:17 +08:00
|
|
|
}
|
2013-04-23 00:12:31 +08:00
|
|
|
#else
|
2022-09-10 05:53:19 +08:00
|
|
|
#define btrfs_leak_debug_add_eb(eb) do {} while (0)
|
|
|
|
#define btrfs_leak_debug_del_eb(eb) do {} while (0)
|
2008-09-08 23:18:08 +08:00
|
|
|
#endif
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2022-04-15 22:33:24 +08:00
|
|
|
/*
|
|
|
|
* Structure to record info about the bio being assembled, and other info like
|
|
|
|
* how many bytes are there before stripe/ordered extent boundary.
|
|
|
|
*/
|
|
|
|
struct btrfs_bio_ctrl {
|
|
|
|
struct bio *bio;
|
2022-06-03 15:11:03 +08:00
|
|
|
int mirror_num;
|
2021-07-27 21:11:53 +08:00
|
|
|
enum btrfs_compression_type compress_type;
|
2022-04-15 22:33:24 +08:00
|
|
|
u32 len_to_stripe_boundary;
|
|
|
|
u32 len_to_oe_boundary;
|
2022-09-13 13:31:14 +08:00
|
|
|
btrfs_bio_end_io_t end_io_func;
|
2022-04-15 22:33:24 +08:00
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
/*
|
|
|
|
* Tell writepage not to lock the state bits for this range, it still
|
|
|
|
* does the unlocking.
|
2008-11-07 11:02:51 +08:00
|
|
|
*/
|
2022-10-27 19:07:03 +08:00
|
|
|
bool extent_locked;
|
2009-04-21 03:50:09 +08:00
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
/* Tell the submit_bio code to use REQ_SYNC */
|
2022-10-27 19:07:03 +08:00
|
|
|
bool sync_io;
|
2008-01-25 05:13:08 +08:00
|
|
|
};
|
|
|
|
|
2022-06-03 15:11:03 +08:00
|
|
|
static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
|
2019-01-25 13:09:15 +08:00
|
|
|
{
|
2022-06-03 15:11:03 +08:00
|
|
|
struct bio *bio;
|
2022-07-07 13:33:28 +08:00
|
|
|
struct bio_vec *bv;
|
2022-10-27 08:41:32 +08:00
|
|
|
struct btrfs_inode *inode;
|
2022-06-03 15:11:03 +08:00
|
|
|
int mirror_num;
|
|
|
|
|
|
|
|
if (!bio_ctrl->bio)
|
|
|
|
return;
|
2019-01-25 13:09:15 +08:00
|
|
|
|
2022-06-03 15:11:03 +08:00
|
|
|
bio = bio_ctrl->bio;
|
2022-07-07 13:33:28 +08:00
|
|
|
bv = bio_first_bvec_all(bio);
|
2022-10-27 08:41:32 +08:00
|
|
|
inode = BTRFS_I(bv->bv_page->mapping->host);
|
2022-06-03 15:11:03 +08:00
|
|
|
mirror_num = bio_ctrl->mirror_num;
|
2019-01-25 13:09:15 +08:00
|
|
|
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
/* Caller should ensure the bio has at least some range added */
|
|
|
|
ASSERT(bio->bi_iter.bi_size);
|
btrfs: avoid double clean up when submit_one_bio() failed
[BUG]
When running generic/475 with 64K page size and 4K sector size, it has a
very high chance (almost 100%) to hang, with mostly data page locked but
no one is going to unlock it.
[CAUSE]
With commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads"), if we failed to lookup checksum due to metadata IO error, we
will return error for btrfs_submit_data_bio().
This will cause the page to be unlocked twice in btrfs_do_readpage():
btrfs_do_readpage()
|- submit_extent_page()
| |- submit_one_bio()
| |- btrfs_submit_data_bio()
| |- if (ret) {
| |- bio->bi_status = ret;
| |- bio_endio(bio); }
| In the endio function, we will call end_page_read()
| and unlock_extent() to cleanup the subpage range.
|
|- if (ret) {
|- unlock_extent(); end_page_read() }
Here we unlock the extent and cleanup the subpage range
again.
For unlock_extent(), it's mostly double unlock safe.
But for end_page_read(), it's not, especially for subpage case,
as for subpage case we will call btrfs_subpage_end_reader() to reduce
the reader number, and use that to number to determine if we need to
unlock the full page.
If double accounted, it can underflow the number and leave the page
locked without anyone to unlock it.
[FIX]
The commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads") itself is completely fine, it's our existing code not properly
handling the error from bio submission hook properly.
This patch will make submit_one_bio() to return void so that the callers
will never be able to do cleanup when bio submission hook fails.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:13 +08:00
|
|
|
|
2022-07-07 13:33:28 +08:00
|
|
|
btrfs_bio(bio)->file_offset = page_offset(bv->bv_page) + bv->bv_offset;
|
2019-01-25 13:09:15 +08:00
|
|
|
|
2022-10-27 08:41:32 +08:00
|
|
|
if (!is_data_inode(&inode->vfs_inode))
|
|
|
|
btrfs_submit_metadata_bio(inode, bio, mirror_num);
|
2022-05-26 15:36:35 +08:00
|
|
|
else if (btrfs_op(bio) == BTRFS_MAP_WRITE)
|
2022-10-27 08:41:32 +08:00
|
|
|
btrfs_submit_data_write_bio(inode, bio, mirror_num);
|
2020-09-18 21:34:37 +08:00
|
|
|
else
|
2022-10-27 08:41:32 +08:00
|
|
|
btrfs_submit_data_read_bio(inode, bio, mirror_num,
|
2022-06-03 15:11:03 +08:00
|
|
|
bio_ctrl->compress_type);
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
|
2022-08-06 16:03:26 +08:00
|
|
|
/* The bio is owned by the end_io handler now */
|
2022-06-03 15:11:03 +08:00
|
|
|
bio_ctrl->bio = NULL;
|
2019-03-20 14:27:42 +08:00
|
|
|
}
|
|
|
|
|
2019-03-20 14:27:41 +08:00
|
|
|
/*
|
2022-10-27 19:07:05 +08:00
|
|
|
* Submit or fail the current bio in the bio_ctrl structure.
|
2019-03-20 14:27:41 +08:00
|
|
|
*/
|
2022-10-27 19:07:05 +08:00
|
|
|
static void submit_write_bio(struct btrfs_bio_ctrl *bio_ctrl, int ret)
|
2019-01-25 13:09:15 +08:00
|
|
|
{
|
2022-10-27 19:07:05 +08:00
|
|
|
struct bio *bio = bio_ctrl->bio;
|
2019-01-25 13:09:15 +08:00
|
|
|
|
2022-06-03 15:11:02 +08:00
|
|
|
if (!bio)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (ret) {
|
|
|
|
ASSERT(ret < 0);
|
2022-08-06 16:03:26 +08:00
|
|
|
btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
|
|
|
|
/* The bio is owned by the end_io handler now */
|
2022-10-27 19:07:05 +08:00
|
|
|
bio_ctrl->bio = NULL;
|
2022-06-03 15:11:02 +08:00
|
|
|
} else {
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_one_bio(bio_ctrl);
|
2019-01-25 13:09:15 +08:00
|
|
|
}
|
|
|
|
}
|
2017-06-23 10:16:17 +08:00
|
|
|
|
2022-09-10 05:53:18 +08:00
|
|
|
int __init extent_buffer_init_cachep(void)
|
|
|
|
{
|
2012-09-07 17:00:48 +08:00
|
|
|
extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
|
2009-04-13 21:33:09 +08:00
|
|
|
sizeof(struct extent_buffer), 0,
|
2016-06-24 02:17:08 +08:00
|
|
|
SLAB_MEM_SPREAD, NULL);
|
2022-09-10 05:53:18 +08:00
|
|
|
if (!extent_buffer_cache)
|
2019-09-23 22:05:18 +08:00
|
|
|
return -ENOMEM;
|
2013-09-20 11:37:07 +08:00
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2022-09-10 05:53:18 +08:00
|
|
|
void __cold extent_buffer_free_cachep(void)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2012-09-26 09:33:07 +08:00
|
|
|
/*
|
|
|
|
* Make sure all delayed rcu free are flushed before we
|
|
|
|
* destroy caches.
|
|
|
|
*/
|
|
|
|
rcu_barrier();
|
2016-01-29 21:36:35 +08:00
|
|
|
kmem_cache_destroy(extent_buffer_cache);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2015-12-03 20:08:59 +08:00
|
|
|
void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
|
2013-03-27 01:07:00 +08:00
|
|
|
{
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
unsigned long index = start >> PAGE_SHIFT;
|
|
|
|
unsigned long end_index = end >> PAGE_SHIFT;
|
2013-03-27 01:07:00 +08:00
|
|
|
struct page *page;
|
|
|
|
|
|
|
|
while (index <= end_index) {
|
|
|
|
page = find_get_page(inode->i_mapping, index);
|
|
|
|
BUG_ON(!page); /* Pages should be in the extent_io_tree */
|
|
|
|
clear_page_dirty_for_io(page);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
put_page(page);
|
2013-03-27 01:07:00 +08:00
|
|
|
index++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-12-03 20:08:59 +08:00
|
|
|
void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
|
2013-03-27 01:07:00 +08:00
|
|
|
{
|
2022-02-10 04:22:04 +08:00
|
|
|
struct address_space *mapping = inode->i_mapping;
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
unsigned long index = start >> PAGE_SHIFT;
|
|
|
|
unsigned long end_index = end >> PAGE_SHIFT;
|
2022-02-10 04:22:04 +08:00
|
|
|
struct folio *folio;
|
2013-03-27 01:07:00 +08:00
|
|
|
|
|
|
|
while (index <= end_index) {
|
2022-02-10 04:22:04 +08:00
|
|
|
folio = filemap_get_folio(mapping, index);
|
|
|
|
filemap_dirty_folio(mapping, folio);
|
|
|
|
folio_account_redirty(folio);
|
|
|
|
index += folio_nr_pages(folio);
|
|
|
|
folio_put(folio);
|
2013-03-27 01:07:00 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-05-31 16:50:38 +08:00
|
|
|
/*
|
|
|
|
* Process one page for __process_pages_contig().
|
|
|
|
*
|
|
|
|
* Return >0 if we hit @page == @locked_page.
|
|
|
|
* Return 0 if we updated the page status.
|
|
|
|
* Return -EGAIN if the we need to try again.
|
|
|
|
* (For PAGE_LOCK case but got dirty page or page not belong to mapping)
|
|
|
|
*/
|
2021-05-31 16:50:42 +08:00
|
|
|
static int process_one_page(struct btrfs_fs_info *fs_info,
|
|
|
|
struct address_space *mapping,
|
2021-05-31 16:50:38 +08:00
|
|
|
struct page *page, struct page *locked_page,
|
2021-05-31 16:50:42 +08:00
|
|
|
unsigned long page_ops, u64 start, u64 end)
|
2021-05-31 16:50:38 +08:00
|
|
|
{
|
2021-05-31 16:50:42 +08:00
|
|
|
u32 len;
|
|
|
|
|
|
|
|
ASSERT(end + 1 - start != 0 && end + 1 - start < U32_MAX);
|
|
|
|
len = end + 1 - start;
|
|
|
|
|
2021-05-31 16:50:38 +08:00
|
|
|
if (page_ops & PAGE_SET_ORDERED)
|
2021-05-31 16:50:46 +08:00
|
|
|
btrfs_page_clamp_set_ordered(fs_info, page, start, len);
|
2021-05-31 16:50:38 +08:00
|
|
|
if (page_ops & PAGE_SET_ERROR)
|
2021-05-31 16:50:42 +08:00
|
|
|
btrfs_page_clamp_set_error(fs_info, page, start, len);
|
2021-05-31 16:50:38 +08:00
|
|
|
if (page_ops & PAGE_START_WRITEBACK) {
|
2021-05-31 16:50:42 +08:00
|
|
|
btrfs_page_clamp_clear_dirty(fs_info, page, start, len);
|
|
|
|
btrfs_page_clamp_set_writeback(fs_info, page, start, len);
|
2021-05-31 16:50:38 +08:00
|
|
|
}
|
|
|
|
if (page_ops & PAGE_END_WRITEBACK)
|
2021-05-31 16:50:42 +08:00
|
|
|
btrfs_page_clamp_clear_writeback(fs_info, page, start, len);
|
2021-05-31 16:50:47 +08:00
|
|
|
|
|
|
|
if (page == locked_page)
|
|
|
|
return 1;
|
|
|
|
|
2021-05-31 16:50:38 +08:00
|
|
|
if (page_ops & PAGE_LOCK) {
|
2021-05-31 16:50:44 +08:00
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = btrfs_page_start_writer_lock(fs_info, page, start, len);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
2021-05-31 16:50:38 +08:00
|
|
|
if (!PageDirty(page) || page->mapping != mapping) {
|
2021-05-31 16:50:44 +08:00
|
|
|
btrfs_page_end_writer_lock(fs_info, page, start, len);
|
2021-05-31 16:50:38 +08:00
|
|
|
return -EAGAIN;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (page_ops & PAGE_UNLOCK)
|
2021-05-31 16:50:44 +08:00
|
|
|
btrfs_page_end_writer_lock(fs_info, page, start, len);
|
2021-05-31 16:50:38 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-02-10 23:41:05 +08:00
|
|
|
static int __process_pages_contig(struct address_space *mapping,
|
|
|
|
struct page *locked_page,
|
btrfs: pass bytenr directly to __process_pages_contig()
As a preparation for incoming subpage support, we need bytenr passed to
__process_pages_contig() directly, not the current page index.
So change the parameter and all callers to pass bytenr in.
With the modification, here we need to replace the old @index_ret with
@processed_end for __process_pages_contig(), but this brings a small
problem.
Normally we follow the inclusive return value, meaning @processed_end
should be the last byte we processed.
If parameter @start is 0, and we failed to lock any page, then we would
return @processed_end as -1, causing more problems for
__unlock_for_delalloc().
So here for @processed_end, we use two different return value patterns.
If we have locked any page, @processed_end will be the last byte of
locked page.
Or it will be @start otherwise.
This change will impact lock_delalloc_pages(), so it needs to check
@processed_end to only unlock the range if we have locked any.
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-31 16:50:37 +08:00
|
|
|
u64 start, u64 end, unsigned long page_ops,
|
2021-05-31 16:50:38 +08:00
|
|
|
u64 *processed_end)
|
|
|
|
{
|
2021-05-31 16:50:42 +08:00
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb);
|
2021-05-31 16:50:38 +08:00
|
|
|
pgoff_t start_index = start >> PAGE_SHIFT;
|
|
|
|
pgoff_t end_index = end >> PAGE_SHIFT;
|
|
|
|
pgoff_t index = start_index;
|
|
|
|
unsigned long pages_processed = 0;
|
2022-08-24 08:40:18 +08:00
|
|
|
struct folio_batch fbatch;
|
2021-05-31 16:50:38 +08:00
|
|
|
int err = 0;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (page_ops & PAGE_LOCK) {
|
|
|
|
ASSERT(page_ops == PAGE_LOCK);
|
|
|
|
ASSERT(processed_end && *processed_end == start);
|
|
|
|
}
|
|
|
|
|
2022-08-24 08:40:18 +08:00
|
|
|
if ((page_ops & PAGE_SET_ERROR) && start_index <= end_index)
|
2021-05-31 16:50:38 +08:00
|
|
|
mapping_set_error(mapping, -EIO);
|
|
|
|
|
2022-08-24 08:40:18 +08:00
|
|
|
folio_batch_init(&fbatch);
|
|
|
|
while (index <= end_index) {
|
|
|
|
int found_folios;
|
|
|
|
|
|
|
|
found_folios = filemap_get_folios_contig(mapping, &index,
|
|
|
|
end_index, &fbatch);
|
2021-05-31 16:50:38 +08:00
|
|
|
|
2022-08-24 08:40:18 +08:00
|
|
|
if (found_folios == 0) {
|
2021-05-31 16:50:38 +08:00
|
|
|
/*
|
|
|
|
* Only if we're going to lock these pages, we can find
|
|
|
|
* nothing at @index.
|
|
|
|
*/
|
|
|
|
ASSERT(page_ops & PAGE_LOCK);
|
|
|
|
err = -EAGAIN;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2022-08-24 08:40:18 +08:00
|
|
|
for (i = 0; i < found_folios; i++) {
|
2021-05-31 16:50:38 +08:00
|
|
|
int process_ret;
|
2022-08-24 08:40:18 +08:00
|
|
|
struct folio *folio = fbatch.folios[i];
|
2021-05-31 16:50:42 +08:00
|
|
|
process_ret = process_one_page(fs_info, mapping,
|
2022-08-24 08:40:18 +08:00
|
|
|
&folio->page, locked_page, page_ops,
|
2021-05-31 16:50:42 +08:00
|
|
|
start, end);
|
2021-05-31 16:50:38 +08:00
|
|
|
if (process_ret < 0) {
|
|
|
|
err = -EAGAIN;
|
2022-08-24 08:40:18 +08:00
|
|
|
folio_batch_release(&fbatch);
|
2021-05-31 16:50:38 +08:00
|
|
|
goto out;
|
|
|
|
}
|
2022-08-24 08:40:18 +08:00
|
|
|
pages_processed += folio_nr_pages(folio);
|
2021-05-31 16:50:38 +08:00
|
|
|
}
|
2022-08-24 08:40:18 +08:00
|
|
|
folio_batch_release(&fbatch);
|
2021-05-31 16:50:38 +08:00
|
|
|
cond_resched();
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
if (err && processed_end) {
|
|
|
|
/*
|
|
|
|
* Update @processed_end. I know this is awful since it has
|
|
|
|
* two different return value patterns (inclusive vs exclusive).
|
|
|
|
*
|
|
|
|
* But the exclusive pattern is necessary if @start is 0, or we
|
|
|
|
* underflow and check against processed_end won't work as
|
|
|
|
* expected.
|
|
|
|
*/
|
|
|
|
if (pages_processed)
|
|
|
|
*processed_end = min(end,
|
|
|
|
((u64)(start_index + pages_processed) << PAGE_SHIFT) - 1);
|
|
|
|
else
|
|
|
|
*processed_end = start;
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
2017-02-10 23:41:05 +08:00
|
|
|
|
2012-03-01 21:56:26 +08:00
|
|
|
static noinline void __unlock_for_delalloc(struct inode *inode,
|
|
|
|
struct page *locked_page,
|
|
|
|
u64 start, u64 end)
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
{
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
unsigned long index = start >> PAGE_SHIFT;
|
|
|
|
unsigned long end_index = end >> PAGE_SHIFT;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
|
2017-02-10 23:42:14 +08:00
|
|
|
ASSERT(locked_page);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
if (index == locked_page->index && end_index == index)
|
2012-03-01 21:56:26 +08:00
|
|
|
return;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
|
btrfs: pass bytenr directly to __process_pages_contig()
As a preparation for incoming subpage support, we need bytenr passed to
__process_pages_contig() directly, not the current page index.
So change the parameter and all callers to pass bytenr in.
With the modification, here we need to replace the old @index_ret with
@processed_end for __process_pages_contig(), but this brings a small
problem.
Normally we follow the inclusive return value, meaning @processed_end
should be the last byte we processed.
If parameter @start is 0, and we failed to lock any page, then we would
return @processed_end as -1, causing more problems for
__unlock_for_delalloc().
So here for @processed_end, we use two different return value patterns.
If we have locked any page, @processed_end will be the last byte of
locked page.
Or it will be @start otherwise.
This change will impact lock_delalloc_pages(), so it needs to check
@processed_end to only unlock the range if we have locked any.
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-31 16:50:37 +08:00
|
|
|
__process_pages_contig(inode->i_mapping, locked_page, start, end,
|
2017-02-10 23:42:14 +08:00
|
|
|
PAGE_UNLOCK, NULL);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static noinline int lock_delalloc_pages(struct inode *inode,
|
|
|
|
struct page *locked_page,
|
|
|
|
u64 delalloc_start,
|
|
|
|
u64 delalloc_end)
|
|
|
|
{
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
unsigned long index = delalloc_start >> PAGE_SHIFT;
|
|
|
|
unsigned long end_index = delalloc_end >> PAGE_SHIFT;
|
btrfs: pass bytenr directly to __process_pages_contig()
As a preparation for incoming subpage support, we need bytenr passed to
__process_pages_contig() directly, not the current page index.
So change the parameter and all callers to pass bytenr in.
With the modification, here we need to replace the old @index_ret with
@processed_end for __process_pages_contig(), but this brings a small
problem.
Normally we follow the inclusive return value, meaning @processed_end
should be the last byte we processed.
If parameter @start is 0, and we failed to lock any page, then we would
return @processed_end as -1, causing more problems for
__unlock_for_delalloc().
So here for @processed_end, we use two different return value patterns.
If we have locked any page, @processed_end will be the last byte of
locked page.
Or it will be @start otherwise.
This change will impact lock_delalloc_pages(), so it needs to check
@processed_end to only unlock the range if we have locked any.
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-31 16:50:37 +08:00
|
|
|
u64 processed_end = delalloc_start;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
int ret;
|
|
|
|
|
2017-02-10 23:42:14 +08:00
|
|
|
ASSERT(locked_page);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
if (index == locked_page->index && index == end_index)
|
|
|
|
return 0;
|
|
|
|
|
btrfs: pass bytenr directly to __process_pages_contig()
As a preparation for incoming subpage support, we need bytenr passed to
__process_pages_contig() directly, not the current page index.
So change the parameter and all callers to pass bytenr in.
With the modification, here we need to replace the old @index_ret with
@processed_end for __process_pages_contig(), but this brings a small
problem.
Normally we follow the inclusive return value, meaning @processed_end
should be the last byte we processed.
If parameter @start is 0, and we failed to lock any page, then we would
return @processed_end as -1, causing more problems for
__unlock_for_delalloc().
So here for @processed_end, we use two different return value patterns.
If we have locked any page, @processed_end will be the last byte of
locked page.
Or it will be @start otherwise.
This change will impact lock_delalloc_pages(), so it needs to check
@processed_end to only unlock the range if we have locked any.
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-31 16:50:37 +08:00
|
|
|
ret = __process_pages_contig(inode->i_mapping, locked_page, delalloc_start,
|
|
|
|
delalloc_end, PAGE_LOCK, &processed_end);
|
|
|
|
if (ret == -EAGAIN && processed_end > delalloc_start)
|
2017-02-10 23:42:14 +08:00
|
|
|
__unlock_for_delalloc(inode, locked_page, delalloc_start,
|
btrfs: pass bytenr directly to __process_pages_contig()
As a preparation for incoming subpage support, we need bytenr passed to
__process_pages_contig() directly, not the current page index.
So change the parameter and all callers to pass bytenr in.
With the modification, here we need to replace the old @index_ret with
@processed_end for __process_pages_contig(), but this brings a small
problem.
Normally we follow the inclusive return value, meaning @processed_end
should be the last byte we processed.
If parameter @start is 0, and we failed to lock any page, then we would
return @processed_end as -1, causing more problems for
__unlock_for_delalloc().
So here for @processed_end, we use two different return value patterns.
If we have locked any page, @processed_end will be the last byte of
locked page.
Or it will be @start otherwise.
This change will impact lock_delalloc_pages(), so it needs to check
@processed_end to only unlock the range if we have locked any.
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-31 16:50:37 +08:00
|
|
|
processed_end);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2018-11-29 11:33:38 +08:00
|
|
|
* Find and lock a contiguous range of bytes in the file marked as delalloc, no
|
btrfs: subpage: avoid potential deadlock with compression and delalloc
[BUG]
With experimental subpage compression enabled, a simple fsstress can
lead to self deadlock on page 720896:
mkfs.btrfs -f -s 4k $dev > /dev/null
mount $dev -o compress $mnt
$fsstress -p 1 -n 100 -w -d $mnt -v -s 1625511156
[CAUSE]
If we have a file layout looks like below:
0 32K 64K 96K 128K
|//| |///////////////|
4K
Then we run delalloc range for the inode, it will:
- Call find_lock_delalloc_range() with @delalloc_start = 0
Then we got a delalloc range [0, 4K).
This range will be COWed.
- Call find_lock_delalloc_range() again with @delalloc_start = 4K
Since find_lock_delalloc_range() never cares whether the range
is still inside page range [0, 64K), it will return range [64K, 128K).
This range meets the condition for subpage compression, will go
through async COW path.
And async COW path will return @page_started.
But that @page_started is now for range [64K, 128K), not for range
[0, 64K).
- writepage_dellloc() returned 1 for page [0, 64K)
Thus page [0, 64K) will not be unlocked, nor its page dirty status
will be cleared.
Next time when we try to lock page [0, 64K) we will deadlock, as there
is no one to release page [0, 64K).
This problem will never happen for regular page size as one page only
contains one sector. After the first find_lock_delalloc_range() call,
the @delalloc_end will go beyond @page_end no matter if we found a
delalloc range or not
Thus this bug only happens for subpage, as now we need multiple runs to
exhaust the delalloc range of a page.
[FIX]
Fix the problem by ensuring the delalloc range we ran at least started
inside @locked_page.
So that we will never get incorrect @page_started.
And to prevent such problem from happening again:
- Make find_lock_delalloc_range() return false if the found range is
beyond @end value passed in.
Since @end will be utilized now, add an ASSERT() to ensure we pass
correct @end into find_lock_delalloc_range().
This also means, for selftests we needs to populate @end before calling
find_lock_delalloc_range().
- New ASSERT() in find_lock_delalloc_range()
Now we will make sure the @start/@end passed in at least covers part
of the page.
- New ASSERT() in run_delalloc_range()
To make sure the range at least starts inside @locked page.
- Use @delalloc_start as proper cursor, while @delalloc_end is always
reset to @page_end.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:22:07 +08:00
|
|
|
* more than @max_bytes.
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
*
|
btrfs: subpage: avoid potential deadlock with compression and delalloc
[BUG]
With experimental subpage compression enabled, a simple fsstress can
lead to self deadlock on page 720896:
mkfs.btrfs -f -s 4k $dev > /dev/null
mount $dev -o compress $mnt
$fsstress -p 1 -n 100 -w -d $mnt -v -s 1625511156
[CAUSE]
If we have a file layout looks like below:
0 32K 64K 96K 128K
|//| |///////////////|
4K
Then we run delalloc range for the inode, it will:
- Call find_lock_delalloc_range() with @delalloc_start = 0
Then we got a delalloc range [0, 4K).
This range will be COWed.
- Call find_lock_delalloc_range() again with @delalloc_start = 4K
Since find_lock_delalloc_range() never cares whether the range
is still inside page range [0, 64K), it will return range [64K, 128K).
This range meets the condition for subpage compression, will go
through async COW path.
And async COW path will return @page_started.
But that @page_started is now for range [64K, 128K), not for range
[0, 64K).
- writepage_dellloc() returned 1 for page [0, 64K)
Thus page [0, 64K) will not be unlocked, nor its page dirty status
will be cleared.
Next time when we try to lock page [0, 64K) we will deadlock, as there
is no one to release page [0, 64K).
This problem will never happen for regular page size as one page only
contains one sector. After the first find_lock_delalloc_range() call,
the @delalloc_end will go beyond @page_end no matter if we found a
delalloc range or not
Thus this bug only happens for subpage, as now we need multiple runs to
exhaust the delalloc range of a page.
[FIX]
Fix the problem by ensuring the delalloc range we ran at least started
inside @locked_page.
So that we will never get incorrect @page_started.
And to prevent such problem from happening again:
- Make find_lock_delalloc_range() return false if the found range is
beyond @end value passed in.
Since @end will be utilized now, add an ASSERT() to ensure we pass
correct @end into find_lock_delalloc_range().
This also means, for selftests we needs to populate @end before calling
find_lock_delalloc_range().
- New ASSERT() in find_lock_delalloc_range()
Now we will make sure the @start/@end passed in at least covers part
of the page.
- New ASSERT() in run_delalloc_range()
To make sure the range at least starts inside @locked page.
- Use @delalloc_start as proper cursor, while @delalloc_end is always
reset to @page_end.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:22:07 +08:00
|
|
|
* @start: The original start bytenr to search.
|
|
|
|
* Will store the extent range start bytenr.
|
|
|
|
* @end: The original end bytenr of the search range
|
|
|
|
* Will store the extent range end bytenr.
|
|
|
|
*
|
|
|
|
* Return true if we find a delalloc range which starts inside the original
|
|
|
|
* range, and @start/@end will store the delalloc range start/end.
|
|
|
|
*
|
|
|
|
* Return false if we can't find any delalloc range which starts inside the
|
|
|
|
* original range, and @start/@end will be the non-delalloc range start/end.
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
*/
|
2018-11-19 17:38:17 +08:00
|
|
|
EXPORT_FOR_TESTS
|
2018-11-29 11:33:38 +08:00
|
|
|
noinline_for_stack bool find_lock_delalloc_range(struct inode *inode,
|
2013-10-10 00:00:56 +08:00
|
|
|
struct page *locked_page, u64 *start,
|
2018-10-26 19:43:20 +08:00
|
|
|
u64 *end)
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
{
|
btrfs: replace BTRFS_MAX_EXTENT_SIZE with fs_info->max_extent_size
On zoned filesystem, data write out is limited by max_zone_append_size,
and a large ordered extent is split according the size of a bio. OTOH,
the number of extents to be written is calculated using
BTRFS_MAX_EXTENT_SIZE, and that estimated number is used to reserve the
metadata bytes to update and/or create the metadata items.
The metadata reservation is done at e.g, btrfs_buffered_write() and then
released according to the estimation changes. Thus, if the number of extent
increases massively, the reserved metadata can run out.
The increase of the number of extents easily occurs on zoned filesystem
if BTRFS_MAX_EXTENT_SIZE > max_zone_append_size. And, it causes the
following warning on a small RAM environment with disabling metadata
over-commit (in the following patch).
[75721.498492] ------------[ cut here ]------------
[75721.505624] BTRFS: block rsv 1 returned -28
[75721.512230] WARNING: CPU: 24 PID: 2327559 at fs/btrfs/block-rsv.c:537 btrfs_use_block_rsv+0x560/0x760 [btrfs]
[75721.581854] CPU: 24 PID: 2327559 Comm: kworker/u64:10 Kdump: loaded Tainted: G W 5.18.0-rc2-BTRFS-ZNS+ #109
[75721.597200] Hardware name: Supermicro Super Server/H12SSL-NT, BIOS 2.0 02/22/2021
[75721.607310] Workqueue: btrfs-endio-write btrfs_work_helper [btrfs]
[75721.616209] RIP: 0010:btrfs_use_block_rsv+0x560/0x760 [btrfs]
[75721.646649] RSP: 0018:ffffc9000fbdf3e0 EFLAGS: 00010286
[75721.654126] RAX: 0000000000000000 RBX: 0000000000004000 RCX: 0000000000000000
[75721.663524] RDX: 0000000000000004 RSI: 0000000000000008 RDI: fffff52001f7be6e
[75721.672921] RBP: ffffc9000fbdf420 R08: 0000000000000001 R09: ffff889f8d1fc6c7
[75721.682493] R10: ffffed13f1a3f8d8 R11: 0000000000000001 R12: ffff88980a3c0e28
[75721.692284] R13: ffff889b66590000 R14: ffff88980a3c0e40 R15: ffff88980a3c0e8a
[75721.701878] FS: 0000000000000000(0000) GS:ffff889f8d000000(0000) knlGS:0000000000000000
[75721.712601] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[75721.720726] CR2: 000055d12e05c018 CR3: 0000800193594000 CR4: 0000000000350ee0
[75721.730499] Call Trace:
[75721.735166] <TASK>
[75721.739886] btrfs_alloc_tree_block+0x1e1/0x1100 [btrfs]
[75721.747545] ? btrfs_alloc_logged_file_extent+0x550/0x550 [btrfs]
[75721.756145] ? btrfs_get_32+0xea/0x2d0 [btrfs]
[75721.762852] ? btrfs_get_32+0xea/0x2d0 [btrfs]
[75721.769520] ? push_leaf_left+0x420/0x620 [btrfs]
[75721.776431] ? memcpy+0x4e/0x60
[75721.781931] split_leaf+0x433/0x12d0 [btrfs]
[75721.788392] ? btrfs_get_token_32+0x580/0x580 [btrfs]
[75721.795636] ? push_for_double_split.isra.0+0x420/0x420 [btrfs]
[75721.803759] ? leaf_space_used+0x15d/0x1a0 [btrfs]
[75721.811156] btrfs_search_slot+0x1bc3/0x2790 [btrfs]
[75721.818300] ? lock_downgrade+0x7c0/0x7c0
[75721.824411] ? free_extent_buffer.part.0+0x107/0x200 [btrfs]
[75721.832456] ? split_leaf+0x12d0/0x12d0 [btrfs]
[75721.839149] ? free_extent_buffer.part.0+0x14f/0x200 [btrfs]
[75721.846945] ? free_extent_buffer+0x13/0x20 [btrfs]
[75721.853960] ? btrfs_release_path+0x4b/0x190 [btrfs]
[75721.861429] btrfs_csum_file_blocks+0x85c/0x1500 [btrfs]
[75721.869313] ? rcu_read_lock_sched_held+0x16/0x80
[75721.876085] ? lock_release+0x552/0xf80
[75721.881957] ? btrfs_del_csums+0x8c0/0x8c0 [btrfs]
[75721.888886] ? __kasan_check_write+0x14/0x20
[75721.895152] ? do_raw_read_unlock+0x44/0x80
[75721.901323] ? _raw_write_lock_irq+0x60/0x80
[75721.907983] ? btrfs_global_root+0xb9/0xe0 [btrfs]
[75721.915166] ? btrfs_csum_root+0x12b/0x180 [btrfs]
[75721.921918] ? btrfs_get_global_root+0x820/0x820 [btrfs]
[75721.929166] ? _raw_write_unlock+0x23/0x40
[75721.935116] ? unpin_extent_cache+0x1e3/0x390 [btrfs]
[75721.942041] btrfs_finish_ordered_io.isra.0+0xa0c/0x1dc0 [btrfs]
[75721.949906] ? try_to_wake_up+0x30/0x14a0
[75721.955700] ? btrfs_unlink_subvol+0xda0/0xda0 [btrfs]
[75721.962661] ? rcu_read_lock_sched_held+0x16/0x80
[75721.969111] ? lock_acquire+0x41b/0x4c0
[75721.974982] finish_ordered_fn+0x15/0x20 [btrfs]
[75721.981639] btrfs_work_helper+0x1af/0xa80 [btrfs]
[75721.988184] ? _raw_spin_unlock_irq+0x28/0x50
[75721.994643] process_one_work+0x815/0x1460
[75722.000444] ? pwq_dec_nr_in_flight+0x250/0x250
[75722.006643] ? do_raw_spin_trylock+0xbb/0x190
[75722.013086] worker_thread+0x59a/0xeb0
[75722.018511] kthread+0x2ac/0x360
[75722.023428] ? process_one_work+0x1460/0x1460
[75722.029431] ? kthread_complete_and_exit+0x30/0x30
[75722.036044] ret_from_fork+0x22/0x30
[75722.041255] </TASK>
[75722.045047] irq event stamp: 0
[75722.049703] hardirqs last enabled at (0): [<0000000000000000>] 0x0
[75722.057610] hardirqs last disabled at (0): [<ffffffff8118a94a>] copy_process+0x1c1a/0x66b0
[75722.067533] softirqs last enabled at (0): [<ffffffff8118a989>] copy_process+0x1c59/0x66b0
[75722.077423] softirqs last disabled at (0): [<0000000000000000>] 0x0
[75722.085335] ---[ end trace 0000000000000000 ]---
To fix the estimation, we need to introduce fs_info->max_extent_size to
replace BTRFS_MAX_EXTENT_SIZE, which allow setting the different size for
regular vs zoned filesystem.
Set fs_info->max_extent_size to BTRFS_MAX_EXTENT_SIZE by default. On zoned
filesystem, it is set to fs_info->max_zone_append_size.
CC: stable@vger.kernel.org # 5.12+
Fixes: d8e3fb106f39 ("btrfs: zoned: use ZONE_APPEND write for zoned mode")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-07-09 07:18:40 +08:00
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
|
2019-06-21 23:02:54 +08:00
|
|
|
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
|
btrfs: subpage: avoid potential deadlock with compression and delalloc
[BUG]
With experimental subpage compression enabled, a simple fsstress can
lead to self deadlock on page 720896:
mkfs.btrfs -f -s 4k $dev > /dev/null
mount $dev -o compress $mnt
$fsstress -p 1 -n 100 -w -d $mnt -v -s 1625511156
[CAUSE]
If we have a file layout looks like below:
0 32K 64K 96K 128K
|//| |///////////////|
4K
Then we run delalloc range for the inode, it will:
- Call find_lock_delalloc_range() with @delalloc_start = 0
Then we got a delalloc range [0, 4K).
This range will be COWed.
- Call find_lock_delalloc_range() again with @delalloc_start = 4K
Since find_lock_delalloc_range() never cares whether the range
is still inside page range [0, 64K), it will return range [64K, 128K).
This range meets the condition for subpage compression, will go
through async COW path.
And async COW path will return @page_started.
But that @page_started is now for range [64K, 128K), not for range
[0, 64K).
- writepage_dellloc() returned 1 for page [0, 64K)
Thus page [0, 64K) will not be unlocked, nor its page dirty status
will be cleared.
Next time when we try to lock page [0, 64K) we will deadlock, as there
is no one to release page [0, 64K).
This problem will never happen for regular page size as one page only
contains one sector. After the first find_lock_delalloc_range() call,
the @delalloc_end will go beyond @page_end no matter if we found a
delalloc range or not
Thus this bug only happens for subpage, as now we need multiple runs to
exhaust the delalloc range of a page.
[FIX]
Fix the problem by ensuring the delalloc range we ran at least started
inside @locked_page.
So that we will never get incorrect @page_started.
And to prevent such problem from happening again:
- Make find_lock_delalloc_range() return false if the found range is
beyond @end value passed in.
Since @end will be utilized now, add an ASSERT() to ensure we pass
correct @end into find_lock_delalloc_range().
This also means, for selftests we needs to populate @end before calling
find_lock_delalloc_range().
- New ASSERT() in find_lock_delalloc_range()
Now we will make sure the @start/@end passed in at least covers part
of the page.
- New ASSERT() in run_delalloc_range()
To make sure the range at least starts inside @locked page.
- Use @delalloc_start as proper cursor, while @delalloc_end is always
reset to @page_end.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:22:07 +08:00
|
|
|
const u64 orig_start = *start;
|
|
|
|
const u64 orig_end = *end;
|
btrfs: replace BTRFS_MAX_EXTENT_SIZE with fs_info->max_extent_size
On zoned filesystem, data write out is limited by max_zone_append_size,
and a large ordered extent is split according the size of a bio. OTOH,
the number of extents to be written is calculated using
BTRFS_MAX_EXTENT_SIZE, and that estimated number is used to reserve the
metadata bytes to update and/or create the metadata items.
The metadata reservation is done at e.g, btrfs_buffered_write() and then
released according to the estimation changes. Thus, if the number of extent
increases massively, the reserved metadata can run out.
The increase of the number of extents easily occurs on zoned filesystem
if BTRFS_MAX_EXTENT_SIZE > max_zone_append_size. And, it causes the
following warning on a small RAM environment with disabling metadata
over-commit (in the following patch).
[75721.498492] ------------[ cut here ]------------
[75721.505624] BTRFS: block rsv 1 returned -28
[75721.512230] WARNING: CPU: 24 PID: 2327559 at fs/btrfs/block-rsv.c:537 btrfs_use_block_rsv+0x560/0x760 [btrfs]
[75721.581854] CPU: 24 PID: 2327559 Comm: kworker/u64:10 Kdump: loaded Tainted: G W 5.18.0-rc2-BTRFS-ZNS+ #109
[75721.597200] Hardware name: Supermicro Super Server/H12SSL-NT, BIOS 2.0 02/22/2021
[75721.607310] Workqueue: btrfs-endio-write btrfs_work_helper [btrfs]
[75721.616209] RIP: 0010:btrfs_use_block_rsv+0x560/0x760 [btrfs]
[75721.646649] RSP: 0018:ffffc9000fbdf3e0 EFLAGS: 00010286
[75721.654126] RAX: 0000000000000000 RBX: 0000000000004000 RCX: 0000000000000000
[75721.663524] RDX: 0000000000000004 RSI: 0000000000000008 RDI: fffff52001f7be6e
[75721.672921] RBP: ffffc9000fbdf420 R08: 0000000000000001 R09: ffff889f8d1fc6c7
[75721.682493] R10: ffffed13f1a3f8d8 R11: 0000000000000001 R12: ffff88980a3c0e28
[75721.692284] R13: ffff889b66590000 R14: ffff88980a3c0e40 R15: ffff88980a3c0e8a
[75721.701878] FS: 0000000000000000(0000) GS:ffff889f8d000000(0000) knlGS:0000000000000000
[75721.712601] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[75721.720726] CR2: 000055d12e05c018 CR3: 0000800193594000 CR4: 0000000000350ee0
[75721.730499] Call Trace:
[75721.735166] <TASK>
[75721.739886] btrfs_alloc_tree_block+0x1e1/0x1100 [btrfs]
[75721.747545] ? btrfs_alloc_logged_file_extent+0x550/0x550 [btrfs]
[75721.756145] ? btrfs_get_32+0xea/0x2d0 [btrfs]
[75721.762852] ? btrfs_get_32+0xea/0x2d0 [btrfs]
[75721.769520] ? push_leaf_left+0x420/0x620 [btrfs]
[75721.776431] ? memcpy+0x4e/0x60
[75721.781931] split_leaf+0x433/0x12d0 [btrfs]
[75721.788392] ? btrfs_get_token_32+0x580/0x580 [btrfs]
[75721.795636] ? push_for_double_split.isra.0+0x420/0x420 [btrfs]
[75721.803759] ? leaf_space_used+0x15d/0x1a0 [btrfs]
[75721.811156] btrfs_search_slot+0x1bc3/0x2790 [btrfs]
[75721.818300] ? lock_downgrade+0x7c0/0x7c0
[75721.824411] ? free_extent_buffer.part.0+0x107/0x200 [btrfs]
[75721.832456] ? split_leaf+0x12d0/0x12d0 [btrfs]
[75721.839149] ? free_extent_buffer.part.0+0x14f/0x200 [btrfs]
[75721.846945] ? free_extent_buffer+0x13/0x20 [btrfs]
[75721.853960] ? btrfs_release_path+0x4b/0x190 [btrfs]
[75721.861429] btrfs_csum_file_blocks+0x85c/0x1500 [btrfs]
[75721.869313] ? rcu_read_lock_sched_held+0x16/0x80
[75721.876085] ? lock_release+0x552/0xf80
[75721.881957] ? btrfs_del_csums+0x8c0/0x8c0 [btrfs]
[75721.888886] ? __kasan_check_write+0x14/0x20
[75721.895152] ? do_raw_read_unlock+0x44/0x80
[75721.901323] ? _raw_write_lock_irq+0x60/0x80
[75721.907983] ? btrfs_global_root+0xb9/0xe0 [btrfs]
[75721.915166] ? btrfs_csum_root+0x12b/0x180 [btrfs]
[75721.921918] ? btrfs_get_global_root+0x820/0x820 [btrfs]
[75721.929166] ? _raw_write_unlock+0x23/0x40
[75721.935116] ? unpin_extent_cache+0x1e3/0x390 [btrfs]
[75721.942041] btrfs_finish_ordered_io.isra.0+0xa0c/0x1dc0 [btrfs]
[75721.949906] ? try_to_wake_up+0x30/0x14a0
[75721.955700] ? btrfs_unlink_subvol+0xda0/0xda0 [btrfs]
[75721.962661] ? rcu_read_lock_sched_held+0x16/0x80
[75721.969111] ? lock_acquire+0x41b/0x4c0
[75721.974982] finish_ordered_fn+0x15/0x20 [btrfs]
[75721.981639] btrfs_work_helper+0x1af/0xa80 [btrfs]
[75721.988184] ? _raw_spin_unlock_irq+0x28/0x50
[75721.994643] process_one_work+0x815/0x1460
[75722.000444] ? pwq_dec_nr_in_flight+0x250/0x250
[75722.006643] ? do_raw_spin_trylock+0xbb/0x190
[75722.013086] worker_thread+0x59a/0xeb0
[75722.018511] kthread+0x2ac/0x360
[75722.023428] ? process_one_work+0x1460/0x1460
[75722.029431] ? kthread_complete_and_exit+0x30/0x30
[75722.036044] ret_from_fork+0x22/0x30
[75722.041255] </TASK>
[75722.045047] irq event stamp: 0
[75722.049703] hardirqs last enabled at (0): [<0000000000000000>] 0x0
[75722.057610] hardirqs last disabled at (0): [<ffffffff8118a94a>] copy_process+0x1c1a/0x66b0
[75722.067533] softirqs last enabled at (0): [<ffffffff8118a989>] copy_process+0x1c59/0x66b0
[75722.077423] softirqs last disabled at (0): [<0000000000000000>] 0x0
[75722.085335] ---[ end trace 0000000000000000 ]---
To fix the estimation, we need to introduce fs_info->max_extent_size to
replace BTRFS_MAX_EXTENT_SIZE, which allow setting the different size for
regular vs zoned filesystem.
Set fs_info->max_extent_size to BTRFS_MAX_EXTENT_SIZE by default. On zoned
filesystem, it is set to fs_info->max_zone_append_size.
CC: stable@vger.kernel.org # 5.12+
Fixes: d8e3fb106f39 ("btrfs: zoned: use ZONE_APPEND write for zoned mode")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-07-09 07:18:40 +08:00
|
|
|
/* The sanity tests may not set a valid fs_info. */
|
|
|
|
u64 max_bytes = fs_info ? fs_info->max_extent_size : BTRFS_MAX_EXTENT_SIZE;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
u64 delalloc_start;
|
|
|
|
u64 delalloc_end;
|
2018-11-29 11:33:38 +08:00
|
|
|
bool found;
|
2009-09-03 03:22:30 +08:00
|
|
|
struct extent_state *cached_state = NULL;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
int ret;
|
|
|
|
int loops = 0;
|
|
|
|
|
btrfs: subpage: avoid potential deadlock with compression and delalloc
[BUG]
With experimental subpage compression enabled, a simple fsstress can
lead to self deadlock on page 720896:
mkfs.btrfs -f -s 4k $dev > /dev/null
mount $dev -o compress $mnt
$fsstress -p 1 -n 100 -w -d $mnt -v -s 1625511156
[CAUSE]
If we have a file layout looks like below:
0 32K 64K 96K 128K
|//| |///////////////|
4K
Then we run delalloc range for the inode, it will:
- Call find_lock_delalloc_range() with @delalloc_start = 0
Then we got a delalloc range [0, 4K).
This range will be COWed.
- Call find_lock_delalloc_range() again with @delalloc_start = 4K
Since find_lock_delalloc_range() never cares whether the range
is still inside page range [0, 64K), it will return range [64K, 128K).
This range meets the condition for subpage compression, will go
through async COW path.
And async COW path will return @page_started.
But that @page_started is now for range [64K, 128K), not for range
[0, 64K).
- writepage_dellloc() returned 1 for page [0, 64K)
Thus page [0, 64K) will not be unlocked, nor its page dirty status
will be cleared.
Next time when we try to lock page [0, 64K) we will deadlock, as there
is no one to release page [0, 64K).
This problem will never happen for regular page size as one page only
contains one sector. After the first find_lock_delalloc_range() call,
the @delalloc_end will go beyond @page_end no matter if we found a
delalloc range or not
Thus this bug only happens for subpage, as now we need multiple runs to
exhaust the delalloc range of a page.
[FIX]
Fix the problem by ensuring the delalloc range we ran at least started
inside @locked_page.
So that we will never get incorrect @page_started.
And to prevent such problem from happening again:
- Make find_lock_delalloc_range() return false if the found range is
beyond @end value passed in.
Since @end will be utilized now, add an ASSERT() to ensure we pass
correct @end into find_lock_delalloc_range().
This also means, for selftests we needs to populate @end before calling
find_lock_delalloc_range().
- New ASSERT() in find_lock_delalloc_range()
Now we will make sure the @start/@end passed in at least covers part
of the page.
- New ASSERT() in run_delalloc_range()
To make sure the range at least starts inside @locked page.
- Use @delalloc_start as proper cursor, while @delalloc_end is always
reset to @page_end.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:22:07 +08:00
|
|
|
/* Caller should pass a valid @end to indicate the search range end */
|
|
|
|
ASSERT(orig_end > orig_start);
|
|
|
|
|
|
|
|
/* The range should at least cover part of the page */
|
|
|
|
ASSERT(!(orig_start >= page_offset(locked_page) + PAGE_SIZE ||
|
|
|
|
orig_end <= page_offset(locked_page)));
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
again:
|
|
|
|
/* step one, find a bunch of delalloc bytes starting at start */
|
|
|
|
delalloc_start = *start;
|
|
|
|
delalloc_end = 0;
|
2019-09-23 22:05:20 +08:00
|
|
|
found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end,
|
|
|
|
max_bytes, &cached_state);
|
btrfs: subpage: avoid potential deadlock with compression and delalloc
[BUG]
With experimental subpage compression enabled, a simple fsstress can
lead to self deadlock on page 720896:
mkfs.btrfs -f -s 4k $dev > /dev/null
mount $dev -o compress $mnt
$fsstress -p 1 -n 100 -w -d $mnt -v -s 1625511156
[CAUSE]
If we have a file layout looks like below:
0 32K 64K 96K 128K
|//| |///////////////|
4K
Then we run delalloc range for the inode, it will:
- Call find_lock_delalloc_range() with @delalloc_start = 0
Then we got a delalloc range [0, 4K).
This range will be COWed.
- Call find_lock_delalloc_range() again with @delalloc_start = 4K
Since find_lock_delalloc_range() never cares whether the range
is still inside page range [0, 64K), it will return range [64K, 128K).
This range meets the condition for subpage compression, will go
through async COW path.
And async COW path will return @page_started.
But that @page_started is now for range [64K, 128K), not for range
[0, 64K).
- writepage_dellloc() returned 1 for page [0, 64K)
Thus page [0, 64K) will not be unlocked, nor its page dirty status
will be cleared.
Next time when we try to lock page [0, 64K) we will deadlock, as there
is no one to release page [0, 64K).
This problem will never happen for regular page size as one page only
contains one sector. After the first find_lock_delalloc_range() call,
the @delalloc_end will go beyond @page_end no matter if we found a
delalloc range or not
Thus this bug only happens for subpage, as now we need multiple runs to
exhaust the delalloc range of a page.
[FIX]
Fix the problem by ensuring the delalloc range we ran at least started
inside @locked_page.
So that we will never get incorrect @page_started.
And to prevent such problem from happening again:
- Make find_lock_delalloc_range() return false if the found range is
beyond @end value passed in.
Since @end will be utilized now, add an ASSERT() to ensure we pass
correct @end into find_lock_delalloc_range().
This also means, for selftests we needs to populate @end before calling
find_lock_delalloc_range().
- New ASSERT() in find_lock_delalloc_range()
Now we will make sure the @start/@end passed in at least covers part
of the page.
- New ASSERT() in run_delalloc_range()
To make sure the range at least starts inside @locked page.
- Use @delalloc_start as proper cursor, while @delalloc_end is always
reset to @page_end.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:22:07 +08:00
|
|
|
if (!found || delalloc_end <= *start || delalloc_start > orig_end) {
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
*start = delalloc_start;
|
btrfs: subpage: avoid potential deadlock with compression and delalloc
[BUG]
With experimental subpage compression enabled, a simple fsstress can
lead to self deadlock on page 720896:
mkfs.btrfs -f -s 4k $dev > /dev/null
mount $dev -o compress $mnt
$fsstress -p 1 -n 100 -w -d $mnt -v -s 1625511156
[CAUSE]
If we have a file layout looks like below:
0 32K 64K 96K 128K
|//| |///////////////|
4K
Then we run delalloc range for the inode, it will:
- Call find_lock_delalloc_range() with @delalloc_start = 0
Then we got a delalloc range [0, 4K).
This range will be COWed.
- Call find_lock_delalloc_range() again with @delalloc_start = 4K
Since find_lock_delalloc_range() never cares whether the range
is still inside page range [0, 64K), it will return range [64K, 128K).
This range meets the condition for subpage compression, will go
through async COW path.
And async COW path will return @page_started.
But that @page_started is now for range [64K, 128K), not for range
[0, 64K).
- writepage_dellloc() returned 1 for page [0, 64K)
Thus page [0, 64K) will not be unlocked, nor its page dirty status
will be cleared.
Next time when we try to lock page [0, 64K) we will deadlock, as there
is no one to release page [0, 64K).
This problem will never happen for regular page size as one page only
contains one sector. After the first find_lock_delalloc_range() call,
the @delalloc_end will go beyond @page_end no matter if we found a
delalloc range or not
Thus this bug only happens for subpage, as now we need multiple runs to
exhaust the delalloc range of a page.
[FIX]
Fix the problem by ensuring the delalloc range we ran at least started
inside @locked_page.
So that we will never get incorrect @page_started.
And to prevent such problem from happening again:
- Make find_lock_delalloc_range() return false if the found range is
beyond @end value passed in.
Since @end will be utilized now, add an ASSERT() to ensure we pass
correct @end into find_lock_delalloc_range().
This also means, for selftests we needs to populate @end before calling
find_lock_delalloc_range().
- New ASSERT() in find_lock_delalloc_range()
Now we will make sure the @start/@end passed in at least covers part
of the page.
- New ASSERT() in run_delalloc_range()
To make sure the range at least starts inside @locked page.
- Use @delalloc_start as proper cursor, while @delalloc_end is always
reset to @page_end.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:22:07 +08:00
|
|
|
|
|
|
|
/* @delalloc_end can be -1, never go beyond @orig_end */
|
|
|
|
*end = min(delalloc_end, orig_end);
|
2010-02-03 05:19:11 +08:00
|
|
|
free_extent_state(cached_state);
|
2018-11-29 11:33:38 +08:00
|
|
|
return false;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
}
|
|
|
|
|
2008-11-01 00:46:39 +08:00
|
|
|
/*
|
|
|
|
* start comes from the offset of locked_page. We have to lock
|
|
|
|
* pages in order, so we can't process delalloc bytes before
|
|
|
|
* locked_page
|
|
|
|
*/
|
2009-01-06 10:25:51 +08:00
|
|
|
if (delalloc_start < *start)
|
2008-11-01 00:46:39 +08:00
|
|
|
delalloc_start = *start;
|
|
|
|
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
/*
|
|
|
|
* make sure to limit the number of pages we try to lock down
|
|
|
|
*/
|
2013-10-08 10:11:09 +08:00
|
|
|
if (delalloc_end + 1 - delalloc_start > max_bytes)
|
|
|
|
delalloc_end = delalloc_start + max_bytes - 1;
|
2009-01-06 10:25:51 +08:00
|
|
|
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
/* step two, lock all the pages after the page that has start */
|
|
|
|
ret = lock_delalloc_pages(inode, locked_page,
|
|
|
|
delalloc_start, delalloc_end);
|
2018-10-26 19:43:21 +08:00
|
|
|
ASSERT(!ret || ret == -EAGAIN);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
if (ret == -EAGAIN) {
|
|
|
|
/* some of the pages are gone, lets avoid looping by
|
|
|
|
* shortening the size of the delalloc range we're searching
|
|
|
|
*/
|
2009-09-03 03:22:30 +08:00
|
|
|
free_extent_state(cached_state);
|
2014-05-21 20:49:54 +08:00
|
|
|
cached_state = NULL;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
if (!loops) {
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
max_bytes = PAGE_SIZE;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
loops = 1;
|
|
|
|
goto again;
|
|
|
|
} else {
|
2018-11-29 11:33:38 +08:00
|
|
|
found = false;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
goto out_failed;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* step three, lock the state bits for the whole range */
|
2022-09-10 05:53:43 +08:00
|
|
|
lock_extent(tree, delalloc_start, delalloc_end, &cached_state);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
|
|
|
|
/* then test to make sure it is all still delalloc */
|
|
|
|
ret = test_range_bit(tree, delalloc_start, delalloc_end,
|
2009-09-03 03:22:30 +08:00
|
|
|
EXTENT_DELALLOC, 1, cached_state);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
if (!ret) {
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(tree, delalloc_start, delalloc_end,
|
|
|
|
&cached_state);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
__unlock_for_delalloc(inode, locked_page,
|
|
|
|
delalloc_start, delalloc_end);
|
|
|
|
cond_resched();
|
|
|
|
goto again;
|
|
|
|
}
|
2009-09-03 03:22:30 +08:00
|
|
|
free_extent_state(cached_state);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
*start = delalloc_start;
|
|
|
|
*end = delalloc_end;
|
|
|
|
out_failed:
|
|
|
|
return found;
|
|
|
|
}
|
|
|
|
|
2020-06-03 13:55:06 +08:00
|
|
|
void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
|
2019-07-17 21:18:16 +08:00
|
|
|
struct page *locked_page,
|
2020-11-13 20:51:40 +08:00
|
|
|
u32 clear_bits, unsigned long page_ops)
|
2017-02-03 09:49:22 +08:00
|
|
|
{
|
2022-09-10 05:53:47 +08:00
|
|
|
clear_extent_bit(&inode->io_tree, start, end, clear_bits, NULL);
|
2017-02-03 09:49:22 +08:00
|
|
|
|
2020-06-03 13:55:06 +08:00
|
|
|
__process_pages_contig(inode->vfs_inode.i_mapping, locked_page,
|
btrfs: pass bytenr directly to __process_pages_contig()
As a preparation for incoming subpage support, we need bytenr passed to
__process_pages_contig() directly, not the current page index.
So change the parameter and all callers to pass bytenr in.
With the modification, here we need to replace the old @index_ret with
@processed_end for __process_pages_contig(), but this brings a small
problem.
Normally we follow the inclusive return value, meaning @processed_end
should be the last byte we processed.
If parameter @start is 0, and we failed to lock any page, then we would
return @processed_end as -1, causing more problems for
__unlock_for_delalloc().
So here for @processed_end, we use two different return value patterns.
If we have locked any page, @processed_end will be the last byte of
locked page.
Or it will be @start otherwise.
This change will impact lock_delalloc_pages(), so it needs to check
@processed_end to only unlock the range if we have locked any.
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-31 16:50:37 +08:00
|
|
|
start, end, page_ops, NULL);
|
2017-02-03 09:49:22 +08:00
|
|
|
}
|
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
static int insert_failrec(struct btrfs_inode *inode,
|
|
|
|
struct io_failure_record *failrec)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2022-09-10 05:53:16 +08:00
|
|
|
struct rb_node *exist;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
spin_lock(&inode->io_failure_lock);
|
|
|
|
exist = rb_simple_insert(&inode->io_failure_tree, failrec->bytenr,
|
|
|
|
&failrec->rb_node);
|
|
|
|
spin_unlock(&inode->io_failure_lock);
|
|
|
|
|
|
|
|
return (exist == NULL) ? 0 : -EEXIST;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
static struct io_failure_record *get_failrec(struct btrfs_inode *inode, u64 start)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
struct rb_node *node;
|
2022-09-10 05:53:16 +08:00
|
|
|
struct io_failure_record *failrec = ERR_PTR(-ENOENT);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
spin_lock(&inode->io_failure_lock);
|
|
|
|
node = rb_simple_search(&inode->io_failure_tree, start);
|
|
|
|
if (node)
|
|
|
|
failrec = rb_entry(node, struct io_failure_record, rb_node);
|
|
|
|
spin_unlock(&inode->io_failure_lock);
|
2020-07-02 20:23:28 +08:00
|
|
|
return failrec;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2022-09-07 19:17:41 +08:00
|
|
|
static void free_io_failure(struct btrfs_inode *inode,
|
|
|
|
struct io_failure_record *rec)
|
2011-07-22 21:41:52 +08:00
|
|
|
{
|
2022-09-10 05:53:16 +08:00
|
|
|
spin_lock(&inode->io_failure_lock);
|
|
|
|
rb_erase(&rec->rb_node, &inode->io_failure_tree);
|
|
|
|
spin_unlock(&inode->io_failure_lock);
|
2011-07-22 21:41:52 +08:00
|
|
|
|
|
|
|
kfree(rec);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* this bypasses the standard btrfs submit functions deliberately, as
|
|
|
|
* the standard behavior is to write all copies in a raid setup. here we only
|
|
|
|
* want to write the one bad copy. so we do the mapping for ourselves and issue
|
|
|
|
* submit_bio directly.
|
2012-11-05 22:46:42 +08:00
|
|
|
* to avoid any synchronization issues, wait for the data after writing, which
|
2011-07-22 21:41:52 +08:00
|
|
|
* actually prevents the read that triggered the error from finishing.
|
|
|
|
* currently, there can be no more than two copies of every data bit. thus,
|
|
|
|
* exactly one rewrite is required.
|
|
|
|
*/
|
2021-09-03 20:45:14 +08:00
|
|
|
static int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
|
|
|
|
u64 length, u64 logical, struct page *page,
|
|
|
|
unsigned int pg_offset, int mirror_num)
|
2011-07-22 21:41:52 +08:00
|
|
|
{
|
|
|
|
struct btrfs_device *dev;
|
2022-04-04 12:45:20 +08:00
|
|
|
struct bio_vec bvec;
|
|
|
|
struct bio bio;
|
2011-07-22 21:41:52 +08:00
|
|
|
u64 map_length = 0;
|
|
|
|
u64 sector;
|
2021-09-15 15:17:16 +08:00
|
|
|
struct btrfs_io_context *bioc = NULL;
|
2022-04-04 12:45:20 +08:00
|
|
|
int ret = 0;
|
2011-07-22 21:41:52 +08:00
|
|
|
|
2017-11-28 05:05:09 +08:00
|
|
|
ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
|
2011-07-22 21:41:52 +08:00
|
|
|
BUG_ON(!mirror_num);
|
|
|
|
|
2021-12-07 22:28:36 +08:00
|
|
|
if (btrfs_repair_one_zone(fs_info, logical))
|
|
|
|
return 0;
|
btrfs: zoned: relocate block group to repair IO failure in zoned filesystems
When a bad checksum is found and if the filesystem has a mirror of the
damaged data, we read the correct data from the mirror and writes it to
damaged blocks. This however, violates the sequential write constraints
of a zoned block device.
We can consider three methods to repair an IO failure in zoned filesystems:
(1) Reset and rewrite the damaged zone
(2) Allocate new device extent and replace the damaged device extent to
the new extent
(3) Relocate the corresponding block group
Method (1) is most similar to a behavior done with regular devices.
However, it also wipes non-damaged data in the same device extent, and
so it unnecessary degrades non-damaged data.
Method (2) is much like device replacing but done in the same device. It
is safe because it keeps the device extent until the replacing finish.
However, extending device replacing is non-trivial. It assumes
"src_dev->physical == dst_dev->physical". Also, the extent mapping
replacing function should be extended to support replacing device extent
position in one device.
Method (3) invokes relocation of the damaged block group and is
straightforward to implement. It relocates all the mirrored device
extents, so it potentially is a more costly operation than method (1) or
(2). But it relocates only used extents which reduce the total IO size.
Let's apply method (3) for now. In the future, we can extend device-replace
and apply method (2).
For protecting a block group gets relocated multiple time with multiple
IO errors, this commit introduces "relocating_repair" bit to show it's
now relocating to repair IO failures. Also it uses a new kthread
"btrfs-relocating-repair", not to block IO path with relocating process.
This commit also supports repairing in the scrub process.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-04 18:22:16 +08:00
|
|
|
|
2011-07-22 21:41:52 +08:00
|
|
|
map_length = length;
|
|
|
|
|
2016-05-28 05:21:27 +08:00
|
|
|
/*
|
2021-09-15 15:17:16 +08:00
|
|
|
* Avoid races with device replace and make sure our bioc has devices
|
2016-05-28 05:21:27 +08:00
|
|
|
* associated to its stripes that don't go away while we are doing the
|
|
|
|
* read repair operation.
|
|
|
|
*/
|
|
|
|
btrfs_bio_counter_inc_blocked(fs_info);
|
2017-07-19 15:48:42 +08:00
|
|
|
if (btrfs_is_parity_mirror(fs_info, logical, length)) {
|
2017-03-30 01:53:58 +08:00
|
|
|
/*
|
|
|
|
* Note that we don't use BTRFS_MAP_WRITE because it's supposed
|
|
|
|
* to update all raid stripes, but here we just want to correct
|
|
|
|
* bad stripe, thus BTRFS_MAP_READ is abused to only get the bad
|
|
|
|
* stripe's dev and sector.
|
|
|
|
*/
|
|
|
|
ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
|
2021-09-15 15:17:16 +08:00
|
|
|
&map_length, &bioc, 0);
|
2022-04-04 12:45:20 +08:00
|
|
|
if (ret)
|
|
|
|
goto out_counter_dec;
|
2021-09-15 15:17:16 +08:00
|
|
|
ASSERT(bioc->mirror_num == 1);
|
2017-03-30 01:53:58 +08:00
|
|
|
} else {
|
|
|
|
ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
|
2021-09-15 15:17:16 +08:00
|
|
|
&map_length, &bioc, mirror_num);
|
2022-04-04 12:45:20 +08:00
|
|
|
if (ret)
|
|
|
|
goto out_counter_dec;
|
2021-09-15 15:17:16 +08:00
|
|
|
BUG_ON(mirror_num != bioc->mirror_num);
|
2011-07-22 21:41:52 +08:00
|
|
|
}
|
2017-03-30 01:53:58 +08:00
|
|
|
|
2021-09-15 15:17:16 +08:00
|
|
|
sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
|
|
|
|
dev = bioc->stripes[bioc->mirror_num - 1].dev;
|
|
|
|
btrfs_put_bioc(bioc);
|
2022-04-04 12:45:20 +08:00
|
|
|
|
2017-12-04 12:54:52 +08:00
|
|
|
if (!dev || !dev->bdev ||
|
|
|
|
!test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
|
2022-04-04 12:45:20 +08:00
|
|
|
ret = -EIO;
|
|
|
|
goto out_counter_dec;
|
2011-07-22 21:41:52 +08:00
|
|
|
}
|
|
|
|
|
2022-04-04 12:45:20 +08:00
|
|
|
bio_init(&bio, dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC);
|
|
|
|
bio.bi_iter.bi_sector = sector;
|
|
|
|
__bio_add_page(&bio, page, length, pg_offset);
|
|
|
|
|
|
|
|
btrfsic_check_bio(&bio);
|
|
|
|
ret = submit_bio_wait(&bio);
|
|
|
|
if (ret) {
|
2011-07-22 21:41:52 +08:00
|
|
|
/* try to remap that extent elsewhere? */
|
2012-05-25 22:06:08 +08:00
|
|
|
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
|
2022-04-04 12:45:20 +08:00
|
|
|
goto out_bio_uninit;
|
2011-07-22 21:41:52 +08:00
|
|
|
}
|
|
|
|
|
2015-10-08 16:43:10 +08:00
|
|
|
btrfs_info_rl_in_rcu(fs_info,
|
|
|
|
"read error corrected: ino %llu off %llu (dev %s sector %llu)",
|
2017-05-05 23:57:14 +08:00
|
|
|
ino, start,
|
2014-09-12 18:44:01 +08:00
|
|
|
rcu_str_deref(dev->name), sector);
|
2022-04-04 12:45:20 +08:00
|
|
|
ret = 0;
|
|
|
|
|
|
|
|
out_bio_uninit:
|
|
|
|
bio_uninit(&bio);
|
|
|
|
out_counter_dec:
|
2016-05-28 05:21:27 +08:00
|
|
|
btrfs_bio_counter_dec(fs_info);
|
2022-04-04 12:45:20 +08:00
|
|
|
return ret;
|
2011-07-22 21:41:52 +08:00
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num)
|
2012-03-27 09:57:36 +08:00
|
|
|
{
|
2019-03-20 18:23:44 +08:00
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
2012-03-27 09:57:36 +08:00
|
|
|
u64 start = eb->start;
|
2018-03-02 01:20:27 +08:00
|
|
|
int i, num_pages = num_extent_pages(eb);
|
2012-04-13 03:55:15 +08:00
|
|
|
int ret = 0;
|
2012-03-27 09:57:36 +08:00
|
|
|
|
2017-07-17 15:45:34 +08:00
|
|
|
if (sb_rdonly(fs_info->sb))
|
2013-11-04 01:06:39 +08:00
|
|
|
return -EROFS;
|
|
|
|
|
2012-03-27 09:57:36 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
struct page *p = eb->pages[i];
|
2014-09-12 18:44:01 +08:00
|
|
|
|
2017-05-05 23:57:14 +08:00
|
|
|
ret = repair_io_failure(fs_info, 0, start, PAGE_SIZE, start, p,
|
2014-09-12 18:44:01 +08:00
|
|
|
start - page_offset(p), mirror_num);
|
2012-03-27 09:57:36 +08:00
|
|
|
if (ret)
|
|
|
|
break;
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
start += PAGE_SIZE;
|
2012-03-27 09:57:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2022-07-07 13:33:26 +08:00
|
|
|
static int next_mirror(const struct io_failure_record *failrec, int cur_mirror)
|
|
|
|
{
|
|
|
|
if (cur_mirror == failrec->num_copies)
|
|
|
|
return cur_mirror + 1 - failrec->num_copies;
|
|
|
|
return cur_mirror + 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int prev_mirror(const struct io_failure_record *failrec, int cur_mirror)
|
|
|
|
{
|
|
|
|
if (cur_mirror == 1)
|
|
|
|
return failrec->num_copies;
|
|
|
|
return cur_mirror - 1;
|
|
|
|
}
|
|
|
|
|
2011-07-22 21:41:52 +08:00
|
|
|
/*
|
|
|
|
* each time an IO finishes, we do a fast check in the IO failure tree
|
|
|
|
* to see if we need to process or clean up an io_failure_record
|
|
|
|
*/
|
2022-09-10 05:53:14 +08:00
|
|
|
int btrfs_clean_io_failure(struct btrfs_inode *inode, u64 start,
|
|
|
|
struct page *page, unsigned int pg_offset)
|
2011-07-22 21:41:52 +08:00
|
|
|
{
|
2022-09-10 05:53:14 +08:00
|
|
|
struct btrfs_fs_info *fs_info = inode->root->fs_info;
|
|
|
|
struct extent_io_tree *io_tree = &inode->io_tree;
|
|
|
|
u64 ino = btrfs_ino(inode);
|
2022-09-10 05:53:17 +08:00
|
|
|
u64 locked_start, locked_end;
|
2011-07-22 21:41:52 +08:00
|
|
|
struct io_failure_record *failrec;
|
2022-07-07 13:33:26 +08:00
|
|
|
int mirror;
|
2022-09-10 05:53:17 +08:00
|
|
|
int ret;
|
2011-07-22 21:41:52 +08:00
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
failrec = get_failrec(inode, start);
|
2020-07-02 20:23:28 +08:00
|
|
|
if (IS_ERR(failrec))
|
2011-07-22 21:41:52 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
BUG_ON(!failrec->this_mirror);
|
|
|
|
|
2017-07-17 15:45:34 +08:00
|
|
|
if (sb_rdonly(fs_info->sb))
|
2013-11-04 01:06:39 +08:00
|
|
|
goto out;
|
2011-07-22 21:41:52 +08:00
|
|
|
|
2022-09-10 05:53:17 +08:00
|
|
|
ret = find_first_extent_bit(io_tree, failrec->bytenr, &locked_start,
|
|
|
|
&locked_end, EXTENT_LOCKED, NULL);
|
|
|
|
if (ret || locked_start > failrec->bytenr ||
|
|
|
|
locked_end < failrec->bytenr + failrec->len - 1)
|
2022-07-07 13:33:26 +08:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
mirror = failrec->this_mirror;
|
|
|
|
do {
|
|
|
|
mirror = prev_mirror(failrec, mirror);
|
|
|
|
repair_io_failure(fs_info, ino, start, failrec->len,
|
|
|
|
failrec->logical, page, pg_offset, mirror);
|
|
|
|
} while (mirror != failrec->failed_mirror);
|
2011-07-22 21:41:52 +08:00
|
|
|
|
|
|
|
out:
|
2022-09-10 05:53:16 +08:00
|
|
|
free_io_failure(inode, failrec);
|
2014-09-12 18:43:58 +08:00
|
|
|
return 0;
|
2011-07-22 21:41:52 +08:00
|
|
|
}
|
|
|
|
|
Btrfs: cleanup the read failure record after write or when the inode is freeing
After the data is written successfully, we should cleanup the read failure record
in that range because
- If we set data COW for the file, the range that the failure record pointed to is
mapped to a new place, so it is invalid.
- If we set no data COW for the file, and if there is no error during writting,
the corrupted data is corrected, so the failure record can be removed. And if
some errors happen on the mirrors, we also needn't worry about it because the
failure record will be recreated if we read the same place again.
Sometimes, we may fail to correct the data, so the failure records will be left
in the tree, we need free them when we free the inode or the memory leak happens.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-12 18:44:04 +08:00
|
|
|
/*
|
|
|
|
* Can be called when
|
|
|
|
* - hold extent lock
|
|
|
|
* - under ordered extent
|
|
|
|
* - the inode is freeing
|
|
|
|
*/
|
2017-02-20 19:50:57 +08:00
|
|
|
void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end)
|
Btrfs: cleanup the read failure record after write or when the inode is freeing
After the data is written successfully, we should cleanup the read failure record
in that range because
- If we set data COW for the file, the range that the failure record pointed to is
mapped to a new place, so it is invalid.
- If we set no data COW for the file, and if there is no error during writting,
the corrupted data is corrected, so the failure record can be removed. And if
some errors happen on the mirrors, we also needn't worry about it because the
failure record will be recreated if we read the same place again.
Sometimes, we may fail to correct the data, so the failure records will be left
in the tree, we need free them when we free the inode or the memory leak happens.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-12 18:44:04 +08:00
|
|
|
{
|
|
|
|
struct io_failure_record *failrec;
|
2022-09-10 05:53:16 +08:00
|
|
|
struct rb_node *node, *next;
|
Btrfs: cleanup the read failure record after write or when the inode is freeing
After the data is written successfully, we should cleanup the read failure record
in that range because
- If we set data COW for the file, the range that the failure record pointed to is
mapped to a new place, so it is invalid.
- If we set no data COW for the file, and if there is no error during writting,
the corrupted data is corrected, so the failure record can be removed. And if
some errors happen on the mirrors, we also needn't worry about it because the
failure record will be recreated if we read the same place again.
Sometimes, we may fail to correct the data, so the failure records will be left
in the tree, we need free them when we free the inode or the memory leak happens.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-12 18:44:04 +08:00
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
if (RB_EMPTY_ROOT(&inode->io_failure_tree))
|
Btrfs: cleanup the read failure record after write or when the inode is freeing
After the data is written successfully, we should cleanup the read failure record
in that range because
- If we set data COW for the file, the range that the failure record pointed to is
mapped to a new place, so it is invalid.
- If we set no data COW for the file, and if there is no error during writting,
the corrupted data is corrected, so the failure record can be removed. And if
some errors happen on the mirrors, we also needn't worry about it because the
failure record will be recreated if we read the same place again.
Sometimes, we may fail to correct the data, so the failure records will be left
in the tree, we need free them when we free the inode or the memory leak happens.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-12 18:44:04 +08:00
|
|
|
return;
|
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
spin_lock(&inode->io_failure_lock);
|
|
|
|
node = rb_simple_search_first(&inode->io_failure_tree, start);
|
|
|
|
while (node) {
|
|
|
|
failrec = rb_entry(node, struct io_failure_record, rb_node);
|
|
|
|
if (failrec->bytenr > end)
|
Btrfs: cleanup the read failure record after write or when the inode is freeing
After the data is written successfully, we should cleanup the read failure record
in that range because
- If we set data COW for the file, the range that the failure record pointed to is
mapped to a new place, so it is invalid.
- If we set no data COW for the file, and if there is no error during writting,
the corrupted data is corrected, so the failure record can be removed. And if
some errors happen on the mirrors, we also needn't worry about it because the
failure record will be recreated if we read the same place again.
Sometimes, we may fail to correct the data, so the failure records will be left
in the tree, we need free them when we free the inode or the memory leak happens.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-12 18:44:04 +08:00
|
|
|
break;
|
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
next = rb_next(node);
|
|
|
|
rb_erase(&failrec->rb_node, &inode->io_failure_tree);
|
Btrfs: cleanup the read failure record after write or when the inode is freeing
After the data is written successfully, we should cleanup the read failure record
in that range because
- If we set data COW for the file, the range that the failure record pointed to is
mapped to a new place, so it is invalid.
- If we set no data COW for the file, and if there is no error during writting,
the corrupted data is corrected, so the failure record can be removed. And if
some errors happen on the mirrors, we also needn't worry about it because the
failure record will be recreated if we read the same place again.
Sometimes, we may fail to correct the data, so the failure records will be left
in the tree, we need free them when we free the inode or the memory leak happens.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-12 18:44:04 +08:00
|
|
|
kfree(failrec);
|
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
node = next;
|
Btrfs: cleanup the read failure record after write or when the inode is freeing
After the data is written successfully, we should cleanup the read failure record
in that range because
- If we set data COW for the file, the range that the failure record pointed to is
mapped to a new place, so it is invalid.
- If we set no data COW for the file, and if there is no error during writting,
the corrupted data is corrected, so the failure record can be removed. And if
some errors happen on the mirrors, we also needn't worry about it because the
failure record will be recreated if we read the same place again.
Sometimes, we may fail to correct the data, so the failure records will be left
in the tree, we need free them when we free the inode or the memory leak happens.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-12 18:44:04 +08:00
|
|
|
}
|
2022-09-10 05:53:16 +08:00
|
|
|
spin_unlock(&inode->io_failure_lock);
|
Btrfs: cleanup the read failure record after write or when the inode is freeing
After the data is written successfully, we should cleanup the read failure record
in that range because
- If we set data COW for the file, the range that the failure record pointed to is
mapped to a new place, so it is invalid.
- If we set no data COW for the file, and if there is no error during writting,
the corrupted data is corrected, so the failure record can be removed. And if
some errors happen on the mirrors, we also needn't worry about it because the
failure record will be recreated if we read the same place again.
Sometimes, we may fail to correct the data, so the failure records will be left
in the tree, we need free them when we free the inode or the memory leak happens.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-12 18:44:04 +08:00
|
|
|
}
|
|
|
|
|
2020-07-02 20:23:29 +08:00
|
|
|
static struct io_failure_record *btrfs_get_io_failure_record(struct inode *inode,
|
2022-07-07 13:33:28 +08:00
|
|
|
struct btrfs_bio *bbio,
|
|
|
|
unsigned int bio_offset)
|
2011-07-22 21:41:52 +08:00
|
|
|
{
|
2016-09-20 22:05:02 +08:00
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
|
2022-07-07 13:33:28 +08:00
|
|
|
u64 start = bbio->file_offset + bio_offset;
|
2014-09-12 18:43:59 +08:00
|
|
|
struct io_failure_record *failrec;
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
const u32 sectorsize = fs_info->sectorsize;
|
2011-07-22 21:41:52 +08:00
|
|
|
int ret;
|
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
failrec = get_failrec(BTRFS_I(inode), start);
|
2020-07-02 20:23:29 +08:00
|
|
|
if (!IS_ERR(failrec)) {
|
2016-09-20 22:05:02 +08:00
|
|
|
btrfs_debug(fs_info,
|
2021-05-03 10:08:56 +08:00
|
|
|
"Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu",
|
2022-09-10 05:53:16 +08:00
|
|
|
failrec->logical, failrec->bytenr, failrec->len);
|
2011-07-22 21:41:52 +08:00
|
|
|
/*
|
|
|
|
* when data can be on disk more than twice, add to failrec here
|
|
|
|
* (e.g. with a list for failed_mirror) to make
|
|
|
|
* clean_io_failure() clean all those errors at once.
|
|
|
|
*/
|
2022-07-07 13:33:28 +08:00
|
|
|
ASSERT(failrec->this_mirror == bbio->mirror_num);
|
2022-07-07 13:33:26 +08:00
|
|
|
ASSERT(failrec->len == fs_info->sectorsize);
|
2020-07-02 20:23:29 +08:00
|
|
|
return failrec;
|
2011-07-22 21:41:52 +08:00
|
|
|
}
|
2014-09-12 18:43:59 +08:00
|
|
|
|
2020-07-02 20:23:29 +08:00
|
|
|
failrec = kzalloc(sizeof(*failrec), GFP_NOFS);
|
|
|
|
if (!failrec)
|
|
|
|
return ERR_PTR(-ENOMEM);
|
2014-09-12 18:43:59 +08:00
|
|
|
|
2022-09-10 05:53:16 +08:00
|
|
|
RB_CLEAR_NODE(&failrec->rb_node);
|
|
|
|
failrec->bytenr = start;
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
failrec->len = sectorsize;
|
2022-07-07 13:33:28 +08:00
|
|
|
failrec->failed_mirror = bbio->mirror_num;
|
|
|
|
failrec->this_mirror = bbio->mirror_num;
|
2022-07-07 13:33:30 +08:00
|
|
|
failrec->logical = (bbio->iter.bi_sector << SECTOR_SHIFT) + bio_offset;
|
2020-07-02 20:23:29 +08:00
|
|
|
|
|
|
|
btrfs_debug(fs_info,
|
2022-07-07 13:33:30 +08:00
|
|
|
"new io failure record logical %llu start %llu",
|
|
|
|
failrec->logical, start);
|
2020-07-02 20:23:29 +08:00
|
|
|
|
2022-07-07 13:33:30 +08:00
|
|
|
failrec->num_copies = btrfs_num_copies(fs_info, failrec->logical, sectorsize);
|
2022-07-07 13:33:26 +08:00
|
|
|
if (failrec->num_copies == 1) {
|
|
|
|
/*
|
|
|
|
* We only have a single copy of the data, so don't bother with
|
|
|
|
* all the retry and error correction code that follows. No
|
|
|
|
* matter what the error is, it is very likely to persist.
|
|
|
|
*/
|
|
|
|
btrfs_debug(fs_info,
|
|
|
|
"cannot repair logical %llu num_copies %d",
|
|
|
|
failrec->logical, failrec->num_copies);
|
2020-07-02 20:23:29 +08:00
|
|
|
kfree(failrec);
|
|
|
|
return ERR_PTR(-EIO);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Set the bits in the private failure tree */
|
2022-09-10 05:53:16 +08:00
|
|
|
ret = insert_failrec(BTRFS_I(inode), failrec);
|
|
|
|
if (ret) {
|
2020-07-02 20:23:29 +08:00
|
|
|
kfree(failrec);
|
|
|
|
return ERR_PTR(ret);
|
|
|
|
}
|
|
|
|
|
|
|
|
return failrec;
|
2014-09-12 18:43:59 +08:00
|
|
|
}
|
|
|
|
|
2022-10-27 08:41:32 +08:00
|
|
|
int btrfs_repair_one_sector(struct btrfs_inode *inode, struct btrfs_bio *failed_bbio,
|
2022-07-07 13:33:28 +08:00
|
|
|
u32 bio_offset, struct page *page, unsigned int pgoff,
|
2022-10-27 08:02:32 +08:00
|
|
|
bool submit_buffered)
|
2014-09-12 18:43:59 +08:00
|
|
|
{
|
2022-07-07 13:33:28 +08:00
|
|
|
u64 start = failed_bbio->file_offset + bio_offset;
|
2014-09-12 18:43:59 +08:00
|
|
|
struct io_failure_record *failrec;
|
2022-10-27 08:41:32 +08:00
|
|
|
struct btrfs_fs_info *fs_info = inode->root->fs_info;
|
2022-07-07 13:33:28 +08:00
|
|
|
struct bio *failed_bio = &failed_bbio->bio;
|
2020-12-02 14:47:58 +08:00
|
|
|
const int icsum = bio_offset >> fs_info->sectorsize_bits;
|
2020-04-17 05:46:25 +08:00
|
|
|
struct bio *repair_bio;
|
2021-09-15 15:17:18 +08:00
|
|
|
struct btrfs_bio *repair_bbio;
|
2014-09-12 18:43:59 +08:00
|
|
|
|
2020-04-17 05:46:25 +08:00
|
|
|
btrfs_debug(fs_info,
|
|
|
|
"repair read error: read error at %llu", start);
|
2014-09-12 18:43:59 +08:00
|
|
|
|
2016-06-06 03:31:51 +08:00
|
|
|
BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
|
2014-09-12 18:43:59 +08:00
|
|
|
|
2022-10-27 08:41:32 +08:00
|
|
|
failrec = btrfs_get_io_failure_record(&inode->vfs_inode, failed_bbio, bio_offset);
|
2020-07-02 20:23:29 +08:00
|
|
|
if (IS_ERR(failrec))
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
return PTR_ERR(failrec);
|
2014-09-12 18:43:59 +08:00
|
|
|
|
2022-07-07 13:33:26 +08:00
|
|
|
/*
|
|
|
|
* There are two premises:
|
|
|
|
* a) deliver good data to the caller
|
|
|
|
* b) correct the bad sectors on disk
|
|
|
|
*
|
|
|
|
* Since we're only doing repair for one sector, we only need to get
|
|
|
|
* a good copy of the failed sector and if we succeed, we have setup
|
|
|
|
* everything for repair_io_failure to do the rest for us.
|
|
|
|
*/
|
|
|
|
failrec->this_mirror = next_mirror(failrec, failrec->this_mirror);
|
|
|
|
if (failrec->this_mirror == failrec->failed_mirror) {
|
|
|
|
btrfs_debug(fs_info,
|
|
|
|
"failed to repair num_copies %d this_mirror %d failed_mirror %d",
|
|
|
|
failrec->num_copies, failrec->this_mirror, failrec->failed_mirror);
|
2022-10-27 08:41:32 +08:00
|
|
|
free_io_failure(inode, failrec);
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
return -EIO;
|
2014-09-12 18:43:59 +08:00
|
|
|
}
|
|
|
|
|
2022-08-06 16:03:26 +08:00
|
|
|
repair_bio = btrfs_bio_alloc(1, REQ_OP_READ, failed_bbio->end_io,
|
|
|
|
failed_bbio->private);
|
2021-09-15 15:17:18 +08:00
|
|
|
repair_bbio = btrfs_bio(repair_bio);
|
2022-03-25 00:06:27 +08:00
|
|
|
repair_bbio->file_offset = start;
|
2020-04-17 05:46:25 +08:00
|
|
|
repair_bio->bi_iter.bi_sector = failrec->logical >> 9;
|
2014-09-12 18:43:59 +08:00
|
|
|
|
2021-09-15 15:17:18 +08:00
|
|
|
if (failed_bbio->csum) {
|
2020-07-02 17:27:30 +08:00
|
|
|
const u32 csum_size = fs_info->csum_size;
|
2020-04-17 05:46:25 +08:00
|
|
|
|
2021-09-15 15:17:18 +08:00
|
|
|
repair_bbio->csum = repair_bbio->csum_inline;
|
|
|
|
memcpy(repair_bbio->csum,
|
|
|
|
failed_bbio->csum + csum_size * icsum, csum_size);
|
2020-04-17 05:46:25 +08:00
|
|
|
}
|
2014-09-12 18:43:59 +08:00
|
|
|
|
2020-04-17 05:46:25 +08:00
|
|
|
bio_add_page(repair_bio, page, failrec->len, pgoff);
|
2021-09-15 15:17:18 +08:00
|
|
|
repair_bbio->iter = repair_bio->bi_iter;
|
2011-07-22 21:41:52 +08:00
|
|
|
|
2022-10-27 08:41:32 +08:00
|
|
|
btrfs_debug(fs_info,
|
2021-05-03 10:08:56 +08:00
|
|
|
"repair read error: submitting new read to mirror %d",
|
|
|
|
failrec->this_mirror);
|
2011-07-22 21:41:52 +08:00
|
|
|
|
2022-02-18 23:03:29 +08:00
|
|
|
/*
|
2022-10-27 08:02:32 +08:00
|
|
|
* At this point we have a bio, so any errors from bio submission will
|
|
|
|
* be handled by the endio on the repair_bio, so we can't return an
|
2022-02-18 23:03:29 +08:00
|
|
|
* error here.
|
|
|
|
*/
|
2022-10-27 08:02:32 +08:00
|
|
|
if (submit_buffered)
|
2022-10-27 08:41:32 +08:00
|
|
|
btrfs_submit_data_read_bio(inode, repair_bio,
|
2022-10-27 08:41:32 +08:00
|
|
|
failrec->this_mirror, 0);
|
2022-10-27 08:02:32 +08:00
|
|
|
else
|
2022-10-27 08:41:32 +08:00
|
|
|
btrfs_submit_dio_repair_bio(inode, repair_bio, failrec->this_mirror);
|
2022-10-27 08:02:32 +08:00
|
|
|
|
2022-02-18 23:03:29 +08:00
|
|
|
return BLK_STS_OK;
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
|
|
|
|
|
|
|
|
ASSERT(page_offset(page) <= start &&
|
|
|
|
start + len <= page_offset(page) + PAGE_SIZE);
|
|
|
|
|
|
|
|
if (uptodate) {
|
2021-07-01 04:01:49 +08:00
|
|
|
if (fsverity_active(page->mapping->host) &&
|
|
|
|
!PageError(page) &&
|
|
|
|
!PageUptodate(page) &&
|
|
|
|
start < i_size_read(page->mapping->host) &&
|
|
|
|
!fsverity_verify_page(page)) {
|
|
|
|
btrfs_page_set_error(fs_info, page, start, len);
|
|
|
|
} else {
|
|
|
|
btrfs_page_set_uptodate(fs_info, page, start, len);
|
|
|
|
}
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
} else {
|
|
|
|
btrfs_page_clear_uptodate(fs_info, page, start, len);
|
|
|
|
btrfs_page_set_error(fs_info, page, start, len);
|
|
|
|
}
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (!btrfs_is_subpage(fs_info, page))
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
unlock_page(page);
|
btrfs: subpage: fix a rare race between metadata endio and eb freeing
[BUG]
There is a very rare ASSERT() triggering during full fstests run for
subpage rw support.
No other reproducer so far.
The ASSERT() gets triggered for metadata read in
btrfs_page_set_uptodate() inside end_page_read().
[CAUSE]
There is still a small race window for metadata only, the race could
happen like this:
T1 | T2
------------------------------------+-----------------------------
end_bio_extent_readpage() |
|- btrfs_validate_metadata_buffer() |
| |- free_extent_buffer() |
| Still have 2 refs |
|- end_page_read() |
|- if (unlikely(PagePrivate()) |
| The page still has Private |
| | free_extent_buffer()
| | | Only one ref 1, will be
| | | released
| | |- detach_extent_buffer_page()
| | |- btrfs_detach_subpage()
|- btrfs_set_page_uptodate() |
The page no longer has Private|
>>> ASSERT() triggered <<< |
This race window is super small, thus pretty hard to hit, even with so
many runs of fstests.
But the race window is still there, we have to go another way to solve
it other than relying on random PagePrivate() check.
Data path is not affected, as it will lock the page before reading,
while unlocking the page after the last read has finished, thus no race
window.
[FIX]
This patch will fix the bug by repurposing btrfs_subpage::readers.
Now btrfs_subpage::readers will be a member shared by both metadata and
data.
For metadata path, we don't do the page unlock as metadata only relies
on extent locking.
At the same time, teach page_range_has_eb() to take
btrfs_subpage::readers into consideration.
So that even if the last eb of a page gets freed, page::private won't be
detached as long as there still are pending end_page_read() calls.
By this we eliminate the race window, this will slight increase the
metadata memory usage, as the page may not be released as frequently as
usual. But it should not be a big deal.
The code got introduced in ("btrfs: submit read time repair only for
each corrupted sector"), but the fix is in a separate patch to keep the
problem description and the crash is rare so it should not hurt
bisectability.
Signed-off-by: Qu Wegruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-06-07 17:02:58 +08:00
|
|
|
else
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
btrfs_subpage_end_reader(fs_info, page, start, len);
|
|
|
|
}
|
|
|
|
|
2022-05-22 19:47:50 +08:00
|
|
|
static void end_sector_io(struct page *page, u64 offset, bool uptodate)
|
|
|
|
{
|
|
|
|
struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
|
|
|
|
const u32 sectorsize = inode->root->fs_info->sectorsize;
|
|
|
|
struct extent_state *cached = NULL;
|
|
|
|
|
|
|
|
end_page_read(page, uptodate, offset, sectorsize);
|
|
|
|
if (uptodate)
|
|
|
|
set_extent_uptodate(&inode->io_tree, offset,
|
2022-10-14 22:00:39 +08:00
|
|
|
offset + sectorsize - 1, &cached, GFP_NOFS);
|
|
|
|
unlock_extent(&inode->io_tree, offset, offset + sectorsize - 1,
|
|
|
|
&cached);
|
2022-05-22 19:47:50 +08:00
|
|
|
}
|
|
|
|
|
2022-07-07 13:33:28 +08:00
|
|
|
static void submit_data_read_repair(struct inode *inode,
|
|
|
|
struct btrfs_bio *failed_bbio,
|
2022-05-22 19:47:49 +08:00
|
|
|
u32 bio_offset, const struct bio_vec *bvec,
|
2022-07-07 13:33:28 +08:00
|
|
|
unsigned int error_bitmap)
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
{
|
2022-05-22 19:47:49 +08:00
|
|
|
const unsigned int pgoff = bvec->bv_offset;
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
|
2022-05-22 19:47:49 +08:00
|
|
|
struct page *page = bvec->bv_page;
|
|
|
|
const u64 start = page_offset(bvec->bv_page) + bvec->bv_offset;
|
|
|
|
const u64 end = start + bvec->bv_len - 1;
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
const u32 sectorsize = fs_info->sectorsize;
|
|
|
|
const int nr_bits = (end + 1 - start) >> fs_info->sectorsize_bits;
|
|
|
|
int i;
|
|
|
|
|
2022-07-07 13:33:28 +08:00
|
|
|
BUG_ON(bio_op(&failed_bbio->bio) == REQ_OP_WRITE);
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
|
2022-03-21 13:48:42 +08:00
|
|
|
/* This repair is only for data */
|
|
|
|
ASSERT(is_data_inode(inode));
|
|
|
|
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
/* We're here because we had some read errors or csum mismatch */
|
|
|
|
ASSERT(error_bitmap);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We only get called on buffered IO, thus page must be mapped and bio
|
|
|
|
* must not be cloned.
|
|
|
|
*/
|
2022-07-07 13:33:28 +08:00
|
|
|
ASSERT(page->mapping && !bio_flagged(&failed_bbio->bio, BIO_CLONED));
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
|
|
|
|
/* Iterate through all the sectors in the range */
|
|
|
|
for (i = 0; i < nr_bits; i++) {
|
|
|
|
const unsigned int offset = i * sectorsize;
|
|
|
|
bool uptodate = false;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!(error_bitmap & (1U << i))) {
|
|
|
|
/*
|
|
|
|
* This sector has no error, just end the page read
|
|
|
|
* and unlock the range.
|
|
|
|
*/
|
|
|
|
uptodate = true;
|
|
|
|
goto next;
|
|
|
|
}
|
|
|
|
|
2022-10-27 08:41:32 +08:00
|
|
|
ret = btrfs_repair_one_sector(BTRFS_I(inode), failed_bbio,
|
2022-07-07 13:33:28 +08:00
|
|
|
bio_offset + offset, page, pgoff + offset,
|
2022-10-27 08:02:32 +08:00
|
|
|
true);
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
if (!ret) {
|
|
|
|
/*
|
|
|
|
* We have submitted the read repair, the page release
|
|
|
|
* will be handled by the endio function of the
|
|
|
|
* submitted repair bio.
|
|
|
|
* Thus we don't need to do any thing here.
|
|
|
|
*/
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
/*
|
2022-05-22 19:47:49 +08:00
|
|
|
* Continue on failed repair, otherwise the remaining sectors
|
|
|
|
* will not be properly unlocked.
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
*/
|
|
|
|
next:
|
2022-05-22 19:47:50 +08:00
|
|
|
end_sector_io(page, start + offset, uptodate);
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
}
|
2011-07-22 21:41:52 +08:00
|
|
|
}
|
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
/* lots and lots of room for performance fixes in the end_bio funcs */
|
|
|
|
|
2015-12-03 20:08:59 +08:00
|
|
|
void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
|
2012-02-15 23:23:57 +08:00
|
|
|
{
|
2021-04-08 20:32:27 +08:00
|
|
|
struct btrfs_inode *inode;
|
2021-07-26 20:15:08 +08:00
|
|
|
const bool uptodate = (err == 0);
|
2014-06-12 13:39:58 +08:00
|
|
|
int ret = 0;
|
2012-02-15 23:23:57 +08:00
|
|
|
|
2021-04-08 20:32:27 +08:00
|
|
|
ASSERT(page && page->mapping);
|
|
|
|
inode = BTRFS_I(page->mapping->host);
|
|
|
|
btrfs_writepage_endio_finish_ordered(inode, page, start, end, uptodate);
|
2012-02-15 23:23:57 +08:00
|
|
|
|
|
|
|
if (!uptodate) {
|
btrfs: unify regular and subpage error paths in __extent_writepage()
[BUG]
When running btrfs/160 in a loop for subpage with experimental
compression support, it has a high chance to crash (~20%):
BTRFS critical (device dm-7): panic in __btrfs_add_ordered_extent:238: inconsistency in ordered tree at offset 0 (errno=-17 Object already exists)
------------[ cut here ]------------
kernel BUG at fs/btrfs/ordered-data.c:238!
Internal error: Oops - BUG: 0 [#1] SMP
pc : __btrfs_add_ordered_extent+0x550/0x670 [btrfs]
lr : __btrfs_add_ordered_extent+0x550/0x670 [btrfs]
Call trace:
__btrfs_add_ordered_extent+0x550/0x670 [btrfs]
btrfs_add_ordered_extent+0x2c/0x50 [btrfs]
run_delalloc_nocow+0x81c/0x8fc [btrfs]
btrfs_run_delalloc_range+0xa4/0x390 [btrfs]
writepage_delalloc+0xc0/0x1ac [btrfs]
__extent_writepage+0xf4/0x370 [btrfs]
extent_write_cache_pages+0x288/0x4f4 [btrfs]
extent_writepages+0x58/0xe0 [btrfs]
btrfs_writepages+0x1c/0x30 [btrfs]
do_writepages+0x60/0x110
__filemap_fdatawrite_range+0x108/0x170
filemap_fdatawrite_range+0x20/0x30
btrfs_fdatawrite_range+0x34/0x4dc [btrfs]
__btrfs_write_out_cache+0x34c/0x480 [btrfs]
btrfs_write_out_cache+0x144/0x220 [btrfs]
btrfs_start_dirty_block_groups+0x3ac/0x6b0 [btrfs]
btrfs_commit_transaction+0xd0/0xbb4 [btrfs]
btrfs_sync_fs+0x64/0x1cc [btrfs]
sync_fs_one_sb+0x3c/0x50
iterate_supers+0xcc/0x1d4
ksys_sync+0x6c/0xd0
__arm64_sys_sync+0x1c/0x30
invoke_syscall+0x50/0x120
el0_svc_common.constprop.0+0x4c/0xd4
do_el0_svc+0x30/0x9c
el0_svc+0x2c/0x54
el0_sync_handler+0x1a8/0x1b0
el0_sync+0x198/0x1c0
---[ end trace 336f67369ae6e0af ]---
[CAUSE]
For subpage case, we can have multiple sectors inside a page, this makes
it possible for __extent_writepage() to have part of its page submitted
before returning.
In btrfs/160, we are using dm-dust to emulate write error, this means
for certain pages, we could have everything running fine, but at the end
of __extent_writepage(), one of the submitted bios fails due to dm-dust.
Then the page is marked Error, and we change @ret from 0 to -EIO.
This makes the caller extent_write_cache_pages() to error out, without
submitting the remaining pages.
Furthermore, since we're erroring out for free space cache, it doesn't
really care about the error and will update the inode and retry the
writeback.
Then we re-run the delalloc range, and will try to insert the same
delalloc range while previous delalloc range is still hanging there,
triggering the above error.
[FIX]
The proper fix is to handle errors from __extent_writepage() properly,
by ending the remaining ordered extent.
But that fix needs the following changes:
- Know at exactly which sector the error happened
Currently __extent_writepage_io() works for the full page, can't
return at which sector we hit the error.
- Grab the ordered extent covering the failed sector
As a hotfix for subpage case, here we unify the error paths in
__extent_writepage().
In fact, the "if (PageError(page))" branch never get executed if @ret is
still 0 for non-subpage cases.
As for non-subpage case, we never submit current page in
__extent_writepage(), but only add current page into bio.
The bio can only get submitted in next page.
Thus we never get PageError() set due to IO failure, thus when we hit
the branch, @ret is never 0.
By simply removing that @ret assignment, we let subpage case ignore the
IO failure, thus only error out for fatal errors just like regular
sectorsize.
So that IO error won't be treated as fatal error not trigger the hanging
OE problem.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:07 +08:00
|
|
|
const struct btrfs_fs_info *fs_info = inode->root->fs_info;
|
|
|
|
u32 len;
|
|
|
|
|
|
|
|
ASSERT(end + 1 - start <= U32_MAX);
|
|
|
|
len = end + 1 - start;
|
|
|
|
|
|
|
|
btrfs_page_clear_uptodate(fs_info, page, start, len);
|
|
|
|
btrfs_page_set_error(fs_info, page, start, len);
|
2017-05-10 01:14:01 +08:00
|
|
|
ret = err < 0 ? err : -EIO;
|
2014-05-12 12:47:36 +08:00
|
|
|
mapping_set_error(page->mapping, ret);
|
2012-02-15 23:23:57 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
/*
|
|
|
|
* after a writepage IO is done, we need to:
|
|
|
|
* clear the uptodate bits on error
|
|
|
|
* clear the writeback bits in the extent tree for this IO
|
|
|
|
* end_page_writeback if the page has no more pending IO
|
|
|
|
*
|
|
|
|
* Scheduling is not allowed, so the extent state tree is expected
|
|
|
|
* to have one and only one object corresponding to this IO.
|
|
|
|
*/
|
2022-08-06 16:03:26 +08:00
|
|
|
static void end_bio_extent_writepage(struct btrfs_bio *bbio)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2022-08-06 16:03:26 +08:00
|
|
|
struct bio *bio = &bbio->bio;
|
2017-06-03 15:38:06 +08:00
|
|
|
int error = blk_status_to_errno(bio->bi_status);
|
2013-11-08 04:20:26 +08:00
|
|
|
struct bio_vec *bvec;
|
2008-01-25 05:13:08 +08:00
|
|
|
u64 start;
|
|
|
|
u64 end;
|
2019-02-15 19:13:19 +08:00
|
|
|
struct bvec_iter_all iter_all;
|
2021-02-04 18:22:05 +08:00
|
|
|
bool first_bvec = true;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2017-07-14 00:10:07 +08:00
|
|
|
ASSERT(!bio_flagged(bio, BIO_CLONED));
|
2019-04-25 15:03:00 +08:00
|
|
|
bio_for_each_segment_all(bvec, bio, iter_all) {
|
2008-01-25 05:13:08 +08:00
|
|
|
struct page *page = bvec->bv_page;
|
2016-06-23 06:54:23 +08:00
|
|
|
struct inode *inode = page->mapping->host;
|
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
|
2021-05-31 16:50:40 +08:00
|
|
|
const u32 sectorsize = fs_info->sectorsize;
|
|
|
|
|
|
|
|
/* Our read/write should always be sector aligned. */
|
|
|
|
if (!IS_ALIGNED(bvec->bv_offset, sectorsize))
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"partial page write in btrfs with offset %u and length %u",
|
|
|
|
bvec->bv_offset, bvec->bv_len);
|
|
|
|
else if (!IS_ALIGNED(bvec->bv_len, sectorsize))
|
|
|
|
btrfs_info(fs_info,
|
|
|
|
"incomplete page write with offset %u and length %u",
|
|
|
|
bvec->bv_offset, bvec->bv_len);
|
|
|
|
|
|
|
|
start = page_offset(page) + bvec->bv_offset;
|
|
|
|
end = start + bvec->bv_len - 1;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2021-02-04 18:22:05 +08:00
|
|
|
if (first_bvec) {
|
|
|
|
btrfs_record_physical_zoned(inode, start, bio);
|
|
|
|
first_bvec = false;
|
|
|
|
}
|
|
|
|
|
2017-06-03 15:38:06 +08:00
|
|
|
end_extent_writepage(page, error, start, end);
|
2021-05-31 16:50:43 +08:00
|
|
|
|
|
|
|
btrfs_page_clear_writeback(fs_info, page, start, bvec->bv_len);
|
2013-11-08 04:20:26 +08:00
|
|
|
}
|
2008-09-24 23:48:04 +08:00
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
bio_put(bio);
|
|
|
|
}
|
|
|
|
|
btrfs: add structure to keep track of extent range in end_bio_extent_readpage
In end_bio_extent_readpage() we had a strange dance around
extent_start/extent_len.
Hidden behind the strange dance is, it's just calling
endio_readpage_release_extent() on each bvec range.
Here is an example to explain the original work flow:
Bio is for inode 257, containing 2 pages, for range [1M, 1M+8K)
end_bio_extent_extent_readpage() entered
|- extent_start = 0;
|- extent_end = 0;
|- bio_for_each_segment_all() {
| |- /* Got the 1st bvec */
| |- start = SZ_1M;
| |- end = SZ_1M + SZ_4K - 1;
| |- update = 1;
| |- if (extent_len == 0) {
| | |- extent_start = start; /* SZ_1M */
| | |- extent_len = end + 1 - start; /* SZ_1M */
| | }
| |
| |- /* Got the 2nd bvec */
| |- start = SZ_1M + 4K;
| |- end = SZ_1M + 4K - 1;
| |- update = 1;
| |- if (extent_start + extent_len == start) {
| | |- extent_len += end + 1 - start; /* SZ_8K */
| | }
| } /* All bio vec iterated */
|
|- if (extent_len) {
|- endio_readpage_release_extent(tree, extent_start, extent_len,
update);
/* extent_start == SZ_1M, extent_len == SZ_8K, uptodate = 1 */
As the above flow shows, the existing code in end_bio_extent_readpage()
is accumulates extent_start/extent_len, and when the contiguous range
stops, calls endio_readpage_release_extent() for the range.
However current behavior has something not really considered:
- The inode can change
For bio, its pages don't need to have contiguous page_offset.
This means, even pages from different inodes can be packed into one
bio.
- bvec cross page boundary
There is a feature called multi-page bvec, where bvec->bv_len can go
beyond bvec->bv_page boundary.
- Poor readability
This patch will address the problem:
- Introduce a proper structure, processed_extent, to record processed
extent range
- Integrate inode/start/end/uptodate check into
endio_readpage_release_extent()
- Add more comment on each step.
This should greatly improve the readability, now in
end_bio_extent_readpage() there are only two
endio_readpage_release_extent() calls.
- Add inode check for contiguity
Now we also ensure the inode is the same one before checking if the
range is contiguous.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 20:51:28 +08:00
|
|
|
/*
|
|
|
|
* Record previously processed extent range
|
|
|
|
*
|
|
|
|
* For endio_readpage_release_extent() to handle a full extent range, reducing
|
|
|
|
* the extent io operations.
|
|
|
|
*/
|
|
|
|
struct processed_extent {
|
|
|
|
struct btrfs_inode *inode;
|
|
|
|
/* Start of the range in @inode */
|
|
|
|
u64 start;
|
2021-01-25 09:41:41 +08:00
|
|
|
/* End of the range in @inode */
|
btrfs: add structure to keep track of extent range in end_bio_extent_readpage
In end_bio_extent_readpage() we had a strange dance around
extent_start/extent_len.
Hidden behind the strange dance is, it's just calling
endio_readpage_release_extent() on each bvec range.
Here is an example to explain the original work flow:
Bio is for inode 257, containing 2 pages, for range [1M, 1M+8K)
end_bio_extent_extent_readpage() entered
|- extent_start = 0;
|- extent_end = 0;
|- bio_for_each_segment_all() {
| |- /* Got the 1st bvec */
| |- start = SZ_1M;
| |- end = SZ_1M + SZ_4K - 1;
| |- update = 1;
| |- if (extent_len == 0) {
| | |- extent_start = start; /* SZ_1M */
| | |- extent_len = end + 1 - start; /* SZ_1M */
| | }
| |
| |- /* Got the 2nd bvec */
| |- start = SZ_1M + 4K;
| |- end = SZ_1M + 4K - 1;
| |- update = 1;
| |- if (extent_start + extent_len == start) {
| | |- extent_len += end + 1 - start; /* SZ_8K */
| | }
| } /* All bio vec iterated */
|
|- if (extent_len) {
|- endio_readpage_release_extent(tree, extent_start, extent_len,
update);
/* extent_start == SZ_1M, extent_len == SZ_8K, uptodate = 1 */
As the above flow shows, the existing code in end_bio_extent_readpage()
is accumulates extent_start/extent_len, and when the contiguous range
stops, calls endio_readpage_release_extent() for the range.
However current behavior has something not really considered:
- The inode can change
For bio, its pages don't need to have contiguous page_offset.
This means, even pages from different inodes can be packed into one
bio.
- bvec cross page boundary
There is a feature called multi-page bvec, where bvec->bv_len can go
beyond bvec->bv_page boundary.
- Poor readability
This patch will address the problem:
- Introduce a proper structure, processed_extent, to record processed
extent range
- Integrate inode/start/end/uptodate check into
endio_readpage_release_extent()
- Add more comment on each step.
This should greatly improve the readability, now in
end_bio_extent_readpage() there are only two
endio_readpage_release_extent() calls.
- Add inode check for contiguity
Now we also ensure the inode is the same one before checking if the
range is contiguous.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 20:51:28 +08:00
|
|
|
u64 end;
|
|
|
|
bool uptodate;
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Try to release processed extent range
|
|
|
|
*
|
|
|
|
* May not release the extent range right now if the current range is
|
|
|
|
* contiguous to processed extent.
|
|
|
|
*
|
|
|
|
* Will release processed extent when any of @inode, @uptodate, the range is
|
|
|
|
* no longer contiguous to the processed range.
|
|
|
|
*
|
|
|
|
* Passing @inode == NULL will force processed extent to be released.
|
|
|
|
*/
|
|
|
|
static void endio_readpage_release_extent(struct processed_extent *processed,
|
|
|
|
struct btrfs_inode *inode, u64 start, u64 end,
|
|
|
|
bool uptodate)
|
2013-07-25 19:22:35 +08:00
|
|
|
{
|
|
|
|
struct extent_state *cached = NULL;
|
btrfs: add structure to keep track of extent range in end_bio_extent_readpage
In end_bio_extent_readpage() we had a strange dance around
extent_start/extent_len.
Hidden behind the strange dance is, it's just calling
endio_readpage_release_extent() on each bvec range.
Here is an example to explain the original work flow:
Bio is for inode 257, containing 2 pages, for range [1M, 1M+8K)
end_bio_extent_extent_readpage() entered
|- extent_start = 0;
|- extent_end = 0;
|- bio_for_each_segment_all() {
| |- /* Got the 1st bvec */
| |- start = SZ_1M;
| |- end = SZ_1M + SZ_4K - 1;
| |- update = 1;
| |- if (extent_len == 0) {
| | |- extent_start = start; /* SZ_1M */
| | |- extent_len = end + 1 - start; /* SZ_1M */
| | }
| |
| |- /* Got the 2nd bvec */
| |- start = SZ_1M + 4K;
| |- end = SZ_1M + 4K - 1;
| |- update = 1;
| |- if (extent_start + extent_len == start) {
| | |- extent_len += end + 1 - start; /* SZ_8K */
| | }
| } /* All bio vec iterated */
|
|- if (extent_len) {
|- endio_readpage_release_extent(tree, extent_start, extent_len,
update);
/* extent_start == SZ_1M, extent_len == SZ_8K, uptodate = 1 */
As the above flow shows, the existing code in end_bio_extent_readpage()
is accumulates extent_start/extent_len, and when the contiguous range
stops, calls endio_readpage_release_extent() for the range.
However current behavior has something not really considered:
- The inode can change
For bio, its pages don't need to have contiguous page_offset.
This means, even pages from different inodes can be packed into one
bio.
- bvec cross page boundary
There is a feature called multi-page bvec, where bvec->bv_len can go
beyond bvec->bv_page boundary.
- Poor readability
This patch will address the problem:
- Introduce a proper structure, processed_extent, to record processed
extent range
- Integrate inode/start/end/uptodate check into
endio_readpage_release_extent()
- Add more comment on each step.
This should greatly improve the readability, now in
end_bio_extent_readpage() there are only two
endio_readpage_release_extent() calls.
- Add inode check for contiguity
Now we also ensure the inode is the same one before checking if the
range is contiguous.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 20:51:28 +08:00
|
|
|
struct extent_io_tree *tree;
|
|
|
|
|
|
|
|
/* The first extent, initialize @processed */
|
|
|
|
if (!processed->inode)
|
|
|
|
goto update;
|
2013-07-25 19:22:35 +08:00
|
|
|
|
btrfs: add structure to keep track of extent range in end_bio_extent_readpage
In end_bio_extent_readpage() we had a strange dance around
extent_start/extent_len.
Hidden behind the strange dance is, it's just calling
endio_readpage_release_extent() on each bvec range.
Here is an example to explain the original work flow:
Bio is for inode 257, containing 2 pages, for range [1M, 1M+8K)
end_bio_extent_extent_readpage() entered
|- extent_start = 0;
|- extent_end = 0;
|- bio_for_each_segment_all() {
| |- /* Got the 1st bvec */
| |- start = SZ_1M;
| |- end = SZ_1M + SZ_4K - 1;
| |- update = 1;
| |- if (extent_len == 0) {
| | |- extent_start = start; /* SZ_1M */
| | |- extent_len = end + 1 - start; /* SZ_1M */
| | }
| |
| |- /* Got the 2nd bvec */
| |- start = SZ_1M + 4K;
| |- end = SZ_1M + 4K - 1;
| |- update = 1;
| |- if (extent_start + extent_len == start) {
| | |- extent_len += end + 1 - start; /* SZ_8K */
| | }
| } /* All bio vec iterated */
|
|- if (extent_len) {
|- endio_readpage_release_extent(tree, extent_start, extent_len,
update);
/* extent_start == SZ_1M, extent_len == SZ_8K, uptodate = 1 */
As the above flow shows, the existing code in end_bio_extent_readpage()
is accumulates extent_start/extent_len, and when the contiguous range
stops, calls endio_readpage_release_extent() for the range.
However current behavior has something not really considered:
- The inode can change
For bio, its pages don't need to have contiguous page_offset.
This means, even pages from different inodes can be packed into one
bio.
- bvec cross page boundary
There is a feature called multi-page bvec, where bvec->bv_len can go
beyond bvec->bv_page boundary.
- Poor readability
This patch will address the problem:
- Introduce a proper structure, processed_extent, to record processed
extent range
- Integrate inode/start/end/uptodate check into
endio_readpage_release_extent()
- Add more comment on each step.
This should greatly improve the readability, now in
end_bio_extent_readpage() there are only two
endio_readpage_release_extent() calls.
- Add inode check for contiguity
Now we also ensure the inode is the same one before checking if the
range is contiguous.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 20:51:28 +08:00
|
|
|
/*
|
|
|
|
* Contiguous to processed extent, just uptodate the end.
|
|
|
|
*
|
|
|
|
* Several things to notice:
|
|
|
|
*
|
|
|
|
* - bio can be merged as long as on-disk bytenr is contiguous
|
|
|
|
* This means we can have page belonging to other inodes, thus need to
|
|
|
|
* check if the inode still matches.
|
|
|
|
* - bvec can contain range beyond current page for multi-page bvec
|
|
|
|
* Thus we need to do processed->end + 1 >= start check
|
|
|
|
*/
|
|
|
|
if (processed->inode == inode && processed->uptodate == uptodate &&
|
|
|
|
processed->end + 1 >= start && end >= processed->end) {
|
|
|
|
processed->end = end;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
tree = &processed->inode->io_tree;
|
|
|
|
/*
|
|
|
|
* Now we don't have range contiguous to the processed range, release
|
|
|
|
* the processed range now.
|
|
|
|
*/
|
2022-10-14 22:00:39 +08:00
|
|
|
unlock_extent(tree, processed->start, processed->end, &cached);
|
btrfs: add structure to keep track of extent range in end_bio_extent_readpage
In end_bio_extent_readpage() we had a strange dance around
extent_start/extent_len.
Hidden behind the strange dance is, it's just calling
endio_readpage_release_extent() on each bvec range.
Here is an example to explain the original work flow:
Bio is for inode 257, containing 2 pages, for range [1M, 1M+8K)
end_bio_extent_extent_readpage() entered
|- extent_start = 0;
|- extent_end = 0;
|- bio_for_each_segment_all() {
| |- /* Got the 1st bvec */
| |- start = SZ_1M;
| |- end = SZ_1M + SZ_4K - 1;
| |- update = 1;
| |- if (extent_len == 0) {
| | |- extent_start = start; /* SZ_1M */
| | |- extent_len = end + 1 - start; /* SZ_1M */
| | }
| |
| |- /* Got the 2nd bvec */
| |- start = SZ_1M + 4K;
| |- end = SZ_1M + 4K - 1;
| |- update = 1;
| |- if (extent_start + extent_len == start) {
| | |- extent_len += end + 1 - start; /* SZ_8K */
| | }
| } /* All bio vec iterated */
|
|- if (extent_len) {
|- endio_readpage_release_extent(tree, extent_start, extent_len,
update);
/* extent_start == SZ_1M, extent_len == SZ_8K, uptodate = 1 */
As the above flow shows, the existing code in end_bio_extent_readpage()
is accumulates extent_start/extent_len, and when the contiguous range
stops, calls endio_readpage_release_extent() for the range.
However current behavior has something not really considered:
- The inode can change
For bio, its pages don't need to have contiguous page_offset.
This means, even pages from different inodes can be packed into one
bio.
- bvec cross page boundary
There is a feature called multi-page bvec, where bvec->bv_len can go
beyond bvec->bv_page boundary.
- Poor readability
This patch will address the problem:
- Introduce a proper structure, processed_extent, to record processed
extent range
- Integrate inode/start/end/uptodate check into
endio_readpage_release_extent()
- Add more comment on each step.
This should greatly improve the readability, now in
end_bio_extent_readpage() there are only two
endio_readpage_release_extent() calls.
- Add inode check for contiguity
Now we also ensure the inode is the same one before checking if the
range is contiguous.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 20:51:28 +08:00
|
|
|
|
|
|
|
update:
|
|
|
|
/* Update processed to current range */
|
|
|
|
processed->inode = inode;
|
|
|
|
processed->start = start;
|
|
|
|
processed->end = end;
|
|
|
|
processed->uptodate = uptodate;
|
2013-07-25 19:22:35 +08:00
|
|
|
}
|
|
|
|
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page)
|
|
|
|
{
|
|
|
|
ASSERT(PageLocked(page));
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (!btrfs_is_subpage(fs_info, page))
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
ASSERT(PagePrivate(page));
|
|
|
|
btrfs_subpage_start_reader(fs_info, page, page_offset(page), PAGE_SIZE);
|
|
|
|
}
|
|
|
|
|
btrfs: subpage: fix wild pointer access during metadata read failure
[BUG]
When running fstests for btrfs subpage read-write test, it has a very
high chance to crash at generic/475 with the following stack:
BTRFS warning (device dm-8): direct IO failed ino 510 rw 1,34817 sector 0xcdf0 len 94208 err no 10
Unable to handle kernel paging request at virtual address ffff80001157e7c0
CPU: 2 PID: 687125 Comm: kworker/u12:4 Tainted: G WC 5.12.0-rc2-custom+ #5
Hardware name: Khadas VIM3 (DT)
Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs]
pc : queued_spin_lock_slowpath+0x1a0/0x390
lr : do_raw_spin_lock+0xc4/0x11c
Call trace:
queued_spin_lock_slowpath+0x1a0/0x390
_raw_spin_lock+0x68/0x84
btree_readahead_hook+0x38/0xc0 [btrfs]
end_bio_extent_readpage+0x504/0x5f4 [btrfs]
bio_endio+0x170/0x1a4
end_workqueue_fn+0x3c/0x60 [btrfs]
btrfs_work_helper+0x1b0/0x1b4 [btrfs]
process_one_work+0x22c/0x430
worker_thread+0x70/0x3a0
kthread+0x13c/0x140
ret_from_fork+0x10/0x30
Code: 910020e0 8b0200c2 f861d884 aa0203e1 (f8246827)
[CAUSE]
In end_bio_extent_readpage(), if we hit an error during read, we will
handle the error differently for data and metadata.
For data we queue a repair, while for metadata, we record the error and
let the caller choose what to do.
But the code is still using page->private to grab extent buffer, which
no longer points to extent buffer for subpage metadata pages.
Thus this wild pointer access leads to above crash.
[FIX]
Introduce a helper, find_extent_buffer_readpage(), to grab extent
buffer.
The difference against find_extent_buffer_nospinlock() is:
- Also handles regular sectorsize == PAGE_SIZE case
- No extent buffer refs increase/decrease
As extent buffer under IO must have non-zero refs, so this is safe
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-15 13:39:14 +08:00
|
|
|
/*
|
2022-07-15 19:59:31 +08:00
|
|
|
* Find extent buffer for a givne bytenr.
|
btrfs: subpage: fix wild pointer access during metadata read failure
[BUG]
When running fstests for btrfs subpage read-write test, it has a very
high chance to crash at generic/475 with the following stack:
BTRFS warning (device dm-8): direct IO failed ino 510 rw 1,34817 sector 0xcdf0 len 94208 err no 10
Unable to handle kernel paging request at virtual address ffff80001157e7c0
CPU: 2 PID: 687125 Comm: kworker/u12:4 Tainted: G WC 5.12.0-rc2-custom+ #5
Hardware name: Khadas VIM3 (DT)
Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs]
pc : queued_spin_lock_slowpath+0x1a0/0x390
lr : do_raw_spin_lock+0xc4/0x11c
Call trace:
queued_spin_lock_slowpath+0x1a0/0x390
_raw_spin_lock+0x68/0x84
btree_readahead_hook+0x38/0xc0 [btrfs]
end_bio_extent_readpage+0x504/0x5f4 [btrfs]
bio_endio+0x170/0x1a4
end_workqueue_fn+0x3c/0x60 [btrfs]
btrfs_work_helper+0x1b0/0x1b4 [btrfs]
process_one_work+0x22c/0x430
worker_thread+0x70/0x3a0
kthread+0x13c/0x140
ret_from_fork+0x10/0x30
Code: 910020e0 8b0200c2 f861d884 aa0203e1 (f8246827)
[CAUSE]
In end_bio_extent_readpage(), if we hit an error during read, we will
handle the error differently for data and metadata.
For data we queue a repair, while for metadata, we record the error and
let the caller choose what to do.
But the code is still using page->private to grab extent buffer, which
no longer points to extent buffer for subpage metadata pages.
Thus this wild pointer access leads to above crash.
[FIX]
Introduce a helper, find_extent_buffer_readpage(), to grab extent
buffer.
The difference against find_extent_buffer_nospinlock() is:
- Also handles regular sectorsize == PAGE_SIZE case
- No extent buffer refs increase/decrease
As extent buffer under IO must have non-zero refs, so this is safe
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-15 13:39:14 +08:00
|
|
|
*
|
|
|
|
* This is for end_bio_extent_readpage(), thus we can't do any unsafe locking
|
|
|
|
* in endio context.
|
|
|
|
*/
|
|
|
|
static struct extent_buffer *find_extent_buffer_readpage(
|
|
|
|
struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
|
|
|
|
{
|
|
|
|
struct extent_buffer *eb;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For regular sectorsize, we can use page->private to grab extent
|
|
|
|
* buffer
|
|
|
|
*/
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (fs_info->nodesize >= PAGE_SIZE) {
|
btrfs: subpage: fix wild pointer access during metadata read failure
[BUG]
When running fstests for btrfs subpage read-write test, it has a very
high chance to crash at generic/475 with the following stack:
BTRFS warning (device dm-8): direct IO failed ino 510 rw 1,34817 sector 0xcdf0 len 94208 err no 10
Unable to handle kernel paging request at virtual address ffff80001157e7c0
CPU: 2 PID: 687125 Comm: kworker/u12:4 Tainted: G WC 5.12.0-rc2-custom+ #5
Hardware name: Khadas VIM3 (DT)
Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs]
pc : queued_spin_lock_slowpath+0x1a0/0x390
lr : do_raw_spin_lock+0xc4/0x11c
Call trace:
queued_spin_lock_slowpath+0x1a0/0x390
_raw_spin_lock+0x68/0x84
btree_readahead_hook+0x38/0xc0 [btrfs]
end_bio_extent_readpage+0x504/0x5f4 [btrfs]
bio_endio+0x170/0x1a4
end_workqueue_fn+0x3c/0x60 [btrfs]
btrfs_work_helper+0x1b0/0x1b4 [btrfs]
process_one_work+0x22c/0x430
worker_thread+0x70/0x3a0
kthread+0x13c/0x140
ret_from_fork+0x10/0x30
Code: 910020e0 8b0200c2 f861d884 aa0203e1 (f8246827)
[CAUSE]
In end_bio_extent_readpage(), if we hit an error during read, we will
handle the error differently for data and metadata.
For data we queue a repair, while for metadata, we record the error and
let the caller choose what to do.
But the code is still using page->private to grab extent buffer, which
no longer points to extent buffer for subpage metadata pages.
Thus this wild pointer access leads to above crash.
[FIX]
Introduce a helper, find_extent_buffer_readpage(), to grab extent
buffer.
The difference against find_extent_buffer_nospinlock() is:
- Also handles regular sectorsize == PAGE_SIZE case
- No extent buffer refs increase/decrease
As extent buffer under IO must have non-zero refs, so this is safe
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-15 13:39:14 +08:00
|
|
|
ASSERT(PagePrivate(page) && page->private);
|
|
|
|
return (struct extent_buffer *)page->private;
|
|
|
|
}
|
|
|
|
|
2022-07-15 19:59:31 +08:00
|
|
|
/* For subpage case, we need to lookup buffer radix tree */
|
|
|
|
rcu_read_lock();
|
|
|
|
eb = radix_tree_lookup(&fs_info->buffer_radix,
|
|
|
|
bytenr >> fs_info->sectorsize_bits);
|
|
|
|
rcu_read_unlock();
|
btrfs: subpage: fix wild pointer access during metadata read failure
[BUG]
When running fstests for btrfs subpage read-write test, it has a very
high chance to crash at generic/475 with the following stack:
BTRFS warning (device dm-8): direct IO failed ino 510 rw 1,34817 sector 0xcdf0 len 94208 err no 10
Unable to handle kernel paging request at virtual address ffff80001157e7c0
CPU: 2 PID: 687125 Comm: kworker/u12:4 Tainted: G WC 5.12.0-rc2-custom+ #5
Hardware name: Khadas VIM3 (DT)
Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs]
pc : queued_spin_lock_slowpath+0x1a0/0x390
lr : do_raw_spin_lock+0xc4/0x11c
Call trace:
queued_spin_lock_slowpath+0x1a0/0x390
_raw_spin_lock+0x68/0x84
btree_readahead_hook+0x38/0xc0 [btrfs]
end_bio_extent_readpage+0x504/0x5f4 [btrfs]
bio_endio+0x170/0x1a4
end_workqueue_fn+0x3c/0x60 [btrfs]
btrfs_work_helper+0x1b0/0x1b4 [btrfs]
process_one_work+0x22c/0x430
worker_thread+0x70/0x3a0
kthread+0x13c/0x140
ret_from_fork+0x10/0x30
Code: 910020e0 8b0200c2 f861d884 aa0203e1 (f8246827)
[CAUSE]
In end_bio_extent_readpage(), if we hit an error during read, we will
handle the error differently for data and metadata.
For data we queue a repair, while for metadata, we record the error and
let the caller choose what to do.
But the code is still using page->private to grab extent buffer, which
no longer points to extent buffer for subpage metadata pages.
Thus this wild pointer access leads to above crash.
[FIX]
Introduce a helper, find_extent_buffer_readpage(), to grab extent
buffer.
The difference against find_extent_buffer_nospinlock() is:
- Also handles regular sectorsize == PAGE_SIZE case
- No extent buffer refs increase/decrease
As extent buffer under IO must have non-zero refs, so this is safe
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-15 13:39:14 +08:00
|
|
|
ASSERT(eb);
|
|
|
|
return eb;
|
|
|
|
}
|
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
/*
|
|
|
|
* after a readpage IO is done, we need to:
|
|
|
|
* clear the uptodate bits on error
|
|
|
|
* set the uptodate bits if things worked
|
|
|
|
* set the page up to date if all extents in the tree are uptodate
|
|
|
|
* clear the lock bit in the extent tree
|
|
|
|
* unlock the page if there are no other extents locked for it
|
|
|
|
*
|
|
|
|
* Scheduling is not allowed, so the extent state tree is expected
|
|
|
|
* to have one and only one object corresponding to this IO.
|
|
|
|
*/
|
2022-08-06 16:03:26 +08:00
|
|
|
static void end_bio_extent_readpage(struct btrfs_bio *bbio)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2022-08-06 16:03:26 +08:00
|
|
|
struct bio *bio = &bbio->bio;
|
2013-11-08 04:20:26 +08:00
|
|
|
struct bio_vec *bvec;
|
btrfs: add structure to keep track of extent range in end_bio_extent_readpage
In end_bio_extent_readpage() we had a strange dance around
extent_start/extent_len.
Hidden behind the strange dance is, it's just calling
endio_readpage_release_extent() on each bvec range.
Here is an example to explain the original work flow:
Bio is for inode 257, containing 2 pages, for range [1M, 1M+8K)
end_bio_extent_extent_readpage() entered
|- extent_start = 0;
|- extent_end = 0;
|- bio_for_each_segment_all() {
| |- /* Got the 1st bvec */
| |- start = SZ_1M;
| |- end = SZ_1M + SZ_4K - 1;
| |- update = 1;
| |- if (extent_len == 0) {
| | |- extent_start = start; /* SZ_1M */
| | |- extent_len = end + 1 - start; /* SZ_1M */
| | }
| |
| |- /* Got the 2nd bvec */
| |- start = SZ_1M + 4K;
| |- end = SZ_1M + 4K - 1;
| |- update = 1;
| |- if (extent_start + extent_len == start) {
| | |- extent_len += end + 1 - start; /* SZ_8K */
| | }
| } /* All bio vec iterated */
|
|- if (extent_len) {
|- endio_readpage_release_extent(tree, extent_start, extent_len,
update);
/* extent_start == SZ_1M, extent_len == SZ_8K, uptodate = 1 */
As the above flow shows, the existing code in end_bio_extent_readpage()
is accumulates extent_start/extent_len, and when the contiguous range
stops, calls endio_readpage_release_extent() for the range.
However current behavior has something not really considered:
- The inode can change
For bio, its pages don't need to have contiguous page_offset.
This means, even pages from different inodes can be packed into one
bio.
- bvec cross page boundary
There is a feature called multi-page bvec, where bvec->bv_len can go
beyond bvec->bv_page boundary.
- Poor readability
This patch will address the problem:
- Introduce a proper structure, processed_extent, to record processed
extent range
- Integrate inode/start/end/uptodate check into
endio_readpage_release_extent()
- Add more comment on each step.
This should greatly improve the readability, now in
end_bio_extent_readpage() there are only two
endio_readpage_release_extent() calls.
- Add inode check for contiguity
Now we also ensure the inode is the same one before checking if the
range is contiguous.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 20:51:28 +08:00
|
|
|
struct processed_extent processed = { 0 };
|
2020-12-02 14:47:58 +08:00
|
|
|
/*
|
|
|
|
* The offset to the beginning of a bio, since one bio can never be
|
|
|
|
* larger than UINT_MAX, u32 here is enough.
|
|
|
|
*/
|
|
|
|
u32 bio_offset = 0;
|
2012-04-16 21:42:26 +08:00
|
|
|
int mirror;
|
2019-02-15 19:13:19 +08:00
|
|
|
struct bvec_iter_all iter_all;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2017-07-14 00:10:07 +08:00
|
|
|
ASSERT(!bio_flagged(bio, BIO_CLONED));
|
2019-04-25 15:03:00 +08:00
|
|
|
bio_for_each_segment_all(bvec, bio, iter_all) {
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
bool uptodate = !bio->bi_status;
|
2008-01-25 05:13:08 +08:00
|
|
|
struct page *page = bvec->bv_page;
|
2013-06-18 05:14:39 +08:00
|
|
|
struct inode *inode = page->mapping->host;
|
2016-09-20 22:05:02 +08:00
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
|
2020-12-02 14:47:58 +08:00
|
|
|
const u32 sectorsize = fs_info->sectorsize;
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
unsigned int error_bitmap = (unsigned int)-1;
|
2022-05-22 19:47:51 +08:00
|
|
|
bool repair = false;
|
2020-12-02 14:47:58 +08:00
|
|
|
u64 start;
|
|
|
|
u64 end;
|
|
|
|
u32 len;
|
2011-04-06 18:02:20 +08:00
|
|
|
|
2016-09-20 22:05:02 +08:00
|
|
|
btrfs_debug(fs_info,
|
|
|
|
"end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u",
|
2020-11-26 22:41:27 +08:00
|
|
|
bio->bi_iter.bi_sector, bio->bi_status,
|
2021-09-15 15:17:18 +08:00
|
|
|
bbio->mirror_num);
|
2008-08-20 20:51:49 +08:00
|
|
|
|
2020-10-21 14:24:58 +08:00
|
|
|
/*
|
|
|
|
* We always issue full-sector reads, but if some block in a
|
|
|
|
* page fails to read, blk_update_request() will advance
|
|
|
|
* bv_offset and adjust bv_len to compensate. Print a warning
|
|
|
|
* for unaligned offsets, and an error if they don't add up to
|
|
|
|
* a full sector.
|
|
|
|
*/
|
|
|
|
if (!IS_ALIGNED(bvec->bv_offset, sectorsize))
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"partial page read in btrfs with offset %u and length %u",
|
|
|
|
bvec->bv_offset, bvec->bv_len);
|
|
|
|
else if (!IS_ALIGNED(bvec->bv_offset + bvec->bv_len,
|
|
|
|
sectorsize))
|
|
|
|
btrfs_info(fs_info,
|
|
|
|
"incomplete page read with offset %u and length %u",
|
|
|
|
bvec->bv_offset, bvec->bv_len);
|
|
|
|
|
|
|
|
start = page_offset(page) + bvec->bv_offset;
|
|
|
|
end = start + bvec->bv_len - 1;
|
2013-07-25 19:22:34 +08:00
|
|
|
len = bvec->bv_len;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2021-09-15 15:17:18 +08:00
|
|
|
mirror = bbio->mirror_num;
|
2018-11-22 16:17:49 +08:00
|
|
|
if (likely(uptodate)) {
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
if (is_data_inode(inode)) {
|
2021-09-15 15:17:18 +08:00
|
|
|
error_bitmap = btrfs_verify_data_csum(bbio,
|
2021-03-03 20:55:37 +08:00
|
|
|
bio_offset, page, start, end);
|
2022-05-22 19:47:51 +08:00
|
|
|
if (error_bitmap)
|
|
|
|
uptodate = false;
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
} else {
|
2022-05-22 19:47:51 +08:00
|
|
|
if (btrfs_validate_metadata_buffer(bbio,
|
|
|
|
page, start, end, mirror))
|
|
|
|
uptodate = false;
|
btrfs: submit read time repair only for each corrupted sector
Currently btrfs_submit_read_repair() has some extra check on whether the
failed bio needs extra validation for repair. But we can avoid all
these extra mechanisms if we submit the repair for each sector.
By this, each read repair can be easily handled without the need to
verify which sector is corrupted.
This will also benefit subpage, as one subpage bvec can contain several
sectors, making the extra verification more complex.
So this patch will:
- Introduce repair_one_sector()
The main code submitting repair, which is more or less the same as old
btrfs_submit_read_repair().
But this time, it only repairs one sector.
- Make btrfs_submit_read_repair() to handle sectors differently
There are 3 different cases:
* Good sector
We need to release the page and extent, set the range uptodate.
* Bad sector and failed to submit repair bio
We need to release the page and extent, but not set the range
uptodate.
* Bad sector but repair bio submitted
The page and extent release will be handled by the submitted repair
bio. Nothing needs to be done.
Since btrfs_submit_read_repair() will handle the page and extent
release now, we need to skip to next bvec even we hit some error.
- Change the lifespan of @uptodate in end_bio_extent_readpage()
Since now btrfs_submit_read_repair() will handle the full bvec
which contains any corruption, we don't need to bother updating
@uptodate bit anymore.
Just let @uptodate to be local variable inside the main loop,
so that any error from one bvec won't affect later bvec.
- Only export btrfs_repair_one_sector(), unexport
btrfs_submit_read_repair()
The only outside caller for read repair is DIO, which already submits
its repair for just one sector.
Only export btrfs_repair_one_sector() for DIO.
This patch will focus on the change on the repair path, the extra
validation code is still kept as is, and will be cleaned up later.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-05-03 10:08:55 +08:00
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
2012-03-27 09:57:36 +08:00
|
|
|
|
2013-07-25 19:22:35 +08:00
|
|
|
if (likely(uptodate)) {
|
2013-06-18 05:14:39 +08:00
|
|
|
loff_t i_size = i_size_read(inode);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
pgoff_t end_index = i_size >> PAGE_SHIFT;
|
2013-06-18 05:14:39 +08:00
|
|
|
|
2022-09-10 05:53:14 +08:00
|
|
|
btrfs_clean_io_failure(BTRFS_I(inode), start, page, 0);
|
2022-05-22 19:47:51 +08:00
|
|
|
|
btrfs: subpage: fix the false data csum mismatch error
[BUG]
When running fstresss, we can hit strange data csum mismatch where the
on-disk data is in fact correct (passes scrub).
With some extra debug info added, we have the following traces:
0482us: btrfs_do_readpage: root=5 ino=284 offset=393216, submit force=0 pgoff=0 iosize=8192
0494us: btrfs_do_readpage: root=5 ino=284 offset=401408, submit force=0 pgoff=8192 iosize=4096
0498us: btrfs_submit_data_bio: root=5 ino=284 bio first bvec=393216 len=8192
0591us: btrfs_do_readpage: root=5 ino=284 offset=405504, submit force=0 pgoff=12288 iosize=36864
0594us: btrfs_submit_data_bio: root=5 ino=284 bio first bvec=401408 len=4096
0863us: btrfs_submit_data_bio: root=5 ino=284 bio first bvec=405504 len=36864
0933us: btrfs_verify_data_csum: root=5 ino=284 offset=393216 len=8192
0967us: btrfs_do_readpage: root=5 ino=284 offset=442368, skip beyond isize pgoff=49152 iosize=16384
1047us: btrfs_verify_data_csum: root=5 ino=284 offset=401408 len=4096
1163us: btrfs_verify_data_csum: root=5 ino=284 offset=405504 len=36864
1290us: check_data_csum: !!! root=5 ino=284 offset=438272 pg_off=45056 !!!
7387us: end_bio_extent_readpage: root=5 ino=284 before pending_read_bios=0
[CAUSE]
Normally we expect all submitted bio reads to only touch the range we
specified, and under subpage context, it means we should only touch the
range specified in each bvec.
But in data read path, inside end_bio_extent_readpage(), we have page
zeroing which only takes regular page size into consideration.
This means for subpage if we have an inode whose content looks like below:
0 16K 32K 48K 64K
|///////| |///////| |
|//| = data needs to be read from disk
| | = hole
And i_size is 64K initially.
Then the following race can happen:
T1 | T2
--------------------------------+--------------------------------
btrfs_do_readpage() |
|- isize = 64K; |
| At this time, the isize is |
| 64K |
| |
|- submit_extent_page() |
| submit previous assembled bio|
| assemble bio for [0, 16K) |
| |
|- submit_extent_page() |
submit read bio for [0, 16K) |
assemble read bio for |
[32K, 48K) |
|
| btrfs_setsize()
| |- i_size_write(, 16K);
| Now i_size is only 16K
end_io() for [0K, 16K) |
|- end_bio_extent_readpage() |
|- btrfs_verify_data_csum() |
| No csum error |
|- i_size = 16K; |
|- zero_user_segment(16K, |
PAGE_SIZE); |
!!! We zeroed range |
!!! [32K, 48K) |
| end_io for [32K, 48K)
| |- end_bio_extent_readpage()
| |- btrfs_verify_data_csum()
| ! CSUM MISMATCH !
| ! As the range is zeroed now !
[FIX]
To fix the problem, make end_bio_extent_readpage() to only zero the
range of bvec.
The bug only affects subpage read-write support, as for full read-only
mount we can't change i_size thus won't hit the race condition.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-01 16:44:22 +08:00
|
|
|
/*
|
|
|
|
* Zero out the remaining part if this range straddles
|
|
|
|
* i_size.
|
|
|
|
*
|
|
|
|
* Here we should only zero the range inside the bvec,
|
|
|
|
* not touch anything else.
|
|
|
|
*
|
|
|
|
* NOTE: i_size is exclusive while end is inclusive.
|
|
|
|
*/
|
|
|
|
if (page->index == end_index && i_size <= end) {
|
|
|
|
u32 zero_start = max(offset_in_page(i_size),
|
2021-03-08 17:20:17 +08:00
|
|
|
offset_in_page(start));
|
btrfs: subpage: fix the false data csum mismatch error
[BUG]
When running fstresss, we can hit strange data csum mismatch where the
on-disk data is in fact correct (passes scrub).
With some extra debug info added, we have the following traces:
0482us: btrfs_do_readpage: root=5 ino=284 offset=393216, submit force=0 pgoff=0 iosize=8192
0494us: btrfs_do_readpage: root=5 ino=284 offset=401408, submit force=0 pgoff=8192 iosize=4096
0498us: btrfs_submit_data_bio: root=5 ino=284 bio first bvec=393216 len=8192
0591us: btrfs_do_readpage: root=5 ino=284 offset=405504, submit force=0 pgoff=12288 iosize=36864
0594us: btrfs_submit_data_bio: root=5 ino=284 bio first bvec=401408 len=4096
0863us: btrfs_submit_data_bio: root=5 ino=284 bio first bvec=405504 len=36864
0933us: btrfs_verify_data_csum: root=5 ino=284 offset=393216 len=8192
0967us: btrfs_do_readpage: root=5 ino=284 offset=442368, skip beyond isize pgoff=49152 iosize=16384
1047us: btrfs_verify_data_csum: root=5 ino=284 offset=401408 len=4096
1163us: btrfs_verify_data_csum: root=5 ino=284 offset=405504 len=36864
1290us: check_data_csum: !!! root=5 ino=284 offset=438272 pg_off=45056 !!!
7387us: end_bio_extent_readpage: root=5 ino=284 before pending_read_bios=0
[CAUSE]
Normally we expect all submitted bio reads to only touch the range we
specified, and under subpage context, it means we should only touch the
range specified in each bvec.
But in data read path, inside end_bio_extent_readpage(), we have page
zeroing which only takes regular page size into consideration.
This means for subpage if we have an inode whose content looks like below:
0 16K 32K 48K 64K
|///////| |///////| |
|//| = data needs to be read from disk
| | = hole
And i_size is 64K initially.
Then the following race can happen:
T1 | T2
--------------------------------+--------------------------------
btrfs_do_readpage() |
|- isize = 64K; |
| At this time, the isize is |
| 64K |
| |
|- submit_extent_page() |
| submit previous assembled bio|
| assemble bio for [0, 16K) |
| |
|- submit_extent_page() |
submit read bio for [0, 16K) |
assemble read bio for |
[32K, 48K) |
|
| btrfs_setsize()
| |- i_size_write(, 16K);
| Now i_size is only 16K
end_io() for [0K, 16K) |
|- end_bio_extent_readpage() |
|- btrfs_verify_data_csum() |
| No csum error |
|- i_size = 16K; |
|- zero_user_segment(16K, |
PAGE_SIZE); |
!!! We zeroed range |
!!! [32K, 48K) |
| end_io for [32K, 48K)
| |- end_bio_extent_readpage()
| |- btrfs_verify_data_csum()
| ! CSUM MISMATCH !
| ! As the range is zeroed now !
[FIX]
To fix the problem, make end_bio_extent_readpage() to only zero the
range of bvec.
The bug only affects subpage read-write support, as for full read-only
mount we can't change i_size thus won't hit the race condition.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-01 16:44:22 +08:00
|
|
|
|
|
|
|
zero_user_segment(page, zero_start,
|
|
|
|
offset_in_page(end) + 1);
|
|
|
|
}
|
2022-05-22 19:47:51 +08:00
|
|
|
} else if (is_data_inode(inode)) {
|
|
|
|
/*
|
|
|
|
* Only try to repair bios that actually made it to a
|
|
|
|
* device. If the bio failed to be submitted mirror
|
|
|
|
* is 0 and we need to fail it without retrying.
|
2022-07-07 13:33:30 +08:00
|
|
|
*
|
|
|
|
* This also includes the high level bios for compressed
|
|
|
|
* extents - these never make it to a device and repair
|
|
|
|
* is already handled on the lower compressed bio.
|
2022-05-22 19:47:51 +08:00
|
|
|
*/
|
|
|
|
if (mirror > 0)
|
|
|
|
repair = true;
|
|
|
|
} else {
|
|
|
|
struct extent_buffer *eb;
|
|
|
|
|
|
|
|
eb = find_extent_buffer_readpage(fs_info, page, start);
|
|
|
|
set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
|
|
|
|
eb->read_mirror = mirror;
|
|
|
|
atomic_dec(&eb->io_pages);
|
2008-01-29 22:59:12 +08:00
|
|
|
}
|
2022-05-22 19:47:51 +08:00
|
|
|
|
|
|
|
if (repair) {
|
|
|
|
/*
|
|
|
|
* submit_data_read_repair() will handle all the good
|
|
|
|
* and bad sectors, we just continue to the next bvec.
|
|
|
|
*/
|
2022-07-07 13:33:28 +08:00
|
|
|
submit_data_read_repair(inode, bbio, bio_offset, bvec,
|
|
|
|
error_bitmap);
|
2022-05-22 19:47:51 +08:00
|
|
|
} else {
|
|
|
|
/* Update page status and unlock */
|
|
|
|
end_page_read(page, uptodate, start, len);
|
|
|
|
endio_readpage_release_extent(&processed, BTRFS_I(inode),
|
|
|
|
start, end, PageUptodate(page));
|
2008-01-29 22:59:12 +08:00
|
|
|
}
|
2022-05-22 19:47:51 +08:00
|
|
|
|
2020-12-02 14:47:58 +08:00
|
|
|
ASSERT(bio_offset + len > bio_offset);
|
|
|
|
bio_offset += len;
|
2013-07-25 19:22:35 +08:00
|
|
|
|
2013-11-08 04:20:26 +08:00
|
|
|
}
|
btrfs: add structure to keep track of extent range in end_bio_extent_readpage
In end_bio_extent_readpage() we had a strange dance around
extent_start/extent_len.
Hidden behind the strange dance is, it's just calling
endio_readpage_release_extent() on each bvec range.
Here is an example to explain the original work flow:
Bio is for inode 257, containing 2 pages, for range [1M, 1M+8K)
end_bio_extent_extent_readpage() entered
|- extent_start = 0;
|- extent_end = 0;
|- bio_for_each_segment_all() {
| |- /* Got the 1st bvec */
| |- start = SZ_1M;
| |- end = SZ_1M + SZ_4K - 1;
| |- update = 1;
| |- if (extent_len == 0) {
| | |- extent_start = start; /* SZ_1M */
| | |- extent_len = end + 1 - start; /* SZ_1M */
| | }
| |
| |- /* Got the 2nd bvec */
| |- start = SZ_1M + 4K;
| |- end = SZ_1M + 4K - 1;
| |- update = 1;
| |- if (extent_start + extent_len == start) {
| | |- extent_len += end + 1 - start; /* SZ_8K */
| | }
| } /* All bio vec iterated */
|
|- if (extent_len) {
|- endio_readpage_release_extent(tree, extent_start, extent_len,
update);
/* extent_start == SZ_1M, extent_len == SZ_8K, uptodate = 1 */
As the above flow shows, the existing code in end_bio_extent_readpage()
is accumulates extent_start/extent_len, and when the contiguous range
stops, calls endio_readpage_release_extent() for the range.
However current behavior has something not really considered:
- The inode can change
For bio, its pages don't need to have contiguous page_offset.
This means, even pages from different inodes can be packed into one
bio.
- bvec cross page boundary
There is a feature called multi-page bvec, where bvec->bv_len can go
beyond bvec->bv_page boundary.
- Poor readability
This patch will address the problem:
- Introduce a proper structure, processed_extent, to record processed
extent range
- Integrate inode/start/end/uptodate check into
endio_readpage_release_extent()
- Add more comment on each step.
This should greatly improve the readability, now in
end_bio_extent_readpage() there are only two
endio_readpage_release_extent() calls.
- Add inode check for contiguity
Now we also ensure the inode is the same one before checking if the
range is contiguous.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 20:51:28 +08:00
|
|
|
/* Release the last extent */
|
|
|
|
endio_readpage_release_extent(&processed, NULL, 0, 0, false);
|
2021-09-15 15:17:18 +08:00
|
|
|
btrfs_bio_free_csum(bbio);
|
2008-01-25 05:13:08 +08:00
|
|
|
bio_put(bio);
|
|
|
|
}
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
2022-03-31 04:11:22 +08:00
|
|
|
* Populate every free slot in a provided array with pages.
|
|
|
|
*
|
|
|
|
* @nr_pages: number of pages to allocate
|
|
|
|
* @page_array: the array to fill with pages; any existing non-null entries in
|
|
|
|
* the array will be skipped
|
|
|
|
*
|
|
|
|
* Return: 0 if all pages were able to be allocated;
|
|
|
|
* -ENOMEM otherwise, and the caller is responsible for freeing all
|
|
|
|
* non-null page pointers in the array.
|
|
|
|
*/
|
|
|
|
int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
|
|
|
|
{
|
2022-03-31 04:11:23 +08:00
|
|
|
unsigned int allocated;
|
2022-03-31 04:11:22 +08:00
|
|
|
|
2022-03-31 04:11:23 +08:00
|
|
|
for (allocated = 0; allocated < nr_pages;) {
|
|
|
|
unsigned int last = allocated;
|
2022-03-31 04:11:22 +08:00
|
|
|
|
2022-03-31 04:11:23 +08:00
|
|
|
allocated = alloc_pages_bulk_array(GFP_NOFS, nr_pages, page_array);
|
|
|
|
|
2022-04-07 02:24:18 +08:00
|
|
|
if (allocated == nr_pages)
|
|
|
|
return 0;
|
|
|
|
|
2022-03-31 04:11:23 +08:00
|
|
|
/*
|
|
|
|
* During this iteration, no page could be allocated, even
|
|
|
|
* though alloc_pages_bulk_array() falls back to alloc_page()
|
|
|
|
* if it could not bulk-allocate. So we must be out of memory.
|
|
|
|
*/
|
|
|
|
if (allocated == last)
|
2022-03-31 04:11:22 +08:00
|
|
|
return -ENOMEM;
|
2022-04-07 02:24:18 +08:00
|
|
|
|
|
|
|
memalloc_retry_wait(GFP_NOFS);
|
2022-03-31 04:11:22 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
|
|
|
* Attempt to add a page to bio.
|
2021-02-04 18:21:57 +08:00
|
|
|
*
|
2022-10-27 20:21:42 +08:00
|
|
|
* @bio_ctrl: record both the bio, and its bio_flags
|
|
|
|
* @page: page to add to the bio
|
|
|
|
* @disk_bytenr: offset of the new bio or to check whether we are adding
|
|
|
|
* a contiguous page to the previous one
|
|
|
|
* @size: portion of page that we want to write
|
|
|
|
* @pg_offset: starting offset in the page
|
|
|
|
* @compress_type: compression type of the current bio to see if we can merge them
|
2021-02-04 18:21:57 +08:00
|
|
|
*
|
|
|
|
* Attempt to add a page to bio considering stripe alignment etc.
|
|
|
|
*
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
* Return >= 0 for the number of bytes added to the bio.
|
|
|
|
* Can return 0 if the current bio is already at stripe/zone boundary.
|
|
|
|
* Return <0 for error.
|
2021-02-04 18:21:57 +08:00
|
|
|
*/
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
|
|
|
|
struct page *page,
|
|
|
|
u64 disk_bytenr, unsigned int size,
|
|
|
|
unsigned int pg_offset,
|
2021-07-27 20:59:41 +08:00
|
|
|
enum btrfs_compression_type compress_type)
|
2021-02-04 18:21:57 +08:00
|
|
|
{
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
struct bio *bio = bio_ctrl->bio;
|
|
|
|
u32 bio_size = bio->bi_iter.bi_size;
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
u32 real_size;
|
2021-02-04 18:21:57 +08:00
|
|
|
const sector_t sector = disk_bytenr >> SECTOR_SHIFT;
|
btrfs: don't merge pages into bio if their page offset is not contiguous
[BUG]
Zygo reported on latest development branch, he could hit
ASSERT()/BUG_ON() caused crash when doing RAID5 recovery (intentionally
corrupt one disk, and let btrfs to recover the data during read/scrub).
And The following minimal reproducer can cause extent state leakage at
rmmod time:
mkfs.btrfs -f -d raid5 -m raid5 $dev1 $dev2 $dev3 -b 1G > /dev/null
mount $dev1 $mnt
fsstress -w -d $mnt -n 25 -s 1660807876
sync
fssum -A -f -w /tmp/fssum.saved $mnt
umount $mnt
# Wipe the dev1 but keeps its super block
xfs_io -c "pwrite -S 0x0 1m 1023m" $dev1
mount $dev1 $mnt
fssum -r /tmp/fssum.saved $mnt > /dev/null
umount $mnt
rmmod btrfs
This will lead to the following extent states leakage:
BTRFS: state leak: start 499712 end 503807 state 5 in tree 1 refs 1
BTRFS: state leak: start 495616 end 499711 state 5 in tree 1 refs 1
BTRFS: state leak: start 491520 end 495615 state 5 in tree 1 refs 1
BTRFS: state leak: start 487424 end 491519 state 5 in tree 1 refs 1
BTRFS: state leak: start 483328 end 487423 state 5 in tree 1 refs 1
BTRFS: state leak: start 479232 end 483327 state 5 in tree 1 refs 1
BTRFS: state leak: start 475136 end 479231 state 5 in tree 1 refs 1
BTRFS: state leak: start 471040 end 475135 state 5 in tree 1 refs 1
[CAUSE]
Since commit 7aa51232e204 ("btrfs: pass a btrfs_bio to
btrfs_repair_one_sector"), we always use btrfs_bio->file_offset to
determine the file offset of a page.
But that usage assume that, one bio has all its page having a continuous
page offsets.
Unfortunately that's not true, btrfs only requires the logical bytenr
contiguous when assembling its bios.
From above script, we have one bio looks like this:
fssum-27671 submit_one_bio: bio logical=217739264 len=36864
fssum-27671 submit_one_bio: r/i=5/261 page_offset=466944 <<<
fssum-27671 submit_one_bio: r/i=5/261 page_offset=724992 <<<
fssum-27671 submit_one_bio: r/i=5/261 page_offset=729088
fssum-27671 submit_one_bio: r/i=5/261 page_offset=733184
fssum-27671 submit_one_bio: r/i=5/261 page_offset=737280
fssum-27671 submit_one_bio: r/i=5/261 page_offset=741376
fssum-27671 submit_one_bio: r/i=5/261 page_offset=745472
fssum-27671 submit_one_bio: r/i=5/261 page_offset=749568
fssum-27671 submit_one_bio: r/i=5/261 page_offset=753664
Note that the 1st and the 2nd page has non-contiguous page offsets.
This means, at repair time, we will have completely wrong file offset
passed in:
kworker/u32:2-19927 btrfs_repair_one_sector: r/i=5/261 page_off=729088 file_off=475136 bio_offset=8192
Since the file offset is incorrect, we latter incorrectly set the extent
states, and no way to really release them.
Thus later it causes the leakage.
In fact, this can be even worse, since the file offset is incorrect, we
can hit cases like the incorrect file offset belongs to a HOLE, and
later cause btrfs_num_copies() to trigger error, finally hit
BUG_ON()/ASSERT() later.
[FIX]
Add an extra condition in btrfs_bio_add_page() for uncompressed IO.
Now we will have more strict requirement for bio pages:
- They should all have the same mapping
(the mapping check is already implied by the call chain)
- Their logical bytenr should be adjacent
This is the same as the old condition.
- Their page_offset() (file offset) should be adjacent
This is the new check.
This would result a slightly increased amount of bios from btrfs
(needs holes and inside the same stripe boundary to trigger).
But this would greatly reduce the confusion, as it's pretty common
to assume a btrfs bio would only contain continuous page cache.
Later we may need extra cleanups, as we no longer needs to handle gaps
between page offsets in endio functions.
Currently this should be the minimal patch to fix commit 7aa51232e204
("btrfs: pass a btrfs_bio to btrfs_repair_one_sector").
Reported-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Fixes: 7aa51232e204 ("btrfs: pass a btrfs_bio to btrfs_repair_one_sector")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-08-13 16:06:53 +08:00
|
|
|
bool contig = false;
|
2021-02-04 18:21:58 +08:00
|
|
|
int ret;
|
2021-02-04 18:21:57 +08:00
|
|
|
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
ASSERT(bio);
|
|
|
|
/* The limit should be calculated when bio_ctrl->bio is allocated */
|
|
|
|
ASSERT(bio_ctrl->len_to_oe_boundary && bio_ctrl->len_to_stripe_boundary);
|
2021-07-27 21:11:53 +08:00
|
|
|
if (bio_ctrl->compress_type != compress_type)
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
return 0;
|
2021-02-04 18:21:57 +08:00
|
|
|
|
btrfs: don't merge pages into bio if their page offset is not contiguous
[BUG]
Zygo reported on latest development branch, he could hit
ASSERT()/BUG_ON() caused crash when doing RAID5 recovery (intentionally
corrupt one disk, and let btrfs to recover the data during read/scrub).
And The following minimal reproducer can cause extent state leakage at
rmmod time:
mkfs.btrfs -f -d raid5 -m raid5 $dev1 $dev2 $dev3 -b 1G > /dev/null
mount $dev1 $mnt
fsstress -w -d $mnt -n 25 -s 1660807876
sync
fssum -A -f -w /tmp/fssum.saved $mnt
umount $mnt
# Wipe the dev1 but keeps its super block
xfs_io -c "pwrite -S 0x0 1m 1023m" $dev1
mount $dev1 $mnt
fssum -r /tmp/fssum.saved $mnt > /dev/null
umount $mnt
rmmod btrfs
This will lead to the following extent states leakage:
BTRFS: state leak: start 499712 end 503807 state 5 in tree 1 refs 1
BTRFS: state leak: start 495616 end 499711 state 5 in tree 1 refs 1
BTRFS: state leak: start 491520 end 495615 state 5 in tree 1 refs 1
BTRFS: state leak: start 487424 end 491519 state 5 in tree 1 refs 1
BTRFS: state leak: start 483328 end 487423 state 5 in tree 1 refs 1
BTRFS: state leak: start 479232 end 483327 state 5 in tree 1 refs 1
BTRFS: state leak: start 475136 end 479231 state 5 in tree 1 refs 1
BTRFS: state leak: start 471040 end 475135 state 5 in tree 1 refs 1
[CAUSE]
Since commit 7aa51232e204 ("btrfs: pass a btrfs_bio to
btrfs_repair_one_sector"), we always use btrfs_bio->file_offset to
determine the file offset of a page.
But that usage assume that, one bio has all its page having a continuous
page offsets.
Unfortunately that's not true, btrfs only requires the logical bytenr
contiguous when assembling its bios.
From above script, we have one bio looks like this:
fssum-27671 submit_one_bio: bio logical=217739264 len=36864
fssum-27671 submit_one_bio: r/i=5/261 page_offset=466944 <<<
fssum-27671 submit_one_bio: r/i=5/261 page_offset=724992 <<<
fssum-27671 submit_one_bio: r/i=5/261 page_offset=729088
fssum-27671 submit_one_bio: r/i=5/261 page_offset=733184
fssum-27671 submit_one_bio: r/i=5/261 page_offset=737280
fssum-27671 submit_one_bio: r/i=5/261 page_offset=741376
fssum-27671 submit_one_bio: r/i=5/261 page_offset=745472
fssum-27671 submit_one_bio: r/i=5/261 page_offset=749568
fssum-27671 submit_one_bio: r/i=5/261 page_offset=753664
Note that the 1st and the 2nd page has non-contiguous page offsets.
This means, at repair time, we will have completely wrong file offset
passed in:
kworker/u32:2-19927 btrfs_repair_one_sector: r/i=5/261 page_off=729088 file_off=475136 bio_offset=8192
Since the file offset is incorrect, we latter incorrectly set the extent
states, and no way to really release them.
Thus later it causes the leakage.
In fact, this can be even worse, since the file offset is incorrect, we
can hit cases like the incorrect file offset belongs to a HOLE, and
later cause btrfs_num_copies() to trigger error, finally hit
BUG_ON()/ASSERT() later.
[FIX]
Add an extra condition in btrfs_bio_add_page() for uncompressed IO.
Now we will have more strict requirement for bio pages:
- They should all have the same mapping
(the mapping check is already implied by the call chain)
- Their logical bytenr should be adjacent
This is the same as the old condition.
- Their page_offset() (file offset) should be adjacent
This is the new check.
This would result a slightly increased amount of bios from btrfs
(needs holes and inside the same stripe boundary to trigger).
But this would greatly reduce the confusion, as it's pretty common
to assume a btrfs bio would only contain continuous page cache.
Later we may need extra cleanups, as we no longer needs to handle gaps
between page offsets in endio functions.
Currently this should be the minimal patch to fix commit 7aa51232e204
("btrfs: pass a btrfs_bio to btrfs_repair_one_sector").
Reported-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Fixes: 7aa51232e204 ("btrfs: pass a btrfs_bio to btrfs_repair_one_sector")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-08-13 16:06:53 +08:00
|
|
|
|
|
|
|
if (bio->bi_iter.bi_size == 0) {
|
|
|
|
/* We can always add a page into an empty bio. */
|
|
|
|
contig = true;
|
|
|
|
} else if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE) {
|
|
|
|
struct bio_vec *bvec = bio_last_bvec_all(bio);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The contig check requires the following conditions to be met:
|
|
|
|
* 1) The pages are belonging to the same inode
|
|
|
|
* This is implied by the call chain.
|
|
|
|
*
|
|
|
|
* 2) The range has adjacent logical bytenr
|
|
|
|
*
|
|
|
|
* 3) The range has adjacent file offset
|
|
|
|
* This is required for the usage of btrfs_bio->file_offset.
|
|
|
|
*/
|
|
|
|
if (bio_end_sector(bio) == sector &&
|
|
|
|
page_offset(bvec->bv_page) + bvec->bv_offset +
|
|
|
|
bvec->bv_len == page_offset(page) + pg_offset)
|
|
|
|
contig = true;
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* For compression, all IO should have its logical bytenr
|
|
|
|
* set to the starting bytenr of the compressed extent.
|
|
|
|
*/
|
2021-02-04 18:21:57 +08:00
|
|
|
contig = bio->bi_iter.bi_sector == sector;
|
btrfs: don't merge pages into bio if their page offset is not contiguous
[BUG]
Zygo reported on latest development branch, he could hit
ASSERT()/BUG_ON() caused crash when doing RAID5 recovery (intentionally
corrupt one disk, and let btrfs to recover the data during read/scrub).
And The following minimal reproducer can cause extent state leakage at
rmmod time:
mkfs.btrfs -f -d raid5 -m raid5 $dev1 $dev2 $dev3 -b 1G > /dev/null
mount $dev1 $mnt
fsstress -w -d $mnt -n 25 -s 1660807876
sync
fssum -A -f -w /tmp/fssum.saved $mnt
umount $mnt
# Wipe the dev1 but keeps its super block
xfs_io -c "pwrite -S 0x0 1m 1023m" $dev1
mount $dev1 $mnt
fssum -r /tmp/fssum.saved $mnt > /dev/null
umount $mnt
rmmod btrfs
This will lead to the following extent states leakage:
BTRFS: state leak: start 499712 end 503807 state 5 in tree 1 refs 1
BTRFS: state leak: start 495616 end 499711 state 5 in tree 1 refs 1
BTRFS: state leak: start 491520 end 495615 state 5 in tree 1 refs 1
BTRFS: state leak: start 487424 end 491519 state 5 in tree 1 refs 1
BTRFS: state leak: start 483328 end 487423 state 5 in tree 1 refs 1
BTRFS: state leak: start 479232 end 483327 state 5 in tree 1 refs 1
BTRFS: state leak: start 475136 end 479231 state 5 in tree 1 refs 1
BTRFS: state leak: start 471040 end 475135 state 5 in tree 1 refs 1
[CAUSE]
Since commit 7aa51232e204 ("btrfs: pass a btrfs_bio to
btrfs_repair_one_sector"), we always use btrfs_bio->file_offset to
determine the file offset of a page.
But that usage assume that, one bio has all its page having a continuous
page offsets.
Unfortunately that's not true, btrfs only requires the logical bytenr
contiguous when assembling its bios.
From above script, we have one bio looks like this:
fssum-27671 submit_one_bio: bio logical=217739264 len=36864
fssum-27671 submit_one_bio: r/i=5/261 page_offset=466944 <<<
fssum-27671 submit_one_bio: r/i=5/261 page_offset=724992 <<<
fssum-27671 submit_one_bio: r/i=5/261 page_offset=729088
fssum-27671 submit_one_bio: r/i=5/261 page_offset=733184
fssum-27671 submit_one_bio: r/i=5/261 page_offset=737280
fssum-27671 submit_one_bio: r/i=5/261 page_offset=741376
fssum-27671 submit_one_bio: r/i=5/261 page_offset=745472
fssum-27671 submit_one_bio: r/i=5/261 page_offset=749568
fssum-27671 submit_one_bio: r/i=5/261 page_offset=753664
Note that the 1st and the 2nd page has non-contiguous page offsets.
This means, at repair time, we will have completely wrong file offset
passed in:
kworker/u32:2-19927 btrfs_repair_one_sector: r/i=5/261 page_off=729088 file_off=475136 bio_offset=8192
Since the file offset is incorrect, we latter incorrectly set the extent
states, and no way to really release them.
Thus later it causes the leakage.
In fact, this can be even worse, since the file offset is incorrect, we
can hit cases like the incorrect file offset belongs to a HOLE, and
later cause btrfs_num_copies() to trigger error, finally hit
BUG_ON()/ASSERT() later.
[FIX]
Add an extra condition in btrfs_bio_add_page() for uncompressed IO.
Now we will have more strict requirement for bio pages:
- They should all have the same mapping
(the mapping check is already implied by the call chain)
- Their logical bytenr should be adjacent
This is the same as the old condition.
- Their page_offset() (file offset) should be adjacent
This is the new check.
This would result a slightly increased amount of bios from btrfs
(needs holes and inside the same stripe boundary to trigger).
But this would greatly reduce the confusion, as it's pretty common
to assume a btrfs bio would only contain continuous page cache.
Later we may need extra cleanups, as we no longer needs to handle gaps
between page offsets in endio functions.
Currently this should be the minimal patch to fix commit 7aa51232e204
("btrfs: pass a btrfs_bio to btrfs_repair_one_sector").
Reported-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Fixes: 7aa51232e204 ("btrfs: pass a btrfs_bio to btrfs_repair_one_sector")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-08-13 16:06:53 +08:00
|
|
|
}
|
|
|
|
|
2021-02-04 18:21:57 +08:00
|
|
|
if (!contig)
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
return 0;
|
2021-02-04 18:21:57 +08:00
|
|
|
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
real_size = min(bio_ctrl->len_to_oe_boundary,
|
|
|
|
bio_ctrl->len_to_stripe_boundary) - bio_size;
|
|
|
|
real_size = min(real_size, size);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If real_size is 0, never call bio_add_*_page(), as even size is 0,
|
|
|
|
* bio will still execute its endio function on the page!
|
|
|
|
*/
|
|
|
|
if (real_size == 0)
|
|
|
|
return 0;
|
2021-02-04 18:21:57 +08:00
|
|
|
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
if (bio_op(bio) == REQ_OP_ZONE_APPEND)
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
ret = bio_add_zone_append_page(bio, page, real_size, pg_offset);
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
else
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
ret = bio_add_page(bio, page, real_size, pg_offset);
|
2021-02-04 18:21:58 +08:00
|
|
|
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
return ret;
|
2021-02-04 18:21:57 +08:00
|
|
|
}
|
|
|
|
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
static int calc_bio_boundaries(struct btrfs_bio_ctrl *bio_ctrl,
|
2021-08-11 14:37:08 +08:00
|
|
|
struct btrfs_inode *inode, u64 file_offset)
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = inode->root->fs_info;
|
|
|
|
struct btrfs_io_geometry geom;
|
|
|
|
struct btrfs_ordered_extent *ordered;
|
|
|
|
struct extent_map *em;
|
|
|
|
u64 logical = (bio_ctrl->bio->bi_iter.bi_sector << SECTOR_SHIFT);
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Pages for compressed extent are never submitted to disk directly,
|
|
|
|
* thus it has no real boundary, just set them to U32_MAX.
|
|
|
|
*
|
|
|
|
* The split happens for real compressed bio, which happens in
|
|
|
|
* btrfs_submit_compressed_read/write().
|
|
|
|
*/
|
2021-07-27 21:11:53 +08:00
|
|
|
if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) {
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
bio_ctrl->len_to_oe_boundary = U32_MAX;
|
|
|
|
bio_ctrl->len_to_stripe_boundary = U32_MAX;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
em = btrfs_get_chunk_map(fs_info, logical, fs_info->sectorsize);
|
|
|
|
if (IS_ERR(em))
|
|
|
|
return PTR_ERR(em);
|
|
|
|
ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio_ctrl->bio),
|
|
|
|
logical, &geom);
|
|
|
|
free_extent_map(em);
|
|
|
|
if (ret < 0) {
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
if (geom.len > U32_MAX)
|
|
|
|
bio_ctrl->len_to_stripe_boundary = U32_MAX;
|
|
|
|
else
|
|
|
|
bio_ctrl->len_to_stripe_boundary = (u32)geom.len;
|
|
|
|
|
2021-12-07 22:28:37 +08:00
|
|
|
if (bio_op(bio_ctrl->bio) != REQ_OP_ZONE_APPEND) {
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
bio_ctrl->len_to_oe_boundary = U32_MAX;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Ordered extent not yet created, so we're good */
|
2021-08-11 14:37:08 +08:00
|
|
|
ordered = btrfs_lookup_ordered_extent(inode, file_offset);
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
if (!ordered) {
|
|
|
|
bio_ctrl->len_to_oe_boundary = U32_MAX;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
bio_ctrl->len_to_oe_boundary = min_t(u32, U32_MAX,
|
|
|
|
ordered->disk_bytenr + ordered->disk_num_bytes - logical);
|
|
|
|
btrfs_put_ordered_extent(ordered);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
static int alloc_new_bio(struct btrfs_inode *inode,
|
|
|
|
struct btrfs_bio_ctrl *bio_ctrl,
|
|
|
|
struct writeback_control *wbc,
|
2022-07-15 02:07:16 +08:00
|
|
|
blk_opf_t opf,
|
2021-08-11 14:37:08 +08:00
|
|
|
u64 disk_bytenr, u32 offset, u64 file_offset,
|
2021-07-27 20:59:41 +08:00
|
|
|
enum btrfs_compression_type compress_type)
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = inode->root->fs_info;
|
|
|
|
struct bio *bio;
|
|
|
|
int ret;
|
|
|
|
|
2022-09-13 13:31:14 +08:00
|
|
|
ASSERT(bio_ctrl->end_io_func);
|
|
|
|
|
|
|
|
bio = btrfs_bio_alloc(BIO_MAX_VECS, opf, bio_ctrl->end_io_func, NULL);
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
/*
|
|
|
|
* For compressed page range, its disk_bytenr is always @disk_bytenr
|
|
|
|
* passed in, no matter if we have added any range into previous bio.
|
|
|
|
*/
|
2021-07-27 20:59:41 +08:00
|
|
|
if (compress_type != BTRFS_COMPRESS_NONE)
|
2021-09-15 15:17:17 +08:00
|
|
|
bio->bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
else
|
2021-09-15 15:17:17 +08:00
|
|
|
bio->bi_iter.bi_sector = (disk_bytenr + offset) >> SECTOR_SHIFT;
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
bio_ctrl->bio = bio;
|
2021-07-27 21:11:53 +08:00
|
|
|
bio_ctrl->compress_type = compress_type;
|
2021-08-11 14:37:08 +08:00
|
|
|
ret = calc_bio_boundaries(bio_ctrl, inode, file_offset);
|
|
|
|
if (ret < 0)
|
|
|
|
goto error;
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
|
2022-03-25 00:52:10 +08:00
|
|
|
if (wbc) {
|
|
|
|
/*
|
|
|
|
* For Zone append we need the correct block_device that we are
|
|
|
|
* going to write to set in the bio to be able to respect the
|
|
|
|
* hardware limitation. Look it up here:
|
|
|
|
*/
|
|
|
|
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
|
|
|
|
struct btrfs_device *dev;
|
|
|
|
|
|
|
|
dev = btrfs_zoned_get_device(fs_info, disk_bytenr,
|
|
|
|
fs_info->sectorsize);
|
|
|
|
if (IS_ERR(dev)) {
|
|
|
|
ret = PTR_ERR(dev);
|
|
|
|
goto error;
|
|
|
|
}
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
|
2022-03-25 00:52:10 +08:00
|
|
|
bio_set_dev(bio, dev->bdev);
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* Otherwise pick the last added device to support
|
|
|
|
* cgroup writeback. For multi-device file systems this
|
|
|
|
* means blk-cgroup policies have to always be set on the
|
|
|
|
* last added/replaced device. This is a bit odd but has
|
|
|
|
* been like that for a long time.
|
|
|
|
*/
|
|
|
|
bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev);
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
}
|
2022-03-25 00:52:10 +08:00
|
|
|
wbc_init_bio(wbc, bio);
|
|
|
|
} else {
|
|
|
|
ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND);
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
error:
|
|
|
|
bio_ctrl->bio = NULL;
|
2022-08-06 16:03:26 +08:00
|
|
|
btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2017-06-07 01:14:26 +08:00
|
|
|
/*
|
|
|
|
* @opf: bio REQ_OP_* and REQ_* flags as one value
|
2017-06-13 01:50:41 +08:00
|
|
|
* @wbc: optional writeback control for io accounting
|
2021-01-06 09:01:40 +08:00
|
|
|
* @disk_bytenr: logical bytenr where the write will be
|
btrfs: switch page and disk_bytenr argument position for submit_extent_page()
Normally we put (page, pg_len, pg_offset) arguments together, just like
what __bio_add_page() does.
But in submit_extent_page(), what we got is, (page, disk_bytenr, pg_len,
pg_offset), which sometimes can be confusing.
Change the order to (disk_bytenr, page, pg_len, pg_offset) to make it
to follow the common schema.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-13 13:31:13 +08:00
|
|
|
* @page: page to add to the bio
|
2021-01-06 09:01:40 +08:00
|
|
|
* @size: portion of page that we want to write to
|
2017-06-13 01:50:41 +08:00
|
|
|
* @pg_offset: offset of the new bio or to check whether we are adding
|
|
|
|
* a contiguous page to the previous one
|
2021-07-27 20:59:41 +08:00
|
|
|
* @compress_type: compress type for current bio
|
2022-09-13 13:31:12 +08:00
|
|
|
*
|
|
|
|
* The will either add the page into the existing @bio_ctrl->bio, or allocate a
|
|
|
|
* new one in @bio_ctrl->bio.
|
|
|
|
* The mirror number for this IO should already be initizlied in
|
|
|
|
* @bio_ctrl->mirror_num.
|
2017-06-07 01:14:26 +08:00
|
|
|
*/
|
2022-07-15 02:07:16 +08:00
|
|
|
static int submit_extent_page(blk_opf_t opf,
|
2015-07-03 04:57:22 +08:00
|
|
|
struct writeback_control *wbc,
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl,
|
btrfs: switch page and disk_bytenr argument position for submit_extent_page()
Normally we put (page, pg_len, pg_offset) arguments together, just like
what __bio_add_page() does.
But in submit_extent_page(), what we got is, (page, disk_bytenr, pg_len,
pg_offset), which sometimes can be confusing.
Change the order to (disk_bytenr, page, pg_len, pg_offset) to make it
to follow the common schema.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-13 13:31:13 +08:00
|
|
|
u64 disk_bytenr, struct page *page,
|
2017-10-04 23:10:34 +08:00
|
|
|
size_t size, unsigned long pg_offset,
|
2021-07-27 20:59:41 +08:00
|
|
|
enum btrfs_compression_type compress_type,
|
Btrfs: fix read corruption of compressed and shared extents
If a file has a range pointing to a compressed extent, followed by
another range that points to the same compressed extent and a read
operation attempts to read both ranges (either completely or part of
them), the pages that correspond to the second range are incorrectly
filled with zeroes.
Consider the following example:
File layout
[0 - 8K] [8K - 24K]
| |
| |
points to extent X, points to extent X,
offset 4K, length of 8K offset 0, length 16K
[extent X, compressed length = 4K uncompressed length = 16K]
If a readpages() call spans the 2 ranges, a single bio to read the extent
is submitted - extent_io.c:submit_extent_page() would only create a new
bio to cover the second range pointing to the extent if the extent it
points to had a different logical address than the extent associated with
the first range. This has a consequence of the compressed read end io
handler (compression.c:end_compressed_bio_read()) finish once the extent
is decompressed into the pages covering the first range, leaving the
remaining pages (belonging to the second range) filled with zeroes (done
by compression.c:btrfs_clear_biovec_end()).
So fix this by submitting the current bio whenever we find a range
pointing to a compressed extent that was preceded by a range with a
different extent map. This is the simplest solution for this corner
case. Making the end io callback populate both ranges (or more, if we
have multiple pointing to the same extent) is a much more complex
solution since each bio is tightly coupled with a single extent map and
the extent maps associated to the ranges pointing to the shared extent
can have different offsets and lengths.
The following test case for fstests triggers the issue:
seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"
tmp=/tmp/$$
status=1 # failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15
_cleanup()
{
rm -f $tmp.*
}
# get standard environment, filters and checks
. ./common/rc
. ./common/filter
# real QA test starts here
_need_to_be_root
_supported_fs btrfs
_supported_os Linux
_require_scratch
_require_cloner
rm -f $seqres.full
test_clone_and_read_compressed_extent()
{
local mount_opts=$1
_scratch_mkfs >>$seqres.full 2>&1
_scratch_mount $mount_opts
# Create a test file with a single extent that is compressed (the
# data we write into it is highly compressible no matter which
# compression algorithm is used, zlib or lzo).
$XFS_IO_PROG -f -c "pwrite -S 0xaa 0K 4K" \
-c "pwrite -S 0xbb 4K 8K" \
-c "pwrite -S 0xcc 12K 4K" \
$SCRATCH_MNT/foo | _filter_xfs_io
# Now clone our extent into an adjacent offset.
$CLONER_PROG -s $((4 * 1024)) -d $((16 * 1024)) -l $((8 * 1024)) \
$SCRATCH_MNT/foo $SCRATCH_MNT/foo
# Same as before but for this file we clone the extent into a lower
# file offset.
$XFS_IO_PROG -f -c "pwrite -S 0xaa 8K 4K" \
-c "pwrite -S 0xbb 12K 8K" \
-c "pwrite -S 0xcc 20K 4K" \
$SCRATCH_MNT/bar | _filter_xfs_io
$CLONER_PROG -s $((12 * 1024)) -d 0 -l $((8 * 1024)) \
$SCRATCH_MNT/bar $SCRATCH_MNT/bar
echo "File digests before unmounting filesystem:"
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
# Evicting the inode or clearing the page cache before reading
# again the file would also trigger the bug - reads were returning
# all bytes in the range corresponding to the second reference to
# the extent with a value of 0, but the correct data was persisted
# (it was a bug exclusively in the read path). The issue happened
# only if the same readpages() call targeted pages belonging to the
# first and second ranges that point to the same compressed extent.
_scratch_remount
echo "File digests after mounting filesystem again:"
# Must match the same digests we got before.
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
}
echo -e "\nTesting with zlib compression..."
test_clone_and_read_compressed_extent "-o compress=zlib"
_scratch_unmount
echo -e "\nTesting with lzo compression..."
test_clone_and_read_compressed_extent "-o compress=lzo"
status=0
exit
Cc: stable@vger.kernel.org
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo<quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-09-14 16:09:31 +08:00
|
|
|
bool force_bio_submit)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
int ret = 0;
|
2021-02-04 18:21:58 +08:00
|
|
|
struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
unsigned int cur = pg_offset;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
ASSERT(bio_ctrl);
|
2017-06-07 01:22:55 +08:00
|
|
|
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
ASSERT(pg_offset < PAGE_SIZE && size <= PAGE_SIZE &&
|
|
|
|
pg_offset + size <= PAGE_SIZE);
|
2022-09-13 13:31:14 +08:00
|
|
|
|
|
|
|
ASSERT(bio_ctrl->end_io_func);
|
|
|
|
|
2022-06-03 15:11:03 +08:00
|
|
|
if (force_bio_submit)
|
|
|
|
submit_one_bio(bio_ctrl);
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
|
|
|
|
while (cur < pg_offset + size) {
|
|
|
|
u32 offset = cur - pg_offset;
|
|
|
|
int added;
|
|
|
|
|
|
|
|
/* Allocate new bio if needed */
|
|
|
|
if (!bio_ctrl->bio) {
|
|
|
|
ret = alloc_new_bio(inode, bio_ctrl, wbc, opf,
|
2022-09-13 13:31:14 +08:00
|
|
|
disk_bytenr, offset,
|
2021-08-11 14:37:08 +08:00
|
|
|
page_offset(page) + cur,
|
2021-07-27 20:59:41 +08:00
|
|
|
compress_type);
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* We must go through btrfs_bio_add_page() to ensure each
|
|
|
|
* page range won't cross various boundaries.
|
|
|
|
*/
|
2021-07-27 20:59:41 +08:00
|
|
|
if (compress_type != BTRFS_COMPRESS_NONE)
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
added = btrfs_bio_add_page(bio_ctrl, page, disk_bytenr,
|
|
|
|
size - offset, pg_offset + offset,
|
2021-07-27 20:59:41 +08:00
|
|
|
compress_type);
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
else
|
|
|
|
added = btrfs_bio_add_page(bio_ctrl, page,
|
|
|
|
disk_bytenr + offset, size - offset,
|
2021-07-27 20:59:41 +08:00
|
|
|
pg_offset + offset, compress_type);
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
|
|
|
|
/* Metadata page range should never be split */
|
|
|
|
if (!is_data_inode(&inode->vfs_inode))
|
|
|
|
ASSERT(added == 0 || added == size - offset);
|
|
|
|
|
|
|
|
/* At least we added some page, update the account */
|
|
|
|
if (wbc && added)
|
|
|
|
wbc_account_cgroup_owner(wbc, page, added);
|
|
|
|
|
|
|
|
/* We have reached boundary, submit right now */
|
|
|
|
if (added < size - offset) {
|
|
|
|
/* The bio should contain some page(s) */
|
|
|
|
ASSERT(bio_ctrl->bio->bi_iter.bi_size);
|
2022-06-03 15:11:03 +08:00
|
|
|
submit_one_bio(bio_ctrl);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
cur += added;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
btrfs: subpage: allow submit_extent_page() to do bio split
Current submit_extent_page() just checks if the current page range can
be fitted into current bio, and if not, submit then re-add.
But this behavior can't handle subpage case at all.
For subpage case, the problem is in the page size, 64K, which is also
the same size as stripe size.
This means, if we can't fit a full 64K into a bio, due to stripe limit,
then it won't fit into next bio without crossing stripe either.
The proper way to handle it is:
- Check how many bytes we can be put into current bio
- Put as many bytes as possible into current bio first
- Submit current bio
- Create a new bio
- Add the remaining bytes into the new bio
Refactor submit_extent_page() so that it does the above iteration.
The main loop inside submit_extent_page() will look like this:
cur = pg_offset;
while (cur < pg_offset + size) {
u32 offset = cur - pg_offset;
int added;
if (!bio_ctrl->bio) {
/* Allocate new bio if needed */
}
/* Add as many bytes into the bio */
added = btrfs_bio_add_page();
if (added < size - offset) {
/* The current bio is full, submit it */
}
cur += added;
}
Also, since we're doing new bio allocation deep inside the main loop,
extract that code into a new helper, alloc_new_bio().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:00 +08:00
|
|
|
return 0;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2021-01-26 16:33:48 +08:00
|
|
|
static int attach_extent_buffer_page(struct extent_buffer *eb,
|
|
|
|
struct page *page,
|
|
|
|
struct btrfs_subpage *prealloc)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2021-01-26 16:33:48 +08:00
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
|
|
|
int ret = 0;
|
|
|
|
|
2020-10-21 14:25:02 +08:00
|
|
|
/*
|
|
|
|
* If the page is mapped to btree inode, we should hold the private
|
|
|
|
* lock to prevent race.
|
|
|
|
* For cloned or dummy extent buffers, their pages are not mapped and
|
|
|
|
* will not race with any other ebs.
|
|
|
|
*/
|
|
|
|
if (page->mapping)
|
|
|
|
lockdep_assert_held(&page->mapping->private_lock);
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (fs_info->nodesize >= PAGE_SIZE) {
|
2021-01-26 16:33:48 +08:00
|
|
|
if (!PagePrivate(page))
|
|
|
|
attach_page_private(page, eb);
|
|
|
|
else
|
|
|
|
WARN_ON(page->private != (unsigned long)eb);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Already mapped, just free prealloc */
|
|
|
|
if (PagePrivate(page)) {
|
|
|
|
btrfs_free_subpage(prealloc);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (prealloc)
|
|
|
|
/* Has preallocated memory for subpage */
|
|
|
|
attach_page_private(page, prealloc);
|
2020-06-02 12:47:45 +08:00
|
|
|
else
|
2021-01-26 16:33:48 +08:00
|
|
|
/* Do new allocation to attach subpage */
|
|
|
|
ret = btrfs_attach_subpage(fs_info, page,
|
|
|
|
BTRFS_SUBPAGE_METADATA);
|
|
|
|
return ret;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2021-01-26 16:34:00 +08:00
|
|
|
int set_page_extent_mapped(struct page *page)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2021-01-26 16:34:00 +08:00
|
|
|
struct btrfs_fs_info *fs_info;
|
|
|
|
|
|
|
|
ASSERT(page->mapping);
|
|
|
|
|
|
|
|
if (PagePrivate(page))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
fs_info = btrfs_sb(page->mapping->host->i_sb);
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (btrfs_is_subpage(fs_info, page))
|
2021-01-26 16:34:00 +08:00
|
|
|
return btrfs_attach_subpage(fs_info, page, BTRFS_SUBPAGE_DATA);
|
|
|
|
|
|
|
|
attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void clear_page_extent_mapped(struct page *page)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info;
|
|
|
|
|
|
|
|
ASSERT(page->mapping);
|
|
|
|
|
2020-06-02 12:47:45 +08:00
|
|
|
if (!PagePrivate(page))
|
2021-01-26 16:34:00 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
fs_info = btrfs_sb(page->mapping->host->i_sb);
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (btrfs_is_subpage(fs_info, page))
|
2021-01-26 16:34:00 +08:00
|
|
|
return btrfs_detach_subpage(fs_info, page);
|
|
|
|
|
|
|
|
detach_page_private(page);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2013-07-25 19:22:37 +08:00
|
|
|
static struct extent_map *
|
|
|
|
__get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
|
2020-09-14 17:37:06 +08:00
|
|
|
u64 start, u64 len, struct extent_map **em_cached)
|
2013-07-25 19:22:37 +08:00
|
|
|
{
|
|
|
|
struct extent_map *em;
|
|
|
|
|
|
|
|
if (em_cached && *em_cached) {
|
|
|
|
em = *em_cached;
|
2014-02-25 22:15:12 +08:00
|
|
|
if (extent_map_in_tree(em) && start >= em->start &&
|
2013-07-25 19:22:37 +08:00
|
|
|
start < extent_map_end(em)) {
|
2017-03-03 16:55:12 +08:00
|
|
|
refcount_inc(&em->refs);
|
2013-07-25 19:22:37 +08:00
|
|
|
return em;
|
|
|
|
}
|
|
|
|
|
|
|
|
free_extent_map(em);
|
|
|
|
*em_cached = NULL;
|
|
|
|
}
|
|
|
|
|
2020-09-14 17:37:06 +08:00
|
|
|
em = btrfs_get_extent(BTRFS_I(inode), page, pg_offset, start, len);
|
2022-02-03 23:36:42 +08:00
|
|
|
if (em_cached && !IS_ERR(em)) {
|
2013-07-25 19:22:37 +08:00
|
|
|
BUG_ON(*em_cached);
|
2017-03-03 16:55:12 +08:00
|
|
|
refcount_inc(&em->refs);
|
2013-07-25 19:22:37 +08:00
|
|
|
*em_cached = em;
|
|
|
|
}
|
|
|
|
return em;
|
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
/*
|
|
|
|
* basic readpage implementation. Locked extent state structs are inserted
|
|
|
|
* into the tree that are removed when the IO is done (by the end_io
|
|
|
|
* handlers)
|
2012-03-12 23:03:00 +08:00
|
|
|
* XXX JDM: This needs looking at to ensure proper page locking
|
2016-07-12 01:39:07 +08:00
|
|
|
* return 0 on success, otherwise return error
|
2008-01-25 05:13:08 +08:00
|
|
|
*/
|
2022-04-15 22:33:24 +08:00
|
|
|
static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl,
|
2022-07-15 02:07:16 +08:00
|
|
|
blk_opf_t read_flags, u64 *prev_em_start)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
struct inode *inode = page->mapping->host;
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
|
2012-12-21 17:17:45 +08:00
|
|
|
u64 start = page_offset(page);
|
2017-06-07 01:50:13 +08:00
|
|
|
const u64 end = start + PAGE_SIZE - 1;
|
2008-01-25 05:13:08 +08:00
|
|
|
u64 cur = start;
|
|
|
|
u64 extent_offset;
|
|
|
|
u64 last_byte = i_size_read(inode);
|
|
|
|
u64 block_start;
|
|
|
|
struct extent_map *em;
|
2016-07-12 01:39:07 +08:00
|
|
|
int ret = 0;
|
2011-04-19 20:29:38 +08:00
|
|
|
size_t pg_offset = 0;
|
2008-01-25 05:13:08 +08:00
|
|
|
size_t iosize;
|
|
|
|
size_t blocksize = inode->i_sb->s_blocksize;
|
2020-02-06 02:09:42 +08:00
|
|
|
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
|
2020-02-06 02:09:30 +08:00
|
|
|
|
2021-01-26 16:34:00 +08:00
|
|
|
ret = set_page_extent_mapped(page);
|
|
|
|
if (ret < 0) {
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(tree, start, end, NULL);
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
btrfs_page_set_error(fs_info, page, start, PAGE_SIZE);
|
|
|
|
unlock_page(page);
|
2021-01-26 16:34:00 +08:00
|
|
|
goto out;
|
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
if (page->index == last_byte >> PAGE_SHIFT) {
|
2018-12-05 22:23:03 +08:00
|
|
|
size_t zero_offset = offset_in_page(last_byte);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
|
|
|
|
if (zero_offset) {
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
iosize = PAGE_SIZE - zero_offset;
|
btrfs: use memzero_page() instead of open coded kmap pattern
There are many places where kmap/memset/kunmap patterns occur.
Use the newly lifted memzero_page() to eliminate direct uses of kmap and
leverage the new core functions use of kmap_local_page().
The development of this patch was aided by the following coccinelle
script:
// <smpl>
// SPDX-License-Identifier: GPL-2.0-only
// Find kmap/memset/kunmap pattern and replace with memset*page calls
//
// NOTE: Offsets and other expressions may be more complex than what the script
// will automatically generate. Therefore a catchall rule is provided to find
// the pattern which then must be evaluated by hand.
//
// Confidence: Low
// Copyright: (C) 2021 Intel Corporation
// URL: http://coccinelle.lip6.fr/
// Comments:
// Options:
//
// Then the memset pattern
//
@ memset_rule1 @
expression page, V, L, Off;
identifier ptr;
type VP;
@@
(
-VP ptr = kmap(page);
|
-ptr = kmap(page);
|
-VP ptr = kmap_atomic(page);
|
-ptr = kmap_atomic(page);
)
<+...
(
-memset(ptr, 0, L);
+memzero_page(page, 0, L);
|
-memset(ptr + Off, 0, L);
+memzero_page(page, Off, L);
|
-memset(ptr, V, L);
+memset_page(page, V, 0, L);
|
-memset(ptr + Off, V, L);
+memset_page(page, V, Off, L);
)
...+>
(
-kunmap(page);
|
-kunmap_atomic(ptr);
)
// Remove any pointers left unused
@
depends on memset_rule1
@
identifier memset_rule1.ptr;
type VP, VP1;
@@
-VP ptr;
... when != ptr;
? VP1 ptr;
//
// Catch all
//
@ memset_rule2 @
expression page;
identifier ptr;
expression GenTo, GenSize, GenValue;
type VP;
@@
(
-VP ptr = kmap(page);
|
-ptr = kmap(page);
|
-VP ptr = kmap_atomic(page);
|
-ptr = kmap_atomic(page);
)
<+...
(
//
// Some call sites have complex expressions within the memset/memcpy
// The follow are catch alls which need to be evaluated by hand.
//
-memset(GenTo, 0, GenSize);
+memzero_pageExtra(page, GenTo, GenSize);
|
-memset(GenTo, GenValue, GenSize);
+memset_pageExtra(page, GenValue, GenTo, GenSize);
)
...+>
(
-kunmap(page);
|
-kunmap_atomic(ptr);
)
// Remove any pointers left unused
@
depends on memset_rule2
@
identifier memset_rule2.ptr;
type VP, VP1;
@@
-VP ptr;
... when != ptr;
? VP1 ptr;
// </smpl>
Link: https://lkml.kernel.org/r/20210309212137.2610186-4-ira.weiny@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 09:40:07 +08:00
|
|
|
memzero_page(page, zero_offset, iosize);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
}
|
|
|
|
}
|
2022-09-13 13:31:14 +08:00
|
|
|
bio_ctrl->end_io_func = end_bio_extent_readpage;
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
begin_page_read(fs_info, page);
|
2008-01-25 05:13:08 +08:00
|
|
|
while (cur <= end) {
|
2021-07-26 14:34:50 +08:00
|
|
|
unsigned long this_bio_flag = 0;
|
Btrfs: fix read corruption of compressed and shared extents
If a file has a range pointing to a compressed extent, followed by
another range that points to the same compressed extent and a read
operation attempts to read both ranges (either completely or part of
them), the pages that correspond to the second range are incorrectly
filled with zeroes.
Consider the following example:
File layout
[0 - 8K] [8K - 24K]
| |
| |
points to extent X, points to extent X,
offset 4K, length of 8K offset 0, length 16K
[extent X, compressed length = 4K uncompressed length = 16K]
If a readpages() call spans the 2 ranges, a single bio to read the extent
is submitted - extent_io.c:submit_extent_page() would only create a new
bio to cover the second range pointing to the extent if the extent it
points to had a different logical address than the extent associated with
the first range. This has a consequence of the compressed read end io
handler (compression.c:end_compressed_bio_read()) finish once the extent
is decompressed into the pages covering the first range, leaving the
remaining pages (belonging to the second range) filled with zeroes (done
by compression.c:btrfs_clear_biovec_end()).
So fix this by submitting the current bio whenever we find a range
pointing to a compressed extent that was preceded by a range with a
different extent map. This is the simplest solution for this corner
case. Making the end io callback populate both ranges (or more, if we
have multiple pointing to the same extent) is a much more complex
solution since each bio is tightly coupled with a single extent map and
the extent maps associated to the ranges pointing to the shared extent
can have different offsets and lengths.
The following test case for fstests triggers the issue:
seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"
tmp=/tmp/$$
status=1 # failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15
_cleanup()
{
rm -f $tmp.*
}
# get standard environment, filters and checks
. ./common/rc
. ./common/filter
# real QA test starts here
_need_to_be_root
_supported_fs btrfs
_supported_os Linux
_require_scratch
_require_cloner
rm -f $seqres.full
test_clone_and_read_compressed_extent()
{
local mount_opts=$1
_scratch_mkfs >>$seqres.full 2>&1
_scratch_mount $mount_opts
# Create a test file with a single extent that is compressed (the
# data we write into it is highly compressible no matter which
# compression algorithm is used, zlib or lzo).
$XFS_IO_PROG -f -c "pwrite -S 0xaa 0K 4K" \
-c "pwrite -S 0xbb 4K 8K" \
-c "pwrite -S 0xcc 12K 4K" \
$SCRATCH_MNT/foo | _filter_xfs_io
# Now clone our extent into an adjacent offset.
$CLONER_PROG -s $((4 * 1024)) -d $((16 * 1024)) -l $((8 * 1024)) \
$SCRATCH_MNT/foo $SCRATCH_MNT/foo
# Same as before but for this file we clone the extent into a lower
# file offset.
$XFS_IO_PROG -f -c "pwrite -S 0xaa 8K 4K" \
-c "pwrite -S 0xbb 12K 8K" \
-c "pwrite -S 0xcc 20K 4K" \
$SCRATCH_MNT/bar | _filter_xfs_io
$CLONER_PROG -s $((12 * 1024)) -d 0 -l $((8 * 1024)) \
$SCRATCH_MNT/bar $SCRATCH_MNT/bar
echo "File digests before unmounting filesystem:"
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
# Evicting the inode or clearing the page cache before reading
# again the file would also trigger the bug - reads were returning
# all bytes in the range corresponding to the second reference to
# the extent with a value of 0, but the correct data was persisted
# (it was a bug exclusively in the read path). The issue happened
# only if the same readpages() call targeted pages belonging to the
# first and second ranges that point to the same compressed extent.
_scratch_remount
echo "File digests after mounting filesystem again:"
# Must match the same digests we got before.
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
}
echo -e "\nTesting with zlib compression..."
test_clone_and_read_compressed_extent "-o compress=zlib"
_scratch_unmount
echo -e "\nTesting with lzo compression..."
test_clone_and_read_compressed_extent "-o compress=lzo"
status=0
exit
Cc: stable@vger.kernel.org
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo<quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-09-14 16:09:31 +08:00
|
|
|
bool force_bio_submit = false;
|
2021-01-06 09:01:40 +08:00
|
|
|
u64 disk_bytenr;
|
2013-02-12 00:33:00 +08:00
|
|
|
|
btrfs: subpage: make add_ra_bio_pages() compatible
[BUG]
If we remove the subpage limitation in add_ra_bio_pages(), then read a
compressed extent which has part of its range in next page, like the
following inode layout:
0 32K 64K 96K 128K
|<--------------|-------------->|
Btrfs will trigger ASSERT() in endio function:
assertion failed: atomic_read(&subpage->readers) >= nbits
------------[ cut here ]------------
kernel BUG at fs/btrfs/ctree.h:3431!
Internal error: Oops - BUG: 0 [#1] SMP
Workqueue: btrfs-endio btrfs_work_helper [btrfs]
Call trace:
assertfail.constprop.0+0x28/0x2c [btrfs]
btrfs_subpage_end_reader+0x148/0x14c [btrfs]
end_page_read+0x8c/0x100 [btrfs]
end_bio_extent_readpage+0x320/0x6b0 [btrfs]
bio_endio+0x15c/0x1dc
end_workqueue_fn+0x44/0x64 [btrfs]
btrfs_work_helper+0x74/0x250 [btrfs]
process_one_work+0x1d4/0x47c
worker_thread+0x180/0x400
kthread+0x11c/0x120
ret_from_fork+0x10/0x30
---[ end trace c8b7b552d3bb408c ]---
[CAUSE]
When we read the page range [0, 64K), we find it's a compressed extent,
and we will try to add extra pages in add_ra_bio_pages() to avoid
reading the same compressed extent.
But when we add such page into the read bio, it doesn't follow the
behavior of btrfs_do_readpage() to properly set subpage::readers.
This means, for page [64K, 128K), its subpage::readers is still 0.
And when endio is executed on both pages, since page [64K, 128K) has 0
subpage::readers, it triggers above ASSERT()
[FIX]
Function add_ra_bio_pages() is far from subpage compatible, it always
assume PAGE_SIZE == sectorsize, thus when it skip to next range it
always just skip PAGE_SIZE.
Make it subpage compatible by:
- Skip to next page properly when needed
If we find there is already a page cache, we need to skip to next page.
For that case, we shouldn't just skip PAGE_SIZE bytes, but use
@pg_index to calculate the next bytenr and continue.
- Only add the page range covered by current extent map
We need to calculate which range is covered by current extent map and
only add that part into the read bio.
- Update subpage::readers before submitting the bio
- Use proper cursor other than confusing @last_offset
- Calculate the missed threshold based on sector size
It's no longer using missed pages, as for 64K page size, we have at
most 3 pages to skip. (If aligned only 2 pages)
- Add ASSERT() to make sure our bytenr is always aligned
- Add comment for the function
Add a special note for subpage case, as the function won't really
work well for subpage cases.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:47 +08:00
|
|
|
ASSERT(IS_ALIGNED(cur, fs_info->sectorsize));
|
2008-01-25 05:13:08 +08:00
|
|
|
if (cur >= last_byte) {
|
2011-04-06 18:02:20 +08:00
|
|
|
struct extent_state *cached = NULL;
|
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
iosize = PAGE_SIZE - pg_offset;
|
btrfs: use memzero_page() instead of open coded kmap pattern
There are many places where kmap/memset/kunmap patterns occur.
Use the newly lifted memzero_page() to eliminate direct uses of kmap and
leverage the new core functions use of kmap_local_page().
The development of this patch was aided by the following coccinelle
script:
// <smpl>
// SPDX-License-Identifier: GPL-2.0-only
// Find kmap/memset/kunmap pattern and replace with memset*page calls
//
// NOTE: Offsets and other expressions may be more complex than what the script
// will automatically generate. Therefore a catchall rule is provided to find
// the pattern which then must be evaluated by hand.
//
// Confidence: Low
// Copyright: (C) 2021 Intel Corporation
// URL: http://coccinelle.lip6.fr/
// Comments:
// Options:
//
// Then the memset pattern
//
@ memset_rule1 @
expression page, V, L, Off;
identifier ptr;
type VP;
@@
(
-VP ptr = kmap(page);
|
-ptr = kmap(page);
|
-VP ptr = kmap_atomic(page);
|
-ptr = kmap_atomic(page);
)
<+...
(
-memset(ptr, 0, L);
+memzero_page(page, 0, L);
|
-memset(ptr + Off, 0, L);
+memzero_page(page, Off, L);
|
-memset(ptr, V, L);
+memset_page(page, V, 0, L);
|
-memset(ptr + Off, V, L);
+memset_page(page, V, Off, L);
)
...+>
(
-kunmap(page);
|
-kunmap_atomic(ptr);
)
// Remove any pointers left unused
@
depends on memset_rule1
@
identifier memset_rule1.ptr;
type VP, VP1;
@@
-VP ptr;
... when != ptr;
? VP1 ptr;
//
// Catch all
//
@ memset_rule2 @
expression page;
identifier ptr;
expression GenTo, GenSize, GenValue;
type VP;
@@
(
-VP ptr = kmap(page);
|
-ptr = kmap(page);
|
-VP ptr = kmap_atomic(page);
|
-ptr = kmap_atomic(page);
)
<+...
(
//
// Some call sites have complex expressions within the memset/memcpy
// The follow are catch alls which need to be evaluated by hand.
//
-memset(GenTo, 0, GenSize);
+memzero_pageExtra(page, GenTo, GenSize);
|
-memset(GenTo, GenValue, GenSize);
+memset_pageExtra(page, GenValue, GenTo, GenSize);
)
...+>
(
-kunmap(page);
|
-kunmap_atomic(ptr);
)
// Remove any pointers left unused
@
depends on memset_rule2
@
identifier memset_rule2.ptr;
type VP, VP1;
@@
-VP ptr;
... when != ptr;
? VP1 ptr;
// </smpl>
Link: https://lkml.kernel.org/r/20210309212137.2610186-4-ira.weiny@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 09:40:07 +08:00
|
|
|
memzero_page(page, pg_offset, iosize);
|
2008-01-25 05:13:08 +08:00
|
|
|
set_extent_uptodate(tree, cur, cur + iosize - 1,
|
2011-04-06 18:02:20 +08:00
|
|
|
&cached, GFP_NOFS);
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(tree, cur, cur + iosize - 1, &cached);
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
end_page_read(page, true, cur, iosize);
|
2008-01-25 05:13:08 +08:00
|
|
|
break;
|
|
|
|
}
|
2013-07-25 19:22:37 +08:00
|
|
|
em = __get_extent_map(inode, page, pg_offset, cur,
|
2020-09-14 17:37:06 +08:00
|
|
|
end - cur + 1, em_cached);
|
2022-02-03 23:36:42 +08:00
|
|
|
if (IS_ERR(em)) {
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(tree, cur, end, NULL);
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
end_page_read(page, false, cur, end + 1 - cur);
|
2022-02-03 23:36:43 +08:00
|
|
|
ret = PTR_ERR(em);
|
2008-01-25 05:13:08 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
extent_offset = cur - em->start;
|
|
|
|
BUG_ON(extent_map_end(em) <= cur);
|
|
|
|
BUG_ON(end < cur);
|
|
|
|
|
2021-07-27 20:49:32 +08:00
|
|
|
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
|
|
|
|
this_bio_flag = em->compress_type;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
iosize = min(extent_map_end(em) - cur, end - cur + 1);
|
2013-02-26 16:10:22 +08:00
|
|
|
iosize = ALIGN(iosize, blocksize);
|
2021-07-27 20:47:09 +08:00
|
|
|
if (this_bio_flag != BTRFS_COMPRESS_NONE)
|
2021-01-06 09:01:40 +08:00
|
|
|
disk_bytenr = em->block_start;
|
2020-09-15 23:41:40 +08:00
|
|
|
else
|
2021-01-06 09:01:40 +08:00
|
|
|
disk_bytenr = em->block_start + extent_offset;
|
2008-01-25 05:13:08 +08:00
|
|
|
block_start = em->block_start;
|
2008-10-31 02:25:28 +08:00
|
|
|
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
|
|
|
|
block_start = EXTENT_MAP_HOLE;
|
Btrfs: fix read corruption of compressed and shared extents
If a file has a range pointing to a compressed extent, followed by
another range that points to the same compressed extent and a read
operation attempts to read both ranges (either completely or part of
them), the pages that correspond to the second range are incorrectly
filled with zeroes.
Consider the following example:
File layout
[0 - 8K] [8K - 24K]
| |
| |
points to extent X, points to extent X,
offset 4K, length of 8K offset 0, length 16K
[extent X, compressed length = 4K uncompressed length = 16K]
If a readpages() call spans the 2 ranges, a single bio to read the extent
is submitted - extent_io.c:submit_extent_page() would only create a new
bio to cover the second range pointing to the extent if the extent it
points to had a different logical address than the extent associated with
the first range. This has a consequence of the compressed read end io
handler (compression.c:end_compressed_bio_read()) finish once the extent
is decompressed into the pages covering the first range, leaving the
remaining pages (belonging to the second range) filled with zeroes (done
by compression.c:btrfs_clear_biovec_end()).
So fix this by submitting the current bio whenever we find a range
pointing to a compressed extent that was preceded by a range with a
different extent map. This is the simplest solution for this corner
case. Making the end io callback populate both ranges (or more, if we
have multiple pointing to the same extent) is a much more complex
solution since each bio is tightly coupled with a single extent map and
the extent maps associated to the ranges pointing to the shared extent
can have different offsets and lengths.
The following test case for fstests triggers the issue:
seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"
tmp=/tmp/$$
status=1 # failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15
_cleanup()
{
rm -f $tmp.*
}
# get standard environment, filters and checks
. ./common/rc
. ./common/filter
# real QA test starts here
_need_to_be_root
_supported_fs btrfs
_supported_os Linux
_require_scratch
_require_cloner
rm -f $seqres.full
test_clone_and_read_compressed_extent()
{
local mount_opts=$1
_scratch_mkfs >>$seqres.full 2>&1
_scratch_mount $mount_opts
# Create a test file with a single extent that is compressed (the
# data we write into it is highly compressible no matter which
# compression algorithm is used, zlib or lzo).
$XFS_IO_PROG -f -c "pwrite -S 0xaa 0K 4K" \
-c "pwrite -S 0xbb 4K 8K" \
-c "pwrite -S 0xcc 12K 4K" \
$SCRATCH_MNT/foo | _filter_xfs_io
# Now clone our extent into an adjacent offset.
$CLONER_PROG -s $((4 * 1024)) -d $((16 * 1024)) -l $((8 * 1024)) \
$SCRATCH_MNT/foo $SCRATCH_MNT/foo
# Same as before but for this file we clone the extent into a lower
# file offset.
$XFS_IO_PROG -f -c "pwrite -S 0xaa 8K 4K" \
-c "pwrite -S 0xbb 12K 8K" \
-c "pwrite -S 0xcc 20K 4K" \
$SCRATCH_MNT/bar | _filter_xfs_io
$CLONER_PROG -s $((12 * 1024)) -d 0 -l $((8 * 1024)) \
$SCRATCH_MNT/bar $SCRATCH_MNT/bar
echo "File digests before unmounting filesystem:"
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
# Evicting the inode or clearing the page cache before reading
# again the file would also trigger the bug - reads were returning
# all bytes in the range corresponding to the second reference to
# the extent with a value of 0, but the correct data was persisted
# (it was a bug exclusively in the read path). The issue happened
# only if the same readpages() call targeted pages belonging to the
# first and second ranges that point to the same compressed extent.
_scratch_remount
echo "File digests after mounting filesystem again:"
# Must match the same digests we got before.
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
}
echo -e "\nTesting with zlib compression..."
test_clone_and_read_compressed_extent "-o compress=zlib"
_scratch_unmount
echo -e "\nTesting with lzo compression..."
test_clone_and_read_compressed_extent "-o compress=lzo"
status=0
exit
Cc: stable@vger.kernel.org
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo<quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-09-14 16:09:31 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If we have a file range that points to a compressed extent
|
2020-08-05 10:48:34 +08:00
|
|
|
* and it's followed by a consecutive file range that points
|
Btrfs: fix read corruption of compressed and shared extents
If a file has a range pointing to a compressed extent, followed by
another range that points to the same compressed extent and a read
operation attempts to read both ranges (either completely or part of
them), the pages that correspond to the second range are incorrectly
filled with zeroes.
Consider the following example:
File layout
[0 - 8K] [8K - 24K]
| |
| |
points to extent X, points to extent X,
offset 4K, length of 8K offset 0, length 16K
[extent X, compressed length = 4K uncompressed length = 16K]
If a readpages() call spans the 2 ranges, a single bio to read the extent
is submitted - extent_io.c:submit_extent_page() would only create a new
bio to cover the second range pointing to the extent if the extent it
points to had a different logical address than the extent associated with
the first range. This has a consequence of the compressed read end io
handler (compression.c:end_compressed_bio_read()) finish once the extent
is decompressed into the pages covering the first range, leaving the
remaining pages (belonging to the second range) filled with zeroes (done
by compression.c:btrfs_clear_biovec_end()).
So fix this by submitting the current bio whenever we find a range
pointing to a compressed extent that was preceded by a range with a
different extent map. This is the simplest solution for this corner
case. Making the end io callback populate both ranges (or more, if we
have multiple pointing to the same extent) is a much more complex
solution since each bio is tightly coupled with a single extent map and
the extent maps associated to the ranges pointing to the shared extent
can have different offsets and lengths.
The following test case for fstests triggers the issue:
seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"
tmp=/tmp/$$
status=1 # failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15
_cleanup()
{
rm -f $tmp.*
}
# get standard environment, filters and checks
. ./common/rc
. ./common/filter
# real QA test starts here
_need_to_be_root
_supported_fs btrfs
_supported_os Linux
_require_scratch
_require_cloner
rm -f $seqres.full
test_clone_and_read_compressed_extent()
{
local mount_opts=$1
_scratch_mkfs >>$seqres.full 2>&1
_scratch_mount $mount_opts
# Create a test file with a single extent that is compressed (the
# data we write into it is highly compressible no matter which
# compression algorithm is used, zlib or lzo).
$XFS_IO_PROG -f -c "pwrite -S 0xaa 0K 4K" \
-c "pwrite -S 0xbb 4K 8K" \
-c "pwrite -S 0xcc 12K 4K" \
$SCRATCH_MNT/foo | _filter_xfs_io
# Now clone our extent into an adjacent offset.
$CLONER_PROG -s $((4 * 1024)) -d $((16 * 1024)) -l $((8 * 1024)) \
$SCRATCH_MNT/foo $SCRATCH_MNT/foo
# Same as before but for this file we clone the extent into a lower
# file offset.
$XFS_IO_PROG -f -c "pwrite -S 0xaa 8K 4K" \
-c "pwrite -S 0xbb 12K 8K" \
-c "pwrite -S 0xcc 20K 4K" \
$SCRATCH_MNT/bar | _filter_xfs_io
$CLONER_PROG -s $((12 * 1024)) -d 0 -l $((8 * 1024)) \
$SCRATCH_MNT/bar $SCRATCH_MNT/bar
echo "File digests before unmounting filesystem:"
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
# Evicting the inode or clearing the page cache before reading
# again the file would also trigger the bug - reads were returning
# all bytes in the range corresponding to the second reference to
# the extent with a value of 0, but the correct data was persisted
# (it was a bug exclusively in the read path). The issue happened
# only if the same readpages() call targeted pages belonging to the
# first and second ranges that point to the same compressed extent.
_scratch_remount
echo "File digests after mounting filesystem again:"
# Must match the same digests we got before.
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
}
echo -e "\nTesting with zlib compression..."
test_clone_and_read_compressed_extent "-o compress=zlib"
_scratch_unmount
echo -e "\nTesting with lzo compression..."
test_clone_and_read_compressed_extent "-o compress=lzo"
status=0
exit
Cc: stable@vger.kernel.org
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo<quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-09-14 16:09:31 +08:00
|
|
|
* to the same compressed extent (possibly with a different
|
|
|
|
* offset and/or length, so it either points to the whole extent
|
|
|
|
* or only part of it), we must make sure we do not submit a
|
|
|
|
* single bio to populate the pages for the 2 ranges because
|
|
|
|
* this makes the compressed extent read zero out the pages
|
|
|
|
* belonging to the 2nd range. Imagine the following scenario:
|
|
|
|
*
|
|
|
|
* File layout
|
|
|
|
* [0 - 8K] [8K - 24K]
|
|
|
|
* | |
|
|
|
|
* | |
|
|
|
|
* points to extent X, points to extent X,
|
|
|
|
* offset 4K, length of 8K offset 0, length 16K
|
|
|
|
*
|
|
|
|
* [extent X, compressed length = 4K uncompressed length = 16K]
|
|
|
|
*
|
|
|
|
* If the bio to read the compressed extent covers both ranges,
|
|
|
|
* it will decompress extent X into the pages belonging to the
|
|
|
|
* first range and then it will stop, zeroing out the remaining
|
|
|
|
* pages that belong to the other range that points to extent X.
|
|
|
|
* So here we make sure we submit 2 bios, one for the first
|
|
|
|
* range and another one for the third range. Both will target
|
|
|
|
* the same physical extent from disk, but we can't currently
|
|
|
|
* make the compressed bio endio callback populate the pages
|
|
|
|
* for both ranges because each compressed bio is tightly
|
|
|
|
* coupled with a single extent map, and each range can have
|
|
|
|
* an extent map with a different offset value relative to the
|
|
|
|
* uncompressed data of our extent and different lengths. This
|
|
|
|
* is a corner case so we prioritize correctness over
|
|
|
|
* non-optimal behavior (submitting 2 bios for the same extent).
|
|
|
|
*/
|
|
|
|
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
|
|
|
|
prev_em_start && *prev_em_start != (u64)-1 &&
|
Btrfs: fix corruption reading shared and compressed extents after hole punching
In the past we had data corruption when reading compressed extents that
are shared within the same file and they are consecutive, this got fixed
by commit 005efedf2c7d0 ("Btrfs: fix read corruption of compressed and
shared extents") and by commit 808f80b46790f ("Btrfs: update fix for read
corruption of compressed and shared extents"). However there was a case
that was missing in those fixes, which is when the shared and compressed
extents are referenced with a non-zero offset. The following shell script
creates a reproducer for this issue:
#!/bin/bash
mkfs.btrfs -f /dev/sdc &> /dev/null
mount -o compress /dev/sdc /mnt/sdc
# Create a file with 3 consecutive compressed extents, each has an
# uncompressed size of 128Kb and a compressed size of 4Kb.
for ((i = 1; i <= 3; i++)); do
head -c 4096 /dev/zero
for ((j = 1; j <= 31; j++)); do
head -c 4096 /dev/zero | tr '\0' "\377"
done
done > /mnt/sdc/foobar
sync
echo "Digest after file creation: $(md5sum /mnt/sdc/foobar)"
# Clone the first extent into offsets 128K and 256K.
xfs_io -c "reflink /mnt/sdc/foobar 0 128K 128K" /mnt/sdc/foobar
xfs_io -c "reflink /mnt/sdc/foobar 0 256K 128K" /mnt/sdc/foobar
sync
echo "Digest after cloning: $(md5sum /mnt/sdc/foobar)"
# Punch holes into the regions that are already full of zeroes.
xfs_io -c "fpunch 0 4K" /mnt/sdc/foobar
xfs_io -c "fpunch 128K 4K" /mnt/sdc/foobar
xfs_io -c "fpunch 256K 4K" /mnt/sdc/foobar
sync
echo "Digest after hole punching: $(md5sum /mnt/sdc/foobar)"
echo "Dropping page cache..."
sysctl -q vm.drop_caches=1
echo "Digest after hole punching: $(md5sum /mnt/sdc/foobar)"
umount /dev/sdc
When running the script we get the following output:
Digest after file creation: 5a0888d80d7ab1fd31c229f83a3bbcc8 /mnt/sdc/foobar
linked 131072/131072 bytes at offset 131072
128 KiB, 1 ops; 0.0033 sec (36.960 MiB/sec and 295.6830 ops/sec)
linked 131072/131072 bytes at offset 262144
128 KiB, 1 ops; 0.0015 sec (78.567 MiB/sec and 628.5355 ops/sec)
Digest after cloning: 5a0888d80d7ab1fd31c229f83a3bbcc8 /mnt/sdc/foobar
Digest after hole punching: 5a0888d80d7ab1fd31c229f83a3bbcc8 /mnt/sdc/foobar
Dropping page cache...
Digest after hole punching: fba694ae8664ed0c2e9ff8937e7f1484 /mnt/sdc/foobar
This happens because after reading all the pages of the extent in the
range from 128K to 256K for example, we read the hole at offset 256K
and then when reading the page at offset 260K we don't submit the
existing bio, which is responsible for filling all the page in the
range 128K to 256K only, therefore adding the pages from range 260K
to 384K to the existing bio and submitting it after iterating over the
entire range. Once the bio completes, the uncompressed data fills only
the pages in the range 128K to 256K because there's no more data read
from disk, leaving the pages in the range 260K to 384K unfilled. It is
just a slightly different variant of what was solved by commit
005efedf2c7d0 ("Btrfs: fix read corruption of compressed and shared
extents").
Fix this by forcing a bio submit, during readpages(), whenever we find a
compressed extent map for a page that is different from the extent map
for the previous page or has a different starting offset (in case it's
the same compressed extent), instead of the extent map's original start
offset.
A test case for fstests follows soon.
Reported-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Fixes: 808f80b46790f ("Btrfs: update fix for read corruption of compressed and shared extents")
Fixes: 005efedf2c7d0 ("Btrfs: fix read corruption of compressed and shared extents")
Cc: stable@vger.kernel.org # 4.3+
Tested-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2019-02-14 23:17:20 +08:00
|
|
|
*prev_em_start != em->start)
|
Btrfs: fix read corruption of compressed and shared extents
If a file has a range pointing to a compressed extent, followed by
another range that points to the same compressed extent and a read
operation attempts to read both ranges (either completely or part of
them), the pages that correspond to the second range are incorrectly
filled with zeroes.
Consider the following example:
File layout
[0 - 8K] [8K - 24K]
| |
| |
points to extent X, points to extent X,
offset 4K, length of 8K offset 0, length 16K
[extent X, compressed length = 4K uncompressed length = 16K]
If a readpages() call spans the 2 ranges, a single bio to read the extent
is submitted - extent_io.c:submit_extent_page() would only create a new
bio to cover the second range pointing to the extent if the extent it
points to had a different logical address than the extent associated with
the first range. This has a consequence of the compressed read end io
handler (compression.c:end_compressed_bio_read()) finish once the extent
is decompressed into the pages covering the first range, leaving the
remaining pages (belonging to the second range) filled with zeroes (done
by compression.c:btrfs_clear_biovec_end()).
So fix this by submitting the current bio whenever we find a range
pointing to a compressed extent that was preceded by a range with a
different extent map. This is the simplest solution for this corner
case. Making the end io callback populate both ranges (or more, if we
have multiple pointing to the same extent) is a much more complex
solution since each bio is tightly coupled with a single extent map and
the extent maps associated to the ranges pointing to the shared extent
can have different offsets and lengths.
The following test case for fstests triggers the issue:
seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"
tmp=/tmp/$$
status=1 # failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15
_cleanup()
{
rm -f $tmp.*
}
# get standard environment, filters and checks
. ./common/rc
. ./common/filter
# real QA test starts here
_need_to_be_root
_supported_fs btrfs
_supported_os Linux
_require_scratch
_require_cloner
rm -f $seqres.full
test_clone_and_read_compressed_extent()
{
local mount_opts=$1
_scratch_mkfs >>$seqres.full 2>&1
_scratch_mount $mount_opts
# Create a test file with a single extent that is compressed (the
# data we write into it is highly compressible no matter which
# compression algorithm is used, zlib or lzo).
$XFS_IO_PROG -f -c "pwrite -S 0xaa 0K 4K" \
-c "pwrite -S 0xbb 4K 8K" \
-c "pwrite -S 0xcc 12K 4K" \
$SCRATCH_MNT/foo | _filter_xfs_io
# Now clone our extent into an adjacent offset.
$CLONER_PROG -s $((4 * 1024)) -d $((16 * 1024)) -l $((8 * 1024)) \
$SCRATCH_MNT/foo $SCRATCH_MNT/foo
# Same as before but for this file we clone the extent into a lower
# file offset.
$XFS_IO_PROG -f -c "pwrite -S 0xaa 8K 4K" \
-c "pwrite -S 0xbb 12K 8K" \
-c "pwrite -S 0xcc 20K 4K" \
$SCRATCH_MNT/bar | _filter_xfs_io
$CLONER_PROG -s $((12 * 1024)) -d 0 -l $((8 * 1024)) \
$SCRATCH_MNT/bar $SCRATCH_MNT/bar
echo "File digests before unmounting filesystem:"
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
# Evicting the inode or clearing the page cache before reading
# again the file would also trigger the bug - reads were returning
# all bytes in the range corresponding to the second reference to
# the extent with a value of 0, but the correct data was persisted
# (it was a bug exclusively in the read path). The issue happened
# only if the same readpages() call targeted pages belonging to the
# first and second ranges that point to the same compressed extent.
_scratch_remount
echo "File digests after mounting filesystem again:"
# Must match the same digests we got before.
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
}
echo -e "\nTesting with zlib compression..."
test_clone_and_read_compressed_extent "-o compress=zlib"
_scratch_unmount
echo -e "\nTesting with lzo compression..."
test_clone_and_read_compressed_extent "-o compress=lzo"
status=0
exit
Cc: stable@vger.kernel.org
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo<quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-09-14 16:09:31 +08:00
|
|
|
force_bio_submit = true;
|
|
|
|
|
|
|
|
if (prev_em_start)
|
Btrfs: fix corruption reading shared and compressed extents after hole punching
In the past we had data corruption when reading compressed extents that
are shared within the same file and they are consecutive, this got fixed
by commit 005efedf2c7d0 ("Btrfs: fix read corruption of compressed and
shared extents") and by commit 808f80b46790f ("Btrfs: update fix for read
corruption of compressed and shared extents"). However there was a case
that was missing in those fixes, which is when the shared and compressed
extents are referenced with a non-zero offset. The following shell script
creates a reproducer for this issue:
#!/bin/bash
mkfs.btrfs -f /dev/sdc &> /dev/null
mount -o compress /dev/sdc /mnt/sdc
# Create a file with 3 consecutive compressed extents, each has an
# uncompressed size of 128Kb and a compressed size of 4Kb.
for ((i = 1; i <= 3; i++)); do
head -c 4096 /dev/zero
for ((j = 1; j <= 31; j++)); do
head -c 4096 /dev/zero | tr '\0' "\377"
done
done > /mnt/sdc/foobar
sync
echo "Digest after file creation: $(md5sum /mnt/sdc/foobar)"
# Clone the first extent into offsets 128K and 256K.
xfs_io -c "reflink /mnt/sdc/foobar 0 128K 128K" /mnt/sdc/foobar
xfs_io -c "reflink /mnt/sdc/foobar 0 256K 128K" /mnt/sdc/foobar
sync
echo "Digest after cloning: $(md5sum /mnt/sdc/foobar)"
# Punch holes into the regions that are already full of zeroes.
xfs_io -c "fpunch 0 4K" /mnt/sdc/foobar
xfs_io -c "fpunch 128K 4K" /mnt/sdc/foobar
xfs_io -c "fpunch 256K 4K" /mnt/sdc/foobar
sync
echo "Digest after hole punching: $(md5sum /mnt/sdc/foobar)"
echo "Dropping page cache..."
sysctl -q vm.drop_caches=1
echo "Digest after hole punching: $(md5sum /mnt/sdc/foobar)"
umount /dev/sdc
When running the script we get the following output:
Digest after file creation: 5a0888d80d7ab1fd31c229f83a3bbcc8 /mnt/sdc/foobar
linked 131072/131072 bytes at offset 131072
128 KiB, 1 ops; 0.0033 sec (36.960 MiB/sec and 295.6830 ops/sec)
linked 131072/131072 bytes at offset 262144
128 KiB, 1 ops; 0.0015 sec (78.567 MiB/sec and 628.5355 ops/sec)
Digest after cloning: 5a0888d80d7ab1fd31c229f83a3bbcc8 /mnt/sdc/foobar
Digest after hole punching: 5a0888d80d7ab1fd31c229f83a3bbcc8 /mnt/sdc/foobar
Dropping page cache...
Digest after hole punching: fba694ae8664ed0c2e9ff8937e7f1484 /mnt/sdc/foobar
This happens because after reading all the pages of the extent in the
range from 128K to 256K for example, we read the hole at offset 256K
and then when reading the page at offset 260K we don't submit the
existing bio, which is responsible for filling all the page in the
range 128K to 256K only, therefore adding the pages from range 260K
to 384K to the existing bio and submitting it after iterating over the
entire range. Once the bio completes, the uncompressed data fills only
the pages in the range 128K to 256K because there's no more data read
from disk, leaving the pages in the range 260K to 384K unfilled. It is
just a slightly different variant of what was solved by commit
005efedf2c7d0 ("Btrfs: fix read corruption of compressed and shared
extents").
Fix this by forcing a bio submit, during readpages(), whenever we find a
compressed extent map for a page that is different from the extent map
for the previous page or has a different starting offset (in case it's
the same compressed extent), instead of the extent map's original start
offset.
A test case for fstests follows soon.
Reported-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Fixes: 808f80b46790f ("Btrfs: update fix for read corruption of compressed and shared extents")
Fixes: 005efedf2c7d0 ("Btrfs: fix read corruption of compressed and shared extents")
Cc: stable@vger.kernel.org # 4.3+
Tested-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2019-02-14 23:17:20 +08:00
|
|
|
*prev_em_start = em->start;
|
Btrfs: fix read corruption of compressed and shared extents
If a file has a range pointing to a compressed extent, followed by
another range that points to the same compressed extent and a read
operation attempts to read both ranges (either completely or part of
them), the pages that correspond to the second range are incorrectly
filled with zeroes.
Consider the following example:
File layout
[0 - 8K] [8K - 24K]
| |
| |
points to extent X, points to extent X,
offset 4K, length of 8K offset 0, length 16K
[extent X, compressed length = 4K uncompressed length = 16K]
If a readpages() call spans the 2 ranges, a single bio to read the extent
is submitted - extent_io.c:submit_extent_page() would only create a new
bio to cover the second range pointing to the extent if the extent it
points to had a different logical address than the extent associated with
the first range. This has a consequence of the compressed read end io
handler (compression.c:end_compressed_bio_read()) finish once the extent
is decompressed into the pages covering the first range, leaving the
remaining pages (belonging to the second range) filled with zeroes (done
by compression.c:btrfs_clear_biovec_end()).
So fix this by submitting the current bio whenever we find a range
pointing to a compressed extent that was preceded by a range with a
different extent map. This is the simplest solution for this corner
case. Making the end io callback populate both ranges (or more, if we
have multiple pointing to the same extent) is a much more complex
solution since each bio is tightly coupled with a single extent map and
the extent maps associated to the ranges pointing to the shared extent
can have different offsets and lengths.
The following test case for fstests triggers the issue:
seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"
tmp=/tmp/$$
status=1 # failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15
_cleanup()
{
rm -f $tmp.*
}
# get standard environment, filters and checks
. ./common/rc
. ./common/filter
# real QA test starts here
_need_to_be_root
_supported_fs btrfs
_supported_os Linux
_require_scratch
_require_cloner
rm -f $seqres.full
test_clone_and_read_compressed_extent()
{
local mount_opts=$1
_scratch_mkfs >>$seqres.full 2>&1
_scratch_mount $mount_opts
# Create a test file with a single extent that is compressed (the
# data we write into it is highly compressible no matter which
# compression algorithm is used, zlib or lzo).
$XFS_IO_PROG -f -c "pwrite -S 0xaa 0K 4K" \
-c "pwrite -S 0xbb 4K 8K" \
-c "pwrite -S 0xcc 12K 4K" \
$SCRATCH_MNT/foo | _filter_xfs_io
# Now clone our extent into an adjacent offset.
$CLONER_PROG -s $((4 * 1024)) -d $((16 * 1024)) -l $((8 * 1024)) \
$SCRATCH_MNT/foo $SCRATCH_MNT/foo
# Same as before but for this file we clone the extent into a lower
# file offset.
$XFS_IO_PROG -f -c "pwrite -S 0xaa 8K 4K" \
-c "pwrite -S 0xbb 12K 8K" \
-c "pwrite -S 0xcc 20K 4K" \
$SCRATCH_MNT/bar | _filter_xfs_io
$CLONER_PROG -s $((12 * 1024)) -d 0 -l $((8 * 1024)) \
$SCRATCH_MNT/bar $SCRATCH_MNT/bar
echo "File digests before unmounting filesystem:"
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
# Evicting the inode or clearing the page cache before reading
# again the file would also trigger the bug - reads were returning
# all bytes in the range corresponding to the second reference to
# the extent with a value of 0, but the correct data was persisted
# (it was a bug exclusively in the read path). The issue happened
# only if the same readpages() call targeted pages belonging to the
# first and second ranges that point to the same compressed extent.
_scratch_remount
echo "File digests after mounting filesystem again:"
# Must match the same digests we got before.
md5sum $SCRATCH_MNT/foo | _filter_scratch
md5sum $SCRATCH_MNT/bar | _filter_scratch
}
echo -e "\nTesting with zlib compression..."
test_clone_and_read_compressed_extent "-o compress=zlib"
_scratch_unmount
echo -e "\nTesting with lzo compression..."
test_clone_and_read_compressed_extent "-o compress=lzo"
status=0
exit
Cc: stable@vger.kernel.org
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo<quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-09-14 16:09:31 +08:00
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
free_extent_map(em);
|
|
|
|
em = NULL;
|
|
|
|
|
|
|
|
/* we've found a hole, just zero and go on */
|
|
|
|
if (block_start == EXTENT_MAP_HOLE) {
|
2011-04-06 18:02:20 +08:00
|
|
|
struct extent_state *cached = NULL;
|
|
|
|
|
btrfs: use memzero_page() instead of open coded kmap pattern
There are many places where kmap/memset/kunmap patterns occur.
Use the newly lifted memzero_page() to eliminate direct uses of kmap and
leverage the new core functions use of kmap_local_page().
The development of this patch was aided by the following coccinelle
script:
// <smpl>
// SPDX-License-Identifier: GPL-2.0-only
// Find kmap/memset/kunmap pattern and replace with memset*page calls
//
// NOTE: Offsets and other expressions may be more complex than what the script
// will automatically generate. Therefore a catchall rule is provided to find
// the pattern which then must be evaluated by hand.
//
// Confidence: Low
// Copyright: (C) 2021 Intel Corporation
// URL: http://coccinelle.lip6.fr/
// Comments:
// Options:
//
// Then the memset pattern
//
@ memset_rule1 @
expression page, V, L, Off;
identifier ptr;
type VP;
@@
(
-VP ptr = kmap(page);
|
-ptr = kmap(page);
|
-VP ptr = kmap_atomic(page);
|
-ptr = kmap_atomic(page);
)
<+...
(
-memset(ptr, 0, L);
+memzero_page(page, 0, L);
|
-memset(ptr + Off, 0, L);
+memzero_page(page, Off, L);
|
-memset(ptr, V, L);
+memset_page(page, V, 0, L);
|
-memset(ptr + Off, V, L);
+memset_page(page, V, Off, L);
)
...+>
(
-kunmap(page);
|
-kunmap_atomic(ptr);
)
// Remove any pointers left unused
@
depends on memset_rule1
@
identifier memset_rule1.ptr;
type VP, VP1;
@@
-VP ptr;
... when != ptr;
? VP1 ptr;
//
// Catch all
//
@ memset_rule2 @
expression page;
identifier ptr;
expression GenTo, GenSize, GenValue;
type VP;
@@
(
-VP ptr = kmap(page);
|
-ptr = kmap(page);
|
-VP ptr = kmap_atomic(page);
|
-ptr = kmap_atomic(page);
)
<+...
(
//
// Some call sites have complex expressions within the memset/memcpy
// The follow are catch alls which need to be evaluated by hand.
//
-memset(GenTo, 0, GenSize);
+memzero_pageExtra(page, GenTo, GenSize);
|
-memset(GenTo, GenValue, GenSize);
+memset_pageExtra(page, GenValue, GenTo, GenSize);
)
...+>
(
-kunmap(page);
|
-kunmap_atomic(ptr);
)
// Remove any pointers left unused
@
depends on memset_rule2
@
identifier memset_rule2.ptr;
type VP, VP1;
@@
-VP ptr;
... when != ptr;
? VP1 ptr;
// </smpl>
Link: https://lkml.kernel.org/r/20210309212137.2610186-4-ira.weiny@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 09:40:07 +08:00
|
|
|
memzero_page(page, pg_offset, iosize);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
|
|
|
set_extent_uptodate(tree, cur, cur + iosize - 1,
|
2011-04-06 18:02:20 +08:00
|
|
|
&cached, GFP_NOFS);
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(tree, cur, cur + iosize - 1, &cached);
|
btrfs: integrate page status update for data read path into begin/end_page_read
In btrfs data page read path, the page status update are handled in two
different locations:
btrfs_do_read_page()
{
while (cur <= end) {
/* No need to read from disk */
if (HOLE/PREALLOC/INLINE){
memset();
set_extent_uptodate();
continue;
}
/* Read from disk */
ret = submit_extent_page(end_bio_extent_readpage);
}
end_bio_extent_readpage()
{
endio_readpage_uptodate_page_status();
}
This is fine for sectorsize == PAGE_SIZE case, as for above loop we
should only hit one branch and then exit.
But for subpage, there is more work to be done in page status update:
- Page Unlock condition
Unlike regular page size == sectorsize case, we can no longer just
unlock a page.
Only the last reader of the page can unlock the page.
This means, we can unlock the page either in the while() loop, or in
the endio function.
- Page uptodate condition
Since we have multiple sectors to read for a page, we can only mark
the full page uptodate if all sectors are uptodate.
To handle both subpage and regular cases, introduce a pair of functions
to help handling page status update:
- begin_page_read()
For regular case, it does nothing.
For subpage case, it updates the reader counters so that later
end_page_read() can know who is the last one to unlock the page.
- end_page_read()
This is just endio_readpage_uptodate_page_status() renamed.
The original name is a little too long and too specific for endio.
The new thing added is the condition for page unlock.
Now for subpage data, we unlock the page if we're the last reader.
This does not only provide the basis for subpage data read, but also
hide the special handling of page read from the main read loop.
Also, since we're changing how the page lock is handled, there are two
existing error paths where we need to manually unlock the page before
calling begin_page_read().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-02 10:28:36 +08:00
|
|
|
end_page_read(page, true, cur, iosize);
|
2008-01-25 05:13:08 +08:00
|
|
|
cur = cur + iosize;
|
2011-04-19 20:29:38 +08:00
|
|
|
pg_offset += iosize;
|
2008-01-25 05:13:08 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
/* the get_extent function already copied into the page */
|
2008-01-29 22:59:12 +08:00
|
|
|
if (block_start == EXTENT_MAP_INLINE) {
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(tree, cur, cur + iosize - 1, NULL);
|
btrfs: remove unnecessary EXTENT_UPTODATE state in buffered I/O path
After we copied data to page cache in buffered I/O, we
1. Insert a EXTENT_UPTODATE state into inode's io_tree, by
endio_readpage_release_extent(), set_extent_delalloc() or
set_extent_defrag().
2. Set page uptodate before we unlock the page.
But the only place we check io_tree's EXTENT_UPTODATE state is in
btrfs_do_readpage(). We know we enter btrfs_do_readpage() only when we
have a non-uptodate page, so it is unnecessary to set EXTENT_UPTODATE.
For example, when performing a buffered random read:
fio --rw=randread --ioengine=libaio --direct=0 --numjobs=4 \
--filesize=32G --size=4G --bs=4k --name=job \
--filename=/mnt/file --name=job
Then check how many extent_state in io_tree:
cat /proc/slabinfo | grep btrfs_extent_state | awk '{print $2}'
w/o this patch, we got 640567 btrfs_extent_state.
w/ this patch, we got 204 btrfs_extent_state.
Maintaining such a big tree brings overhead since every I/O needs to insert
EXTENT_LOCKED, insert EXTENT_UPTODATE, then remove EXTENT_LOCKED. And in
every insert or remove, we need to lock io_tree, do tree search, alloc or
dealloc extent states. By removing unnecessary EXTENT_UPTODATE, we keep
io_tree in a minimal size and reduce overhead when performing buffered I/O.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Robbie Ko <robbieko@synology.com>
Signed-off-by: Ethan Lien <ethanlien@synology.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-08-19 10:44:08 +08:00
|
|
|
end_page_read(page, true, cur, iosize);
|
2008-01-29 22:59:12 +08:00
|
|
|
cur = cur + iosize;
|
2011-04-19 20:29:38 +08:00
|
|
|
pg_offset += iosize;
|
2008-01-29 22:59:12 +08:00
|
|
|
continue;
|
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-02-06 02:09:28 +08:00
|
|
|
ret = submit_extent_page(REQ_OP_READ | read_flags, NULL,
|
btrfs: switch page and disk_bytenr argument position for submit_extent_page()
Normally we put (page, pg_len, pg_offset) arguments together, just like
what __bio_add_page() does.
But in submit_extent_page(), what we got is, (page, disk_bytenr, pg_len,
pg_offset), which sometimes can be confusing.
Change the order to (disk_bytenr, page, pg_len, pg_offset) to make it
to follow the common schema.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-13 13:31:13 +08:00
|
|
|
bio_ctrl, disk_bytenr, page, iosize,
|
2022-09-13 13:31:14 +08:00
|
|
|
pg_offset, this_bio_flag,
|
|
|
|
force_bio_submit);
|
2022-02-03 23:36:44 +08:00
|
|
|
if (ret) {
|
btrfs: fix the error handling for submit_extent_page() for btrfs_do_readpage()
[BUG]
Test case generic/475 have a very high chance (almost 100%) to hit a fs
hang, where a data page will never be unlocked and hang all later
operations.
[CAUSE]
In btrfs_do_readpage(), if we hit an error from submit_extent_page() we
will try to do the cleanup for our current io range, and exit.
This works fine for PAGE_SIZE == sectorsize cases, but not for subpage.
For subpage btrfs_do_readpage() will lock the full page first, which can
contain several different sectors and extents:
btrfs_do_readpage()
|- begin_page_read()
| |- btrfs_subpage_start_reader();
| Now the page will have PAGE_SIZE / sectorsize reader pending,
| and the page is locked.
|
|- end_page_read() for different branches
| This function will reduce subpage readers, and when readers
| reach 0, it will unlock the page.
But when submit_extent_page() failed, we only cleanup the current
io range, while the remaining io range will never be cleaned up, and the
page remains locked forever.
[FIX]
Update the error handling of submit_extent_page() to cleanup all the
remaining subpage range before exiting the loop.
Please note that, now submit_extent_page() can only fail due to
sanity check in alloc_new_bio().
Thus regular IO errors are impossible to trigger the error path.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:14 +08:00
|
|
|
/*
|
|
|
|
* We have to unlock the remaining range, or the page
|
|
|
|
* will never be unlocked.
|
|
|
|
*/
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(tree, cur, end, NULL);
|
btrfs: fix the error handling for submit_extent_page() for btrfs_do_readpage()
[BUG]
Test case generic/475 have a very high chance (almost 100%) to hit a fs
hang, where a data page will never be unlocked and hang all later
operations.
[CAUSE]
In btrfs_do_readpage(), if we hit an error from submit_extent_page() we
will try to do the cleanup for our current io range, and exit.
This works fine for PAGE_SIZE == sectorsize cases, but not for subpage.
For subpage btrfs_do_readpage() will lock the full page first, which can
contain several different sectors and extents:
btrfs_do_readpage()
|- begin_page_read()
| |- btrfs_subpage_start_reader();
| Now the page will have PAGE_SIZE / sectorsize reader pending,
| and the page is locked.
|
|- end_page_read() for different branches
| This function will reduce subpage readers, and when readers
| reach 0, it will unlock the page.
But when submit_extent_page() failed, we only cleanup the current
io range, while the remaining io range will never be cleaned up, and the
page remains locked forever.
[FIX]
Update the error handling of submit_extent_page() to cleanup all the
remaining subpage range before exiting the loop.
Please note that, now submit_extent_page() can only fail due to
sanity check in alloc_new_bio().
Thus regular IO errors are impossible to trigger the error path.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:14 +08:00
|
|
|
end_page_read(page, false, cur, end + 1 - cur);
|
2016-07-12 01:39:07 +08:00
|
|
|
goto out;
|
2012-10-06 04:40:32 +08:00
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
cur = cur + iosize;
|
2011-04-19 20:29:38 +08:00
|
|
|
pg_offset += iosize;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
2011-05-27 00:01:56 +08:00
|
|
|
out:
|
2016-07-12 01:39:07 +08:00
|
|
|
return ret;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2022-05-25 10:55:07 +08:00
|
|
|
int btrfs_read_folio(struct file *file, struct folio *folio)
|
2022-04-15 22:33:24 +08:00
|
|
|
{
|
2022-05-25 10:55:07 +08:00
|
|
|
struct page *page = &folio->page;
|
2022-04-15 22:33:24 +08:00
|
|
|
struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
|
|
|
|
u64 start = page_offset(page);
|
|
|
|
u64 end = start + PAGE_SIZE - 1;
|
|
|
|
struct btrfs_bio_ctrl bio_ctrl = { 0 };
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
|
|
|
|
|
|
|
|
ret = btrfs_do_readpage(page, NULL, &bio_ctrl, 0, NULL);
|
|
|
|
/*
|
|
|
|
* If btrfs_do_readpage() failed we will want to submit the assembled
|
|
|
|
* bio to do the cleanup.
|
|
|
|
*/
|
2022-06-03 15:11:03 +08:00
|
|
|
submit_one_bio(&bio_ctrl);
|
2022-04-15 22:33:24 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2020-02-06 02:09:40 +08:00
|
|
|
static inline void contiguous_readpages(struct page *pages[], int nr_pages,
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
u64 start, u64 end,
|
|
|
|
struct extent_map **em_cached,
|
|
|
|
struct btrfs_bio_ctrl *bio_ctrl,
|
|
|
|
u64 *prev_em_start)
|
2013-07-25 19:22:36 +08:00
|
|
|
{
|
2019-05-07 15:19:23 +08:00
|
|
|
struct btrfs_inode *inode = BTRFS_I(pages[0]->mapping->host);
|
2013-07-25 19:22:36 +08:00
|
|
|
int index;
|
|
|
|
|
2020-02-06 02:09:33 +08:00
|
|
|
btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
|
2013-07-25 19:22:36 +08:00
|
|
|
|
|
|
|
for (index = 0; index < nr_pages; index++) {
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
btrfs_do_readpage(pages[index], em_cached, bio_ctrl,
|
2020-09-14 19:39:16 +08:00
|
|
|
REQ_RAHEAD, prev_em_start);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
put_page(pages[index]);
|
2013-07-25 19:22:36 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
/*
|
2014-05-22 04:35:51 +08:00
|
|
|
* helper for __extent_writepage, doing all of the delayed allocation setup.
|
|
|
|
*
|
2018-11-01 20:09:46 +08:00
|
|
|
* This returns 1 if btrfs_run_delalloc_range function did all the work required
|
2014-05-22 04:35:51 +08:00
|
|
|
* to write the page (copy into inline extent). In this case the IO has
|
|
|
|
* been started and the page is already unlocked.
|
|
|
|
*
|
|
|
|
* This returns 0 if all went well (page still locked)
|
|
|
|
* This returns < 0 if there were errors (page still locked)
|
2008-01-25 05:13:08 +08:00
|
|
|
*/
|
2020-06-05 15:42:10 +08:00
|
|
|
static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
|
btrfs: remove unnecessary @nr_written parameters
We use @nr_written to record how many pages have been started by
btrfs_run_delalloc_range().
Currently there are only two cases that would populate @nr_written:
- Inline extent creation
- Compressed write
But both cases will also set @page_started to one.
In fact, in writepage_delalloc() we have the following code, showing
that @nr_written is really only utilized for above two cases:
/* did the fill delalloc function already unlock and start
* the IO?
*/
if (page_started) {
/*
* we've unlocked the page, so we can't update
* the mapping's writeback index, just update
* nr_to_write.
*/
wbc->nr_to_write -= nr_written;
return 1;
}
But for such cases, writepage_delalloc() will return 1, and exit
__extent_writepage() without going through __extent_writepage_io().
Thus this means, inside __extent_writepage_io(), we always get
@nr_written as 0.
So this patch is going to remove the unnecessary parameter from the
following functions:
- writepage_delalloc()
As @nr_written passed in is always the initial value 0.
Although inside that function, we still need a local @nr_written
to update wbc->nr_to_write.
- __extent_writepage_io()
As explained above, @nr_written passed in can only be 0.
This also means we can remove one update_nr_written() call.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-11-12 13:33:14 +08:00
|
|
|
struct page *page, struct writeback_control *wbc)
|
2014-05-22 04:35:51 +08:00
|
|
|
{
|
btrfs: subpage: avoid potential deadlock with compression and delalloc
[BUG]
With experimental subpage compression enabled, a simple fsstress can
lead to self deadlock on page 720896:
mkfs.btrfs -f -s 4k $dev > /dev/null
mount $dev -o compress $mnt
$fsstress -p 1 -n 100 -w -d $mnt -v -s 1625511156
[CAUSE]
If we have a file layout looks like below:
0 32K 64K 96K 128K
|//| |///////////////|
4K
Then we run delalloc range for the inode, it will:
- Call find_lock_delalloc_range() with @delalloc_start = 0
Then we got a delalloc range [0, 4K).
This range will be COWed.
- Call find_lock_delalloc_range() again with @delalloc_start = 4K
Since find_lock_delalloc_range() never cares whether the range
is still inside page range [0, 64K), it will return range [64K, 128K).
This range meets the condition for subpage compression, will go
through async COW path.
And async COW path will return @page_started.
But that @page_started is now for range [64K, 128K), not for range
[0, 64K).
- writepage_dellloc() returned 1 for page [0, 64K)
Thus page [0, 64K) will not be unlocked, nor its page dirty status
will be cleared.
Next time when we try to lock page [0, 64K) we will deadlock, as there
is no one to release page [0, 64K).
This problem will never happen for regular page size as one page only
contains one sector. After the first find_lock_delalloc_range() call,
the @delalloc_end will go beyond @page_end no matter if we found a
delalloc range or not
Thus this bug only happens for subpage, as now we need multiple runs to
exhaust the delalloc range of a page.
[FIX]
Fix the problem by ensuring the delalloc range we ran at least started
inside @locked_page.
So that we will never get incorrect @page_started.
And to prevent such problem from happening again:
- Make find_lock_delalloc_range() return false if the found range is
beyond @end value passed in.
Since @end will be utilized now, add an ASSERT() to ensure we pass
correct @end into find_lock_delalloc_range().
This also means, for selftests we needs to populate @end before calling
find_lock_delalloc_range().
- New ASSERT() in find_lock_delalloc_range()
Now we will make sure the @start/@end passed in at least covers part
of the page.
- New ASSERT() in run_delalloc_range()
To make sure the range at least starts inside @locked page.
- Use @delalloc_start as proper cursor, while @delalloc_end is always
reset to @page_end.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:22:07 +08:00
|
|
|
const u64 page_end = page_offset(page) + PAGE_SIZE - 1;
|
2021-09-27 15:21:44 +08:00
|
|
|
u64 delalloc_start = page_offset(page);
|
2014-05-22 04:35:51 +08:00
|
|
|
u64 delalloc_to_write = 0;
|
btrfs: remove unnecessary @nr_written parameters
We use @nr_written to record how many pages have been started by
btrfs_run_delalloc_range().
Currently there are only two cases that would populate @nr_written:
- Inline extent creation
- Compressed write
But both cases will also set @page_started to one.
In fact, in writepage_delalloc() we have the following code, showing
that @nr_written is really only utilized for above two cases:
/* did the fill delalloc function already unlock and start
* the IO?
*/
if (page_started) {
/*
* we've unlocked the page, so we can't update
* the mapping's writeback index, just update
* nr_to_write.
*/
wbc->nr_to_write -= nr_written;
return 1;
}
But for such cases, writepage_delalloc() will return 1, and exit
__extent_writepage() without going through __extent_writepage_io().
Thus this means, inside __extent_writepage_io(), we always get
@nr_written as 0.
So this patch is going to remove the unnecessary parameter from the
following functions:
- writepage_delalloc()
As @nr_written passed in is always the initial value 0.
Although inside that function, we still need a local @nr_written
to update wbc->nr_to_write.
- __extent_writepage_io()
As explained above, @nr_written passed in can only be 0.
This also means we can remove one update_nr_written() call.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-11-12 13:33:14 +08:00
|
|
|
/* How many pages are started by btrfs_run_delalloc_range() */
|
|
|
|
unsigned long nr_written = 0;
|
2014-05-22 04:35:51 +08:00
|
|
|
int ret;
|
|
|
|
int page_started = 0;
|
|
|
|
|
btrfs: subpage: avoid potential deadlock with compression and delalloc
[BUG]
With experimental subpage compression enabled, a simple fsstress can
lead to self deadlock on page 720896:
mkfs.btrfs -f -s 4k $dev > /dev/null
mount $dev -o compress $mnt
$fsstress -p 1 -n 100 -w -d $mnt -v -s 1625511156
[CAUSE]
If we have a file layout looks like below:
0 32K 64K 96K 128K
|//| |///////////////|
4K
Then we run delalloc range for the inode, it will:
- Call find_lock_delalloc_range() with @delalloc_start = 0
Then we got a delalloc range [0, 4K).
This range will be COWed.
- Call find_lock_delalloc_range() again with @delalloc_start = 4K
Since find_lock_delalloc_range() never cares whether the range
is still inside page range [0, 64K), it will return range [64K, 128K).
This range meets the condition for subpage compression, will go
through async COW path.
And async COW path will return @page_started.
But that @page_started is now for range [64K, 128K), not for range
[0, 64K).
- writepage_dellloc() returned 1 for page [0, 64K)
Thus page [0, 64K) will not be unlocked, nor its page dirty status
will be cleared.
Next time when we try to lock page [0, 64K) we will deadlock, as there
is no one to release page [0, 64K).
This problem will never happen for regular page size as one page only
contains one sector. After the first find_lock_delalloc_range() call,
the @delalloc_end will go beyond @page_end no matter if we found a
delalloc range or not
Thus this bug only happens for subpage, as now we need multiple runs to
exhaust the delalloc range of a page.
[FIX]
Fix the problem by ensuring the delalloc range we ran at least started
inside @locked_page.
So that we will never get incorrect @page_started.
And to prevent such problem from happening again:
- Make find_lock_delalloc_range() return false if the found range is
beyond @end value passed in.
Since @end will be utilized now, add an ASSERT() to ensure we pass
correct @end into find_lock_delalloc_range().
This also means, for selftests we needs to populate @end before calling
find_lock_delalloc_range().
- New ASSERT() in find_lock_delalloc_range()
Now we will make sure the @start/@end passed in at least covers part
of the page.
- New ASSERT() in run_delalloc_range()
To make sure the range at least starts inside @locked page.
- Use @delalloc_start as proper cursor, while @delalloc_end is always
reset to @page_end.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:22:07 +08:00
|
|
|
while (delalloc_start < page_end) {
|
|
|
|
u64 delalloc_end = page_end;
|
|
|
|
bool found;
|
2014-05-22 04:35:51 +08:00
|
|
|
|
2020-06-05 15:42:10 +08:00
|
|
|
found = find_lock_delalloc_range(&inode->vfs_inode, page,
|
2014-05-22 04:35:51 +08:00
|
|
|
&delalloc_start,
|
2018-10-26 19:43:20 +08:00
|
|
|
&delalloc_end);
|
2018-11-29 11:33:38 +08:00
|
|
|
if (!found) {
|
2014-05-22 04:35:51 +08:00
|
|
|
delalloc_start = delalloc_end + 1;
|
|
|
|
continue;
|
|
|
|
}
|
2020-06-05 15:42:10 +08:00
|
|
|
ret = btrfs_run_delalloc_range(inode, page, delalloc_start,
|
btrfs: remove unnecessary @nr_written parameters
We use @nr_written to record how many pages have been started by
btrfs_run_delalloc_range().
Currently there are only two cases that would populate @nr_written:
- Inline extent creation
- Compressed write
But both cases will also set @page_started to one.
In fact, in writepage_delalloc() we have the following code, showing
that @nr_written is really only utilized for above two cases:
/* did the fill delalloc function already unlock and start
* the IO?
*/
if (page_started) {
/*
* we've unlocked the page, so we can't update
* the mapping's writeback index, just update
* nr_to_write.
*/
wbc->nr_to_write -= nr_written;
return 1;
}
But for such cases, writepage_delalloc() will return 1, and exit
__extent_writepage() without going through __extent_writepage_io().
Thus this means, inside __extent_writepage_io(), we always get
@nr_written as 0.
So this patch is going to remove the unnecessary parameter from the
following functions:
- writepage_delalloc()
As @nr_written passed in is always the initial value 0.
Although inside that function, we still need a local @nr_written
to update wbc->nr_to_write.
- __extent_writepage_io()
As explained above, @nr_written passed in can only be 0.
This also means we can remove one update_nr_written() call.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-11-12 13:33:14 +08:00
|
|
|
delalloc_end, &page_started, &nr_written, wbc);
|
2014-05-22 04:35:51 +08:00
|
|
|
if (ret) {
|
btrfs: unify regular and subpage error paths in __extent_writepage()
[BUG]
When running btrfs/160 in a loop for subpage with experimental
compression support, it has a high chance to crash (~20%):
BTRFS critical (device dm-7): panic in __btrfs_add_ordered_extent:238: inconsistency in ordered tree at offset 0 (errno=-17 Object already exists)
------------[ cut here ]------------
kernel BUG at fs/btrfs/ordered-data.c:238!
Internal error: Oops - BUG: 0 [#1] SMP
pc : __btrfs_add_ordered_extent+0x550/0x670 [btrfs]
lr : __btrfs_add_ordered_extent+0x550/0x670 [btrfs]
Call trace:
__btrfs_add_ordered_extent+0x550/0x670 [btrfs]
btrfs_add_ordered_extent+0x2c/0x50 [btrfs]
run_delalloc_nocow+0x81c/0x8fc [btrfs]
btrfs_run_delalloc_range+0xa4/0x390 [btrfs]
writepage_delalloc+0xc0/0x1ac [btrfs]
__extent_writepage+0xf4/0x370 [btrfs]
extent_write_cache_pages+0x288/0x4f4 [btrfs]
extent_writepages+0x58/0xe0 [btrfs]
btrfs_writepages+0x1c/0x30 [btrfs]
do_writepages+0x60/0x110
__filemap_fdatawrite_range+0x108/0x170
filemap_fdatawrite_range+0x20/0x30
btrfs_fdatawrite_range+0x34/0x4dc [btrfs]
__btrfs_write_out_cache+0x34c/0x480 [btrfs]
btrfs_write_out_cache+0x144/0x220 [btrfs]
btrfs_start_dirty_block_groups+0x3ac/0x6b0 [btrfs]
btrfs_commit_transaction+0xd0/0xbb4 [btrfs]
btrfs_sync_fs+0x64/0x1cc [btrfs]
sync_fs_one_sb+0x3c/0x50
iterate_supers+0xcc/0x1d4
ksys_sync+0x6c/0xd0
__arm64_sys_sync+0x1c/0x30
invoke_syscall+0x50/0x120
el0_svc_common.constprop.0+0x4c/0xd4
do_el0_svc+0x30/0x9c
el0_svc+0x2c/0x54
el0_sync_handler+0x1a8/0x1b0
el0_sync+0x198/0x1c0
---[ end trace 336f67369ae6e0af ]---
[CAUSE]
For subpage case, we can have multiple sectors inside a page, this makes
it possible for __extent_writepage() to have part of its page submitted
before returning.
In btrfs/160, we are using dm-dust to emulate write error, this means
for certain pages, we could have everything running fine, but at the end
of __extent_writepage(), one of the submitted bios fails due to dm-dust.
Then the page is marked Error, and we change @ret from 0 to -EIO.
This makes the caller extent_write_cache_pages() to error out, without
submitting the remaining pages.
Furthermore, since we're erroring out for free space cache, it doesn't
really care about the error and will update the inode and retry the
writeback.
Then we re-run the delalloc range, and will try to insert the same
delalloc range while previous delalloc range is still hanging there,
triggering the above error.
[FIX]
The proper fix is to handle errors from __extent_writepage() properly,
by ending the remaining ordered extent.
But that fix needs the following changes:
- Know at exactly which sector the error happened
Currently __extent_writepage_io() works for the full page, can't
return at which sector we hit the error.
- Grab the ordered extent covering the failed sector
As a hotfix for subpage case, here we unify the error paths in
__extent_writepage().
In fact, the "if (PageError(page))" branch never get executed if @ret is
still 0 for non-subpage cases.
As for non-subpage case, we never submit current page in
__extent_writepage(), but only add current page into bio.
The bio can only get submitted in next page.
Thus we never get PageError() set due to IO failure, thus when we hit
the branch, @ret is never 0.
By simply removing that @ret assignment, we let subpage case ignore the
IO failure, thus only error out for fatal errors just like regular
sectorsize.
So that IO error won't be treated as fatal error not trigger the hanging
OE problem.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:07 +08:00
|
|
|
btrfs_page_set_error(inode->root->fs_info, page,
|
|
|
|
page_offset(page), PAGE_SIZE);
|
2021-07-28 14:05:05 +08:00
|
|
|
return ret;
|
2014-05-22 04:35:51 +08:00
|
|
|
}
|
|
|
|
/*
|
2016-04-01 20:29:48 +08:00
|
|
|
* delalloc_end is already one less than the total length, so
|
|
|
|
* we don't subtract one from PAGE_SIZE
|
2014-05-22 04:35:51 +08:00
|
|
|
*/
|
|
|
|
delalloc_to_write += (delalloc_end - delalloc_start +
|
2016-04-01 20:29:48 +08:00
|
|
|
PAGE_SIZE) >> PAGE_SHIFT;
|
2014-05-22 04:35:51 +08:00
|
|
|
delalloc_start = delalloc_end + 1;
|
|
|
|
}
|
|
|
|
if (wbc->nr_to_write < delalloc_to_write) {
|
|
|
|
int thresh = 8192;
|
|
|
|
|
|
|
|
if (delalloc_to_write < thresh * 2)
|
|
|
|
thresh = delalloc_to_write;
|
|
|
|
wbc->nr_to_write = min_t(u64, delalloc_to_write,
|
|
|
|
thresh);
|
|
|
|
}
|
|
|
|
|
btrfs: remove unnecessary @nr_written parameters
We use @nr_written to record how many pages have been started by
btrfs_run_delalloc_range().
Currently there are only two cases that would populate @nr_written:
- Inline extent creation
- Compressed write
But both cases will also set @page_started to one.
In fact, in writepage_delalloc() we have the following code, showing
that @nr_written is really only utilized for above two cases:
/* did the fill delalloc function already unlock and start
* the IO?
*/
if (page_started) {
/*
* we've unlocked the page, so we can't update
* the mapping's writeback index, just update
* nr_to_write.
*/
wbc->nr_to_write -= nr_written;
return 1;
}
But for such cases, writepage_delalloc() will return 1, and exit
__extent_writepage() without going through __extent_writepage_io().
Thus this means, inside __extent_writepage_io(), we always get
@nr_written as 0.
So this patch is going to remove the unnecessary parameter from the
following functions:
- writepage_delalloc()
As @nr_written passed in is always the initial value 0.
Although inside that function, we still need a local @nr_written
to update wbc->nr_to_write.
- __extent_writepage_io()
As explained above, @nr_written passed in can only be 0.
This also means we can remove one update_nr_written() call.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-11-12 13:33:14 +08:00
|
|
|
/* Did btrfs_run_dealloc_range() already unlock and start the IO? */
|
2014-05-22 04:35:51 +08:00
|
|
|
if (page_started) {
|
|
|
|
/*
|
btrfs: remove unnecessary @nr_written parameters
We use @nr_written to record how many pages have been started by
btrfs_run_delalloc_range().
Currently there are only two cases that would populate @nr_written:
- Inline extent creation
- Compressed write
But both cases will also set @page_started to one.
In fact, in writepage_delalloc() we have the following code, showing
that @nr_written is really only utilized for above two cases:
/* did the fill delalloc function already unlock and start
* the IO?
*/
if (page_started) {
/*
* we've unlocked the page, so we can't update
* the mapping's writeback index, just update
* nr_to_write.
*/
wbc->nr_to_write -= nr_written;
return 1;
}
But for such cases, writepage_delalloc() will return 1, and exit
__extent_writepage() without going through __extent_writepage_io().
Thus this means, inside __extent_writepage_io(), we always get
@nr_written as 0.
So this patch is going to remove the unnecessary parameter from the
following functions:
- writepage_delalloc()
As @nr_written passed in is always the initial value 0.
Although inside that function, we still need a local @nr_written
to update wbc->nr_to_write.
- __extent_writepage_io()
As explained above, @nr_written passed in can only be 0.
This also means we can remove one update_nr_written() call.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-11-12 13:33:14 +08:00
|
|
|
* We've unlocked the page, so we can't update the mapping's
|
|
|
|
* writeback index, just update nr_to_write.
|
2014-05-22 04:35:51 +08:00
|
|
|
*/
|
btrfs: remove unnecessary @nr_written parameters
We use @nr_written to record how many pages have been started by
btrfs_run_delalloc_range().
Currently there are only two cases that would populate @nr_written:
- Inline extent creation
- Compressed write
But both cases will also set @page_started to one.
In fact, in writepage_delalloc() we have the following code, showing
that @nr_written is really only utilized for above two cases:
/* did the fill delalloc function already unlock and start
* the IO?
*/
if (page_started) {
/*
* we've unlocked the page, so we can't update
* the mapping's writeback index, just update
* nr_to_write.
*/
wbc->nr_to_write -= nr_written;
return 1;
}
But for such cases, writepage_delalloc() will return 1, and exit
__extent_writepage() without going through __extent_writepage_io().
Thus this means, inside __extent_writepage_io(), we always get
@nr_written as 0.
So this patch is going to remove the unnecessary parameter from the
following functions:
- writepage_delalloc()
As @nr_written passed in is always the initial value 0.
Although inside that function, we still need a local @nr_written
to update wbc->nr_to_write.
- __extent_writepage_io()
As explained above, @nr_written passed in can only be 0.
This also means we can remove one update_nr_written() call.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-11-12 13:33:14 +08:00
|
|
|
wbc->nr_to_write -= nr_written;
|
2014-05-22 04:35:51 +08:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2020-07-16 23:17:19 +08:00
|
|
|
return 0;
|
2014-05-22 04:35:51 +08:00
|
|
|
}
|
|
|
|
|
2021-05-31 16:50:50 +08:00
|
|
|
/*
|
|
|
|
* Find the first byte we need to write.
|
|
|
|
*
|
|
|
|
* For subpage, one page can contain several sectors, and
|
|
|
|
* __extent_writepage_io() will just grab all extent maps in the page
|
|
|
|
* range and try to submit all non-inline/non-compressed extents.
|
|
|
|
*
|
|
|
|
* This is a big problem for subpage, we shouldn't re-submit already written
|
|
|
|
* data at all.
|
|
|
|
* This function will lookup subpage dirty bit to find which range we really
|
|
|
|
* need to submit.
|
|
|
|
*
|
|
|
|
* Return the next dirty range in [@start, @end).
|
|
|
|
* If no dirty range is found, @start will be page_offset(page) + PAGE_SIZE.
|
|
|
|
*/
|
|
|
|
static void find_next_dirty_byte(struct btrfs_fs_info *fs_info,
|
|
|
|
struct page *page, u64 *start, u64 *end)
|
|
|
|
{
|
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
2021-08-17 17:38:52 +08:00
|
|
|
struct btrfs_subpage_info *spi = fs_info->subpage_info;
|
2021-05-31 16:50:50 +08:00
|
|
|
u64 orig_start = *start;
|
|
|
|
/* Declare as unsigned long so we can use bitmap ops */
|
|
|
|
unsigned long flags;
|
2021-08-17 17:38:52 +08:00
|
|
|
int range_start_bit;
|
2021-05-31 16:50:50 +08:00
|
|
|
int range_end_bit;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For regular sector size == page size case, since one page only
|
|
|
|
* contains one sector, we return the page offset directly.
|
|
|
|
*/
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (!btrfs_is_subpage(fs_info, page)) {
|
2021-05-31 16:50:50 +08:00
|
|
|
*start = page_offset(page);
|
|
|
|
*end = page_offset(page) + PAGE_SIZE;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2021-08-17 17:38:52 +08:00
|
|
|
range_start_bit = spi->dirty_offset +
|
|
|
|
(offset_in_page(orig_start) >> fs_info->sectorsize_bits);
|
|
|
|
|
2021-05-31 16:50:50 +08:00
|
|
|
/* We should have the page locked, but just in case */
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
2021-08-17 17:38:52 +08:00
|
|
|
bitmap_next_set_region(subpage->bitmaps, &range_start_bit, &range_end_bit,
|
|
|
|
spi->dirty_offset + spi->bitmap_nr_bits);
|
2021-05-31 16:50:50 +08:00
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
|
2021-08-17 17:38:52 +08:00
|
|
|
range_start_bit -= spi->dirty_offset;
|
|
|
|
range_end_bit -= spi->dirty_offset;
|
|
|
|
|
2021-05-31 16:50:50 +08:00
|
|
|
*start = page_offset(page) + range_start_bit * fs_info->sectorsize;
|
|
|
|
*end = page_offset(page) + range_end_bit * fs_info->sectorsize;
|
|
|
|
}
|
|
|
|
|
2014-05-22 04:35:51 +08:00
|
|
|
/*
|
|
|
|
* helper for __extent_writepage. This calls the writepage start hooks,
|
|
|
|
* and does the loop to map the page into extents and bios.
|
|
|
|
*
|
|
|
|
* We return 1 if the IO is started and the page is unlocked,
|
|
|
|
* 0 if all went well (page still locked)
|
|
|
|
* < 0 if there were errors (page still locked)
|
|
|
|
*/
|
2020-06-03 13:55:33 +08:00
|
|
|
static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
|
2014-05-22 04:35:51 +08:00
|
|
|
struct page *page,
|
|
|
|
struct writeback_control *wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl,
|
2014-05-22 04:35:51 +08:00
|
|
|
loff_t i_size,
|
2019-10-30 01:28:55 +08:00
|
|
|
int *nr_ret)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2021-01-06 09:01:41 +08:00
|
|
|
struct btrfs_fs_info *fs_info = inode->root->fs_info;
|
2021-07-27 13:41:32 +08:00
|
|
|
u64 cur = page_offset(page);
|
|
|
|
u64 end = cur + PAGE_SIZE - 1;
|
2008-01-25 05:13:08 +08:00
|
|
|
u64 extent_offset;
|
|
|
|
u64 block_start;
|
|
|
|
struct extent_map *em;
|
btrfs: return correct error number for __extent_writepage_io()
[BUG]
If we hit an error from submit_extent_page() inside
__extent_writepage_io(), we could still return 0 to the caller, and
even trigger the warning in btrfs_page_assert_not_dirty().
[CAUSE]
In __extent_writepage_io(), if we hit an error from
submit_extent_page(), we will just clean up the range and continue.
This is completely fine for regular PAGE_SIZE == sectorsize, as we can
only hit one sector in one page, thus after the error we're ensured to
exit and @ret will be saved.
But for subpage case, we may have other dirty subpage range in the page,
and in the next loop, we may succeeded submitting the next range.
In that case, @ret will be overwritten, and we return 0 to the caller,
while we have hit some error.
[FIX]
Introduce @has_error and @saved_ret to record the first error we hit, so
we will never forget what error we hit.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:15 +08:00
|
|
|
int saved_ret = 0;
|
2014-05-22 04:35:51 +08:00
|
|
|
int ret = 0;
|
|
|
|
int nr = 0;
|
2022-07-15 02:07:16 +08:00
|
|
|
enum req_op op = REQ_OP_WRITE;
|
|
|
|
const blk_opf_t write_flags = wbc_to_write_flags(wbc);
|
btrfs: return correct error number for __extent_writepage_io()
[BUG]
If we hit an error from submit_extent_page() inside
__extent_writepage_io(), we could still return 0 to the caller, and
even trigger the warning in btrfs_page_assert_not_dirty().
[CAUSE]
In __extent_writepage_io(), if we hit an error from
submit_extent_page(), we will just clean up the range and continue.
This is completely fine for regular PAGE_SIZE == sectorsize, as we can
only hit one sector in one page, thus after the error we're ensured to
exit and @ret will be saved.
But for subpage case, we may have other dirty subpage range in the page,
and in the next loop, we may succeeded submitting the next range.
In that case, @ret will be overwritten, and we return 0 to the caller,
while we have hit some error.
[FIX]
Introduce @has_error and @saved_ret to record the first error we hit, so
we will never forget what error we hit.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:15 +08:00
|
|
|
bool has_error = false;
|
2014-05-22 04:35:51 +08:00
|
|
|
bool compressed;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
|
2021-07-27 13:41:32 +08:00
|
|
|
ret = btrfs_writepage_cow_fixup(page);
|
2018-11-01 20:09:47 +08:00
|
|
|
if (ret) {
|
|
|
|
/* Fixup worker will requeue */
|
2020-01-22 00:51:43 +08:00
|
|
|
redirty_page_for_writepage(wbc, page);
|
2018-11-01 20:09:47 +08:00
|
|
|
unlock_page(page);
|
|
|
|
return 1;
|
2008-07-18 00:53:51 +08:00
|
|
|
}
|
|
|
|
|
2009-04-21 03:50:09 +08:00
|
|
|
/*
|
|
|
|
* we don't want to touch the inode after unlocking the page,
|
|
|
|
* so we update the mapping writeback index now
|
|
|
|
*/
|
2021-07-27 18:45:11 +08:00
|
|
|
wbc->nr_to_write--;
|
2008-11-07 11:02:51 +08:00
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
bio_ctrl->end_io_func = end_bio_extent_writepage;
|
2008-01-25 05:13:08 +08:00
|
|
|
while (cur <= end) {
|
2021-01-06 09:01:40 +08:00
|
|
|
u64 disk_bytenr;
|
2014-05-22 04:35:51 +08:00
|
|
|
u64 em_end;
|
2021-05-31 16:50:50 +08:00
|
|
|
u64 dirty_range_start = cur;
|
|
|
|
u64 dirty_range_end;
|
2021-01-06 09:01:41 +08:00
|
|
|
u32 iosize;
|
2016-05-04 17:46:10 +08:00
|
|
|
|
2014-05-22 04:35:51 +08:00
|
|
|
if (cur >= i_size) {
|
2021-04-08 20:32:27 +08:00
|
|
|
btrfs_writepage_endio_finish_ordered(inode, page, cur,
|
2021-07-26 20:15:08 +08:00
|
|
|
end, true);
|
btrfs: subpage: fix writeback which does not have ordered extent
[BUG]
When running fsstress with subpage RW support, there are random
BUG_ON()s triggered with the following trace:
kernel BUG at fs/btrfs/file-item.c:667!
Internal error: Oops - BUG: 0 [#1] SMP
CPU: 1 PID: 3486 Comm: kworker/u13:2 5.11.0-rc4-custom+ #43
Hardware name: Radxa ROCK Pi 4B (DT)
Workqueue: btrfs-worker-high btrfs_work_helper [btrfs]
pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--)
pc : btrfs_csum_one_bio+0x420/0x4e0 [btrfs]
lr : btrfs_csum_one_bio+0x400/0x4e0 [btrfs]
Call trace:
btrfs_csum_one_bio+0x420/0x4e0 [btrfs]
btrfs_submit_bio_start+0x20/0x30 [btrfs]
run_one_async_start+0x28/0x44 [btrfs]
btrfs_work_helper+0x128/0x1b4 [btrfs]
process_one_work+0x22c/0x430
worker_thread+0x70/0x3a0
kthread+0x13c/0x140
ret_from_fork+0x10/0x30
[CAUSE]
Above BUG_ON() means there is some bio range which doesn't have ordered
extent, which indeed is worth a BUG_ON().
Unlike regular sectorsize == PAGE_SIZE case, in subpage we have extra
subpage dirty bitmap to record which range is dirty and should be
written back.
This means, if we submit bio for a subpage range, we do not only need to
clear page dirty, but also need to clear subpage dirty bits.
In __extent_writepage_io(), we will call btrfs_page_clear_dirty() for
any range we submit a bio.
But there is loophole, if we hit a range which is beyond i_size, we just
call btrfs_writepage_endio_finish_ordered() to finish the ordered io,
then break out, without clearing the subpage dirty.
This means, if we hit above branch, the subpage dirty bits are still
there, if other range of the page get dirtied and we need to writeback
that page again, we will submit bio for the old range, leaving a wild
bio range which doesn't have ordered extent.
[FIX]
Fix it by always calling btrfs_page_clear_dirty() in
__extent_writepage_io().
Also to avoid such problem from happening again, add a new assert,
btrfs_page_assert_not_dirty(), to make sure both page dirty and subpage
dirty bits are cleared before exiting __extent_writepage_io().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:58 +08:00
|
|
|
/*
|
|
|
|
* This range is beyond i_size, thus we don't need to
|
|
|
|
* bother writing back.
|
|
|
|
* But we still need to clear the dirty subpage bit, or
|
|
|
|
* the next time the page gets dirtied, we will try to
|
|
|
|
* writeback the sectors with subpage dirty bits,
|
|
|
|
* causing writeback without ordered extent.
|
|
|
|
*/
|
|
|
|
btrfs_page_clear_dirty(fs_info, page, cur, end + 1 - cur);
|
2008-01-25 05:13:08 +08:00
|
|
|
break;
|
|
|
|
}
|
2021-05-31 16:50:50 +08:00
|
|
|
|
|
|
|
find_next_dirty_byte(fs_info, page, &dirty_range_start,
|
|
|
|
&dirty_range_end);
|
|
|
|
if (cur < dirty_range_start) {
|
|
|
|
cur = dirty_range_start;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2020-06-03 13:55:33 +08:00
|
|
|
em = btrfs_get_extent(inode, NULL, 0, cur, end - cur + 1);
|
2022-02-03 23:36:42 +08:00
|
|
|
if (IS_ERR(em)) {
|
2021-05-31 16:50:50 +08:00
|
|
|
btrfs_page_set_error(fs_info, page, cur, end - cur + 1);
|
2014-05-10 00:17:40 +08:00
|
|
|
ret = PTR_ERR_OR_ZERO(em);
|
btrfs: return correct error number for __extent_writepage_io()
[BUG]
If we hit an error from submit_extent_page() inside
__extent_writepage_io(), we could still return 0 to the caller, and
even trigger the warning in btrfs_page_assert_not_dirty().
[CAUSE]
In __extent_writepage_io(), if we hit an error from
submit_extent_page(), we will just clean up the range and continue.
This is completely fine for regular PAGE_SIZE == sectorsize, as we can
only hit one sector in one page, thus after the error we're ensured to
exit and @ret will be saved.
But for subpage case, we may have other dirty subpage range in the page,
and in the next loop, we may succeeded submitting the next range.
In that case, @ret will be overwritten, and we return 0 to the caller,
while we have hit some error.
[FIX]
Introduce @has_error and @saved_ret to record the first error we hit, so
we will never forget what error we hit.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:15 +08:00
|
|
|
has_error = true;
|
|
|
|
if (!saved_ret)
|
|
|
|
saved_ret = ret;
|
2008-01-25 05:13:08 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
extent_offset = cur - em->start;
|
2014-05-22 04:35:51 +08:00
|
|
|
em_end = extent_map_end(em);
|
2021-01-06 09:01:41 +08:00
|
|
|
ASSERT(cur <= em_end);
|
|
|
|
ASSERT(cur < end);
|
|
|
|
ASSERT(IS_ALIGNED(em->start, fs_info->sectorsize));
|
|
|
|
ASSERT(IS_ALIGNED(em->len, fs_info->sectorsize));
|
2008-01-25 05:13:08 +08:00
|
|
|
block_start = em->block_start;
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
|
2021-01-06 09:01:41 +08:00
|
|
|
disk_bytenr = em->block_start + extent_offset;
|
|
|
|
|
2021-05-31 16:50:50 +08:00
|
|
|
/*
|
|
|
|
* Note that em_end from extent_map_end() and dirty_range_end from
|
|
|
|
* find_next_dirty_byte() are all exclusive
|
|
|
|
*/
|
|
|
|
iosize = min(min(em_end, end + 1), dirty_range_end) - cur;
|
2021-02-04 18:22:05 +08:00
|
|
|
|
2021-05-18 23:40:27 +08:00
|
|
|
if (btrfs_use_zone_append(inode, em->block_start))
|
2022-07-15 02:07:16 +08:00
|
|
|
op = REQ_OP_ZONE_APPEND;
|
2021-02-04 18:22:05 +08:00
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
free_extent_map(em);
|
|
|
|
em = NULL;
|
|
|
|
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
/*
|
|
|
|
* compressed and inline extents are written through other
|
|
|
|
* paths in the FS
|
|
|
|
*/
|
|
|
|
if (compressed || block_start == EXTENT_MAP_HOLE ||
|
2008-01-25 05:13:08 +08:00
|
|
|
block_start == EXTENT_MAP_INLINE) {
|
2019-12-03 09:34:24 +08:00
|
|
|
if (compressed)
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
nr++;
|
2019-12-03 09:34:24 +08:00
|
|
|
else
|
2021-04-08 20:32:27 +08:00
|
|
|
btrfs_writepage_endio_finish_ordered(inode,
|
2021-07-26 20:15:08 +08:00
|
|
|
page, cur, cur + iosize - 1, true);
|
btrfs: subpage: fix writeback which does not have ordered extent
[BUG]
When running fsstress with subpage RW support, there are random
BUG_ON()s triggered with the following trace:
kernel BUG at fs/btrfs/file-item.c:667!
Internal error: Oops - BUG: 0 [#1] SMP
CPU: 1 PID: 3486 Comm: kworker/u13:2 5.11.0-rc4-custom+ #43
Hardware name: Radxa ROCK Pi 4B (DT)
Workqueue: btrfs-worker-high btrfs_work_helper [btrfs]
pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--)
pc : btrfs_csum_one_bio+0x420/0x4e0 [btrfs]
lr : btrfs_csum_one_bio+0x400/0x4e0 [btrfs]
Call trace:
btrfs_csum_one_bio+0x420/0x4e0 [btrfs]
btrfs_submit_bio_start+0x20/0x30 [btrfs]
run_one_async_start+0x28/0x44 [btrfs]
btrfs_work_helper+0x128/0x1b4 [btrfs]
process_one_work+0x22c/0x430
worker_thread+0x70/0x3a0
kthread+0x13c/0x140
ret_from_fork+0x10/0x30
[CAUSE]
Above BUG_ON() means there is some bio range which doesn't have ordered
extent, which indeed is worth a BUG_ON().
Unlike regular sectorsize == PAGE_SIZE case, in subpage we have extra
subpage dirty bitmap to record which range is dirty and should be
written back.
This means, if we submit bio for a subpage range, we do not only need to
clear page dirty, but also need to clear subpage dirty bits.
In __extent_writepage_io(), we will call btrfs_page_clear_dirty() for
any range we submit a bio.
But there is loophole, if we hit a range which is beyond i_size, we just
call btrfs_writepage_endio_finish_ordered() to finish the ordered io,
then break out, without clearing the subpage dirty.
This means, if we hit above branch, the subpage dirty bits are still
there, if other range of the page get dirtied and we need to writeback
that page again, we will submit bio for the old range, leaving a wild
bio range which doesn't have ordered extent.
[FIX]
Fix it by always calling btrfs_page_clear_dirty() in
__extent_writepage_io().
Also to avoid such problem from happening again, add a new assert,
btrfs_page_assert_not_dirty(), to make sure both page dirty and subpage
dirty bits are cleared before exiting __extent_writepage_io().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:58 +08:00
|
|
|
btrfs_page_clear_dirty(fs_info, page, cur, iosize);
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
cur += iosize;
|
2008-01-25 05:13:08 +08:00
|
|
|
continue;
|
|
|
|
}
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
|
2021-05-31 16:50:49 +08:00
|
|
|
btrfs_set_range_writeback(inode, cur, cur + iosize - 1);
|
2016-05-04 17:46:10 +08:00
|
|
|
if (!PageWriteback(page)) {
|
2020-06-03 13:55:33 +08:00
|
|
|
btrfs_err(inode->root->fs_info,
|
2016-05-04 17:46:10 +08:00
|
|
|
"page %lu not writeback, cur %llu end %llu",
|
|
|
|
page->index, cur, end);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
2008-07-19 00:01:11 +08:00
|
|
|
|
2021-05-31 16:50:50 +08:00
|
|
|
/*
|
|
|
|
* Although the PageDirty bit is cleared before entering this
|
|
|
|
* function, subpage dirty bit is not cleared.
|
|
|
|
* So clear subpage dirty bit here so next time we won't submit
|
|
|
|
* page for range already written to disk.
|
|
|
|
*/
|
|
|
|
btrfs_page_clear_dirty(fs_info, page, cur, iosize);
|
|
|
|
|
2022-07-15 02:07:16 +08:00
|
|
|
ret = submit_extent_page(op | write_flags, wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
bio_ctrl, disk_bytenr,
|
btrfs: switch page and disk_bytenr argument position for submit_extent_page()
Normally we put (page, pg_len, pg_offset) arguments together, just like
what __bio_add_page() does.
But in submit_extent_page(), what we got is, (page, disk_bytenr, pg_len,
pg_offset), which sometimes can be confusing.
Change the order to (disk_bytenr, page, pg_len, pg_offset) to make it
to follow the common schema.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-13 13:31:13 +08:00
|
|
|
page, iosize,
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
cur - page_offset(page),
|
2022-06-03 15:11:03 +08:00
|
|
|
0, false);
|
Btrfs: add another missing end_page_writeback on submit_extent_page failure
If btrfs_bio_alloc fails in submit_extent_page, submit_extent_page returns
without clearing the writeback bit of the failed page.
__extent_writepage_io, that is a caller of submit_extent_page,
does not clear the remaining writeback bit anywhere.
As a result, this will cause the hang at filemap_fdatawait_range,
because it waits the writeback bit to be cleared from the failed page.
So, we have to call end_page_writeback to clear the writeback bit.
For reproducing the hang, we inject a fault like
if (should_failtest()) { // I define should_failtest()
bio = NULL;
}
else {
bio = btrfs_bio_alloc(...);
}
in submit_extent_page.
We should also check whether page has the bit before end_page_writeback,
to avoid the conflict against the other end_page_writeback in bio_endio.
Thus, we add PageWriteback checks not only in __extent_writepage_io,
but also in write_one_eb too, because it misses the check.
Signed-off-by: Takafumi Kubota <takafumi.kubota1012@sslab.ics.keio.ac.jp>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Cc: David Sterba <dsterba@suse.cz>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-02-09 16:24:33 +08:00
|
|
|
if (ret) {
|
btrfs: return correct error number for __extent_writepage_io()
[BUG]
If we hit an error from submit_extent_page() inside
__extent_writepage_io(), we could still return 0 to the caller, and
even trigger the warning in btrfs_page_assert_not_dirty().
[CAUSE]
In __extent_writepage_io(), if we hit an error from
submit_extent_page(), we will just clean up the range and continue.
This is completely fine for regular PAGE_SIZE == sectorsize, as we can
only hit one sector in one page, thus after the error we're ensured to
exit and @ret will be saved.
But for subpage case, we may have other dirty subpage range in the page,
and in the next loop, we may succeeded submitting the next range.
In that case, @ret will be overwritten, and we return 0 to the caller,
while we have hit some error.
[FIX]
Introduce @has_error and @saved_ret to record the first error we hit, so
we will never forget what error we hit.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:15 +08:00
|
|
|
has_error = true;
|
|
|
|
if (!saved_ret)
|
|
|
|
saved_ret = ret;
|
|
|
|
|
2021-05-31 16:50:50 +08:00
|
|
|
btrfs_page_set_error(fs_info, page, cur, iosize);
|
Btrfs: add another missing end_page_writeback on submit_extent_page failure
If btrfs_bio_alloc fails in submit_extent_page, submit_extent_page returns
without clearing the writeback bit of the failed page.
__extent_writepage_io, that is a caller of submit_extent_page,
does not clear the remaining writeback bit anywhere.
As a result, this will cause the hang at filemap_fdatawait_range,
because it waits the writeback bit to be cleared from the failed page.
So, we have to call end_page_writeback to clear the writeback bit.
For reproducing the hang, we inject a fault like
if (should_failtest()) { // I define should_failtest()
bio = NULL;
}
else {
bio = btrfs_bio_alloc(...);
}
in submit_extent_page.
We should also check whether page has the bit before end_page_writeback,
to avoid the conflict against the other end_page_writeback in bio_endio.
Thus, we add PageWriteback checks not only in __extent_writepage_io,
but also in write_one_eb too, because it misses the check.
Signed-off-by: Takafumi Kubota <takafumi.kubota1012@sslab.ics.keio.ac.jp>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Cc: David Sterba <dsterba@suse.cz>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-02-09 16:24:33 +08:00
|
|
|
if (PageWriteback(page))
|
2021-05-31 16:50:50 +08:00
|
|
|
btrfs_page_clear_writeback(fs_info, page, cur,
|
|
|
|
iosize);
|
Btrfs: add another missing end_page_writeback on submit_extent_page failure
If btrfs_bio_alloc fails in submit_extent_page, submit_extent_page returns
without clearing the writeback bit of the failed page.
__extent_writepage_io, that is a caller of submit_extent_page,
does not clear the remaining writeback bit anywhere.
As a result, this will cause the hang at filemap_fdatawait_range,
because it waits the writeback bit to be cleared from the failed page.
So, we have to call end_page_writeback to clear the writeback bit.
For reproducing the hang, we inject a fault like
if (should_failtest()) { // I define should_failtest()
bio = NULL;
}
else {
bio = btrfs_bio_alloc(...);
}
in submit_extent_page.
We should also check whether page has the bit before end_page_writeback,
to avoid the conflict against the other end_page_writeback in bio_endio.
Thus, we add PageWriteback checks not only in __extent_writepage_io,
but also in write_one_eb too, because it misses the check.
Signed-off-by: Takafumi Kubota <takafumi.kubota1012@sslab.ics.keio.ac.jp>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Cc: David Sterba <dsterba@suse.cz>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-02-09 16:24:33 +08:00
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2021-01-06 09:01:41 +08:00
|
|
|
cur += iosize;
|
2008-01-25 05:13:08 +08:00
|
|
|
nr++;
|
|
|
|
}
|
btrfs: subpage: fix writeback which does not have ordered extent
[BUG]
When running fsstress with subpage RW support, there are random
BUG_ON()s triggered with the following trace:
kernel BUG at fs/btrfs/file-item.c:667!
Internal error: Oops - BUG: 0 [#1] SMP
CPU: 1 PID: 3486 Comm: kworker/u13:2 5.11.0-rc4-custom+ #43
Hardware name: Radxa ROCK Pi 4B (DT)
Workqueue: btrfs-worker-high btrfs_work_helper [btrfs]
pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--)
pc : btrfs_csum_one_bio+0x420/0x4e0 [btrfs]
lr : btrfs_csum_one_bio+0x400/0x4e0 [btrfs]
Call trace:
btrfs_csum_one_bio+0x420/0x4e0 [btrfs]
btrfs_submit_bio_start+0x20/0x30 [btrfs]
run_one_async_start+0x28/0x44 [btrfs]
btrfs_work_helper+0x128/0x1b4 [btrfs]
process_one_work+0x22c/0x430
worker_thread+0x70/0x3a0
kthread+0x13c/0x140
ret_from_fork+0x10/0x30
[CAUSE]
Above BUG_ON() means there is some bio range which doesn't have ordered
extent, which indeed is worth a BUG_ON().
Unlike regular sectorsize == PAGE_SIZE case, in subpage we have extra
subpage dirty bitmap to record which range is dirty and should be
written back.
This means, if we submit bio for a subpage range, we do not only need to
clear page dirty, but also need to clear subpage dirty bits.
In __extent_writepage_io(), we will call btrfs_page_clear_dirty() for
any range we submit a bio.
But there is loophole, if we hit a range which is beyond i_size, we just
call btrfs_writepage_endio_finish_ordered() to finish the ordered io,
then break out, without clearing the subpage dirty.
This means, if we hit above branch, the subpage dirty bits are still
there, if other range of the page get dirtied and we need to writeback
that page again, we will submit bio for the old range, leaving a wild
bio range which doesn't have ordered extent.
[FIX]
Fix it by always calling btrfs_page_clear_dirty() in
__extent_writepage_io().
Also to avoid such problem from happening again, add a new assert,
btrfs_page_assert_not_dirty(), to make sure both page dirty and subpage
dirty bits are cleared before exiting __extent_writepage_io().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:58 +08:00
|
|
|
/*
|
|
|
|
* If we finish without problem, we should not only clear page dirty,
|
|
|
|
* but also empty subpage dirty bits
|
|
|
|
*/
|
btrfs: return correct error number for __extent_writepage_io()
[BUG]
If we hit an error from submit_extent_page() inside
__extent_writepage_io(), we could still return 0 to the caller, and
even trigger the warning in btrfs_page_assert_not_dirty().
[CAUSE]
In __extent_writepage_io(), if we hit an error from
submit_extent_page(), we will just clean up the range and continue.
This is completely fine for regular PAGE_SIZE == sectorsize, as we can
only hit one sector in one page, thus after the error we're ensured to
exit and @ret will be saved.
But for subpage case, we may have other dirty subpage range in the page,
and in the next loop, we may succeeded submitting the next range.
In that case, @ret will be overwritten, and we return 0 to the caller,
while we have hit some error.
[FIX]
Introduce @has_error and @saved_ret to record the first error we hit, so
we will never forget what error we hit.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:15 +08:00
|
|
|
if (!has_error)
|
btrfs: subpage: fix writeback which does not have ordered extent
[BUG]
When running fsstress with subpage RW support, there are random
BUG_ON()s triggered with the following trace:
kernel BUG at fs/btrfs/file-item.c:667!
Internal error: Oops - BUG: 0 [#1] SMP
CPU: 1 PID: 3486 Comm: kworker/u13:2 5.11.0-rc4-custom+ #43
Hardware name: Radxa ROCK Pi 4B (DT)
Workqueue: btrfs-worker-high btrfs_work_helper [btrfs]
pstate: 60000005 (nZCv daif -PAN -UAO -TCO BTYPE=--)
pc : btrfs_csum_one_bio+0x420/0x4e0 [btrfs]
lr : btrfs_csum_one_bio+0x400/0x4e0 [btrfs]
Call trace:
btrfs_csum_one_bio+0x420/0x4e0 [btrfs]
btrfs_submit_bio_start+0x20/0x30 [btrfs]
run_one_async_start+0x28/0x44 [btrfs]
btrfs_work_helper+0x128/0x1b4 [btrfs]
process_one_work+0x22c/0x430
worker_thread+0x70/0x3a0
kthread+0x13c/0x140
ret_from_fork+0x10/0x30
[CAUSE]
Above BUG_ON() means there is some bio range which doesn't have ordered
extent, which indeed is worth a BUG_ON().
Unlike regular sectorsize == PAGE_SIZE case, in subpage we have extra
subpage dirty bitmap to record which range is dirty and should be
written back.
This means, if we submit bio for a subpage range, we do not only need to
clear page dirty, but also need to clear subpage dirty bits.
In __extent_writepage_io(), we will call btrfs_page_clear_dirty() for
any range we submit a bio.
But there is loophole, if we hit a range which is beyond i_size, we just
call btrfs_writepage_endio_finish_ordered() to finish the ordered io,
then break out, without clearing the subpage dirty.
This means, if we hit above branch, the subpage dirty bits are still
there, if other range of the page get dirtied and we need to writeback
that page again, we will submit bio for the old range, leaving a wild
bio range which doesn't have ordered extent.
[FIX]
Fix it by always calling btrfs_page_clear_dirty() in
__extent_writepage_io().
Also to avoid such problem from happening again, add a new assert,
btrfs_page_assert_not_dirty(), to make sure both page dirty and subpage
dirty bits are cleared before exiting __extent_writepage_io().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:34:58 +08:00
|
|
|
btrfs_page_assert_not_dirty(fs_info, page);
|
btrfs: return correct error number for __extent_writepage_io()
[BUG]
If we hit an error from submit_extent_page() inside
__extent_writepage_io(), we could still return 0 to the caller, and
even trigger the warning in btrfs_page_assert_not_dirty().
[CAUSE]
In __extent_writepage_io(), if we hit an error from
submit_extent_page(), we will just clean up the range and continue.
This is completely fine for regular PAGE_SIZE == sectorsize, as we can
only hit one sector in one page, thus after the error we're ensured to
exit and @ret will be saved.
But for subpage case, we may have other dirty subpage range in the page,
and in the next loop, we may succeeded submitting the next range.
In that case, @ret will be overwritten, and we return 0 to the caller,
while we have hit some error.
[FIX]
Introduce @has_error and @saved_ret to record the first error we hit, so
we will never forget what error we hit.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:15 +08:00
|
|
|
else
|
|
|
|
ret = saved_ret;
|
2014-05-22 04:35:51 +08:00
|
|
|
*nr_ret = nr;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* the writepage semantics are similar to regular writepage. extent
|
|
|
|
* records are inserted to lock ranges in the tree, and as dirty areas
|
|
|
|
* are found, they are marked writeback. Then the lock bits are removed
|
|
|
|
* and the end_io handler clears the writeback ranges
|
2019-03-20 14:27:42 +08:00
|
|
|
*
|
|
|
|
* Return 0 if everything goes well.
|
|
|
|
* Return <0 for error.
|
2014-05-22 04:35:51 +08:00
|
|
|
*/
|
|
|
|
static int __extent_writepage(struct page *page, struct writeback_control *wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl)
|
2014-05-22 04:35:51 +08:00
|
|
|
{
|
2022-02-10 04:21:29 +08:00
|
|
|
struct folio *folio = page_folio(page);
|
2014-05-22 04:35:51 +08:00
|
|
|
struct inode *inode = page->mapping->host;
|
2021-09-27 15:22:05 +08:00
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
|
2021-09-27 15:21:44 +08:00
|
|
|
const u64 page_start = page_offset(page);
|
|
|
|
const u64 page_end = page_start + PAGE_SIZE - 1;
|
2014-05-22 04:35:51 +08:00
|
|
|
int ret;
|
|
|
|
int nr = 0;
|
2019-12-03 09:34:20 +08:00
|
|
|
size_t pg_offset;
|
2014-05-22 04:35:51 +08:00
|
|
|
loff_t i_size = i_size_read(inode);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
unsigned long end_index = i_size >> PAGE_SHIFT;
|
2014-05-22 04:35:51 +08:00
|
|
|
|
|
|
|
trace___extent_writepage(page, inode, wbc);
|
|
|
|
|
|
|
|
WARN_ON(!PageLocked(page));
|
|
|
|
|
btrfs: unify regular and subpage error paths in __extent_writepage()
[BUG]
When running btrfs/160 in a loop for subpage with experimental
compression support, it has a high chance to crash (~20%):
BTRFS critical (device dm-7): panic in __btrfs_add_ordered_extent:238: inconsistency in ordered tree at offset 0 (errno=-17 Object already exists)
------------[ cut here ]------------
kernel BUG at fs/btrfs/ordered-data.c:238!
Internal error: Oops - BUG: 0 [#1] SMP
pc : __btrfs_add_ordered_extent+0x550/0x670 [btrfs]
lr : __btrfs_add_ordered_extent+0x550/0x670 [btrfs]
Call trace:
__btrfs_add_ordered_extent+0x550/0x670 [btrfs]
btrfs_add_ordered_extent+0x2c/0x50 [btrfs]
run_delalloc_nocow+0x81c/0x8fc [btrfs]
btrfs_run_delalloc_range+0xa4/0x390 [btrfs]
writepage_delalloc+0xc0/0x1ac [btrfs]
__extent_writepage+0xf4/0x370 [btrfs]
extent_write_cache_pages+0x288/0x4f4 [btrfs]
extent_writepages+0x58/0xe0 [btrfs]
btrfs_writepages+0x1c/0x30 [btrfs]
do_writepages+0x60/0x110
__filemap_fdatawrite_range+0x108/0x170
filemap_fdatawrite_range+0x20/0x30
btrfs_fdatawrite_range+0x34/0x4dc [btrfs]
__btrfs_write_out_cache+0x34c/0x480 [btrfs]
btrfs_write_out_cache+0x144/0x220 [btrfs]
btrfs_start_dirty_block_groups+0x3ac/0x6b0 [btrfs]
btrfs_commit_transaction+0xd0/0xbb4 [btrfs]
btrfs_sync_fs+0x64/0x1cc [btrfs]
sync_fs_one_sb+0x3c/0x50
iterate_supers+0xcc/0x1d4
ksys_sync+0x6c/0xd0
__arm64_sys_sync+0x1c/0x30
invoke_syscall+0x50/0x120
el0_svc_common.constprop.0+0x4c/0xd4
do_el0_svc+0x30/0x9c
el0_svc+0x2c/0x54
el0_sync_handler+0x1a8/0x1b0
el0_sync+0x198/0x1c0
---[ end trace 336f67369ae6e0af ]---
[CAUSE]
For subpage case, we can have multiple sectors inside a page, this makes
it possible for __extent_writepage() to have part of its page submitted
before returning.
In btrfs/160, we are using dm-dust to emulate write error, this means
for certain pages, we could have everything running fine, but at the end
of __extent_writepage(), one of the submitted bios fails due to dm-dust.
Then the page is marked Error, and we change @ret from 0 to -EIO.
This makes the caller extent_write_cache_pages() to error out, without
submitting the remaining pages.
Furthermore, since we're erroring out for free space cache, it doesn't
really care about the error and will update the inode and retry the
writeback.
Then we re-run the delalloc range, and will try to insert the same
delalloc range while previous delalloc range is still hanging there,
triggering the above error.
[FIX]
The proper fix is to handle errors from __extent_writepage() properly,
by ending the remaining ordered extent.
But that fix needs the following changes:
- Know at exactly which sector the error happened
Currently __extent_writepage_io() works for the full page, can't
return at which sector we hit the error.
- Grab the ordered extent covering the failed sector
As a hotfix for subpage case, here we unify the error paths in
__extent_writepage().
In fact, the "if (PageError(page))" branch never get executed if @ret is
still 0 for non-subpage cases.
As for non-subpage case, we never submit current page in
__extent_writepage(), but only add current page into bio.
The bio can only get submitted in next page.
Thus we never get PageError() set due to IO failure, thus when we hit
the branch, @ret is never 0.
By simply removing that @ret assignment, we let subpage case ignore the
IO failure, thus only error out for fatal errors just like regular
sectorsize.
So that IO error won't be treated as fatal error not trigger the hanging
OE problem.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:07 +08:00
|
|
|
btrfs_page_clear_error(btrfs_sb(inode->i_sb), page,
|
|
|
|
page_offset(page), PAGE_SIZE);
|
2014-05-22 04:35:51 +08:00
|
|
|
|
2018-12-05 22:23:03 +08:00
|
|
|
pg_offset = offset_in_page(i_size);
|
2014-05-22 04:35:51 +08:00
|
|
|
if (page->index > end_index ||
|
|
|
|
(page->index == end_index && !pg_offset)) {
|
2022-02-10 04:21:29 +08:00
|
|
|
folio_invalidate(folio, 0, folio_size(folio));
|
|
|
|
folio_unlock(folio);
|
2014-05-22 04:35:51 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2022-06-01 19:47:54 +08:00
|
|
|
if (page->index == end_index)
|
btrfs: use memzero_page() instead of open coded kmap pattern
There are many places where kmap/memset/kunmap patterns occur.
Use the newly lifted memzero_page() to eliminate direct uses of kmap and
leverage the new core functions use of kmap_local_page().
The development of this patch was aided by the following coccinelle
script:
// <smpl>
// SPDX-License-Identifier: GPL-2.0-only
// Find kmap/memset/kunmap pattern and replace with memset*page calls
//
// NOTE: Offsets and other expressions may be more complex than what the script
// will automatically generate. Therefore a catchall rule is provided to find
// the pattern which then must be evaluated by hand.
//
// Confidence: Low
// Copyright: (C) 2021 Intel Corporation
// URL: http://coccinelle.lip6.fr/
// Comments:
// Options:
//
// Then the memset pattern
//
@ memset_rule1 @
expression page, V, L, Off;
identifier ptr;
type VP;
@@
(
-VP ptr = kmap(page);
|
-ptr = kmap(page);
|
-VP ptr = kmap_atomic(page);
|
-ptr = kmap_atomic(page);
)
<+...
(
-memset(ptr, 0, L);
+memzero_page(page, 0, L);
|
-memset(ptr + Off, 0, L);
+memzero_page(page, Off, L);
|
-memset(ptr, V, L);
+memset_page(page, V, 0, L);
|
-memset(ptr + Off, V, L);
+memset_page(page, V, Off, L);
)
...+>
(
-kunmap(page);
|
-kunmap_atomic(ptr);
)
// Remove any pointers left unused
@
depends on memset_rule1
@
identifier memset_rule1.ptr;
type VP, VP1;
@@
-VP ptr;
... when != ptr;
? VP1 ptr;
//
// Catch all
//
@ memset_rule2 @
expression page;
identifier ptr;
expression GenTo, GenSize, GenValue;
type VP;
@@
(
-VP ptr = kmap(page);
|
-ptr = kmap(page);
|
-VP ptr = kmap_atomic(page);
|
-ptr = kmap_atomic(page);
)
<+...
(
//
// Some call sites have complex expressions within the memset/memcpy
// The follow are catch alls which need to be evaluated by hand.
//
-memset(GenTo, 0, GenSize);
+memzero_pageExtra(page, GenTo, GenSize);
|
-memset(GenTo, GenValue, GenSize);
+memset_pageExtra(page, GenValue, GenTo, GenSize);
)
...+>
(
-kunmap(page);
|
-kunmap_atomic(ptr);
)
// Remove any pointers left unused
@
depends on memset_rule2
@
identifier memset_rule2.ptr;
type VP, VP1;
@@
-VP ptr;
... when != ptr;
? VP1 ptr;
// </smpl>
Link: https://lkml.kernel.org/r/20210309212137.2610186-4-ira.weiny@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 09:40:07 +08:00
|
|
|
memzero_page(page, pg_offset, PAGE_SIZE - pg_offset);
|
2014-05-22 04:35:51 +08:00
|
|
|
|
2021-01-26 16:34:00 +08:00
|
|
|
ret = set_page_extent_mapped(page);
|
|
|
|
if (ret < 0) {
|
|
|
|
SetPageError(page);
|
|
|
|
goto done;
|
|
|
|
}
|
2014-05-22 04:35:51 +08:00
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
if (!bio_ctrl->extent_locked) {
|
btrfs: remove unnecessary @nr_written parameters
We use @nr_written to record how many pages have been started by
btrfs_run_delalloc_range().
Currently there are only two cases that would populate @nr_written:
- Inline extent creation
- Compressed write
But both cases will also set @page_started to one.
In fact, in writepage_delalloc() we have the following code, showing
that @nr_written is really only utilized for above two cases:
/* did the fill delalloc function already unlock and start
* the IO?
*/
if (page_started) {
/*
* we've unlocked the page, so we can't update
* the mapping's writeback index, just update
* nr_to_write.
*/
wbc->nr_to_write -= nr_written;
return 1;
}
But for such cases, writepage_delalloc() will return 1, and exit
__extent_writepage() without going through __extent_writepage_io().
Thus this means, inside __extent_writepage_io(), we always get
@nr_written as 0.
So this patch is going to remove the unnecessary parameter from the
following functions:
- writepage_delalloc()
As @nr_written passed in is always the initial value 0.
Although inside that function, we still need a local @nr_written
to update wbc->nr_to_write.
- __extent_writepage_io()
As explained above, @nr_written passed in can only be 0.
This also means we can remove one update_nr_written() call.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-11-12 13:33:14 +08:00
|
|
|
ret = writepage_delalloc(BTRFS_I(inode), page, wbc);
|
2018-11-08 16:18:06 +08:00
|
|
|
if (ret == 1)
|
2019-12-03 09:34:21 +08:00
|
|
|
return 0;
|
2018-11-08 16:18:06 +08:00
|
|
|
if (ret)
|
|
|
|
goto done;
|
|
|
|
}
|
2014-05-22 04:35:51 +08:00
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = __extent_writepage_io(BTRFS_I(inode), page, wbc, bio_ctrl, i_size,
|
btrfs: remove unnecessary @nr_written parameters
We use @nr_written to record how many pages have been started by
btrfs_run_delalloc_range().
Currently there are only two cases that would populate @nr_written:
- Inline extent creation
- Compressed write
But both cases will also set @page_started to one.
In fact, in writepage_delalloc() we have the following code, showing
that @nr_written is really only utilized for above two cases:
/* did the fill delalloc function already unlock and start
* the IO?
*/
if (page_started) {
/*
* we've unlocked the page, so we can't update
* the mapping's writeback index, just update
* nr_to_write.
*/
wbc->nr_to_write -= nr_written;
return 1;
}
But for such cases, writepage_delalloc() will return 1, and exit
__extent_writepage() without going through __extent_writepage_io().
Thus this means, inside __extent_writepage_io(), we always get
@nr_written as 0.
So this patch is going to remove the unnecessary parameter from the
following functions:
- writepage_delalloc()
As @nr_written passed in is always the initial value 0.
Although inside that function, we still need a local @nr_written
to update wbc->nr_to_write.
- __extent_writepage_io()
As explained above, @nr_written passed in can only be 0.
This also means we can remove one update_nr_written() call.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-11-12 13:33:14 +08:00
|
|
|
&nr);
|
2014-05-22 04:35:51 +08:00
|
|
|
if (ret == 1)
|
2019-12-03 09:34:21 +08:00
|
|
|
return 0;
|
2014-05-22 04:35:51 +08:00
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
done:
|
|
|
|
if (nr == 0) {
|
|
|
|
/* make sure the mapping tag for page dirty gets cleared */
|
|
|
|
set_page_writeback(page);
|
|
|
|
end_page_writeback(page);
|
|
|
|
}
|
btrfs: unify regular and subpage error paths in __extent_writepage()
[BUG]
When running btrfs/160 in a loop for subpage with experimental
compression support, it has a high chance to crash (~20%):
BTRFS critical (device dm-7): panic in __btrfs_add_ordered_extent:238: inconsistency in ordered tree at offset 0 (errno=-17 Object already exists)
------------[ cut here ]------------
kernel BUG at fs/btrfs/ordered-data.c:238!
Internal error: Oops - BUG: 0 [#1] SMP
pc : __btrfs_add_ordered_extent+0x550/0x670 [btrfs]
lr : __btrfs_add_ordered_extent+0x550/0x670 [btrfs]
Call trace:
__btrfs_add_ordered_extent+0x550/0x670 [btrfs]
btrfs_add_ordered_extent+0x2c/0x50 [btrfs]
run_delalloc_nocow+0x81c/0x8fc [btrfs]
btrfs_run_delalloc_range+0xa4/0x390 [btrfs]
writepage_delalloc+0xc0/0x1ac [btrfs]
__extent_writepage+0xf4/0x370 [btrfs]
extent_write_cache_pages+0x288/0x4f4 [btrfs]
extent_writepages+0x58/0xe0 [btrfs]
btrfs_writepages+0x1c/0x30 [btrfs]
do_writepages+0x60/0x110
__filemap_fdatawrite_range+0x108/0x170
filemap_fdatawrite_range+0x20/0x30
btrfs_fdatawrite_range+0x34/0x4dc [btrfs]
__btrfs_write_out_cache+0x34c/0x480 [btrfs]
btrfs_write_out_cache+0x144/0x220 [btrfs]
btrfs_start_dirty_block_groups+0x3ac/0x6b0 [btrfs]
btrfs_commit_transaction+0xd0/0xbb4 [btrfs]
btrfs_sync_fs+0x64/0x1cc [btrfs]
sync_fs_one_sb+0x3c/0x50
iterate_supers+0xcc/0x1d4
ksys_sync+0x6c/0xd0
__arm64_sys_sync+0x1c/0x30
invoke_syscall+0x50/0x120
el0_svc_common.constprop.0+0x4c/0xd4
do_el0_svc+0x30/0x9c
el0_svc+0x2c/0x54
el0_sync_handler+0x1a8/0x1b0
el0_sync+0x198/0x1c0
---[ end trace 336f67369ae6e0af ]---
[CAUSE]
For subpage case, we can have multiple sectors inside a page, this makes
it possible for __extent_writepage() to have part of its page submitted
before returning.
In btrfs/160, we are using dm-dust to emulate write error, this means
for certain pages, we could have everything running fine, but at the end
of __extent_writepage(), one of the submitted bios fails due to dm-dust.
Then the page is marked Error, and we change @ret from 0 to -EIO.
This makes the caller extent_write_cache_pages() to error out, without
submitting the remaining pages.
Furthermore, since we're erroring out for free space cache, it doesn't
really care about the error and will update the inode and retry the
writeback.
Then we re-run the delalloc range, and will try to insert the same
delalloc range while previous delalloc range is still hanging there,
triggering the above error.
[FIX]
The proper fix is to handle errors from __extent_writepage() properly,
by ending the remaining ordered extent.
But that fix needs the following changes:
- Know at exactly which sector the error happened
Currently __extent_writepage_io() works for the full page, can't
return at which sector we hit the error.
- Grab the ordered extent covering the failed sector
As a hotfix for subpage case, here we unify the error paths in
__extent_writepage().
In fact, the "if (PageError(page))" branch never get executed if @ret is
still 0 for non-subpage cases.
As for non-subpage case, we never submit current page in
__extent_writepage(), but only add current page into bio.
The bio can only get submitted in next page.
Thus we never get PageError() set due to IO failure, thus when we hit
the branch, @ret is never 0.
By simply removing that @ret assignment, we let subpage case ignore the
IO failure, thus only error out for fatal errors just like regular
sectorsize.
So that IO error won't be treated as fatal error not trigger the hanging
OE problem.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-26 14:35:07 +08:00
|
|
|
/*
|
|
|
|
* Here we used to have a check for PageError() and then set @ret and
|
|
|
|
* call end_extent_writepage().
|
|
|
|
*
|
|
|
|
* But in fact setting @ret here will cause different error paths
|
|
|
|
* between subpage and regular sectorsize.
|
|
|
|
*
|
|
|
|
* For regular page size, we never submit current page, but only add
|
|
|
|
* current page to current bio.
|
|
|
|
* The bio submission can only happen in next page.
|
|
|
|
* Thus if we hit the PageError() branch, @ret is already set to
|
|
|
|
* non-zero value and will not get updated for regular sectorsize.
|
|
|
|
*
|
|
|
|
* But for subpage case, it's possible we submit part of current page,
|
|
|
|
* thus can get PageError() set by submitted bio of the same page,
|
|
|
|
* while our @ret is still 0.
|
|
|
|
*
|
|
|
|
* So here we unify the behavior and don't set @ret.
|
|
|
|
* Error can still be properly passed to higher layer as page will
|
|
|
|
* be set error, here we just don't handle the IO failure.
|
|
|
|
*
|
|
|
|
* NOTE: This is just a hotfix for subpage.
|
|
|
|
* The root fix will be properly ending ordered extent when we hit
|
|
|
|
* an error during writeback.
|
|
|
|
*
|
|
|
|
* But that needs a bigger refactoring, as we not only need to grab the
|
|
|
|
* submitted OE, but also need to know exactly at which bytenr we hit
|
|
|
|
* the error.
|
|
|
|
* Currently the full page based __extent_writepage_io() is not
|
|
|
|
* capable of that.
|
|
|
|
*/
|
|
|
|
if (PageError(page))
|
2021-09-27 15:21:44 +08:00
|
|
|
end_extent_writepage(page, ret, page_start, page_end);
|
2022-10-27 19:07:05 +08:00
|
|
|
if (bio_ctrl->extent_locked) {
|
2021-09-27 15:22:05 +08:00
|
|
|
/*
|
2022-10-27 19:07:05 +08:00
|
|
|
* If bio_ctrl->extent_locked, it's from extent_write_locked_range(),
|
2021-09-27 15:22:05 +08:00
|
|
|
* the page can either be locked by lock_page() or
|
|
|
|
* process_one_page().
|
|
|
|
* Let btrfs_page_unlock_writer() handle both cases.
|
|
|
|
*/
|
|
|
|
ASSERT(wbc);
|
|
|
|
btrfs_page_unlock_writer(fs_info, page, wbc->range_start,
|
|
|
|
wbc->range_end + 1 - wbc->range_start);
|
|
|
|
} else {
|
|
|
|
unlock_page(page);
|
|
|
|
}
|
2019-03-20 14:27:42 +08:00
|
|
|
ASSERT(ret <= 0);
|
2014-05-22 04:35:51 +08:00
|
|
|
return ret;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2013-04-25 04:41:19 +08:00
|
|
|
void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
|
2012-03-13 21:38:00 +08:00
|
|
|
{
|
sched: Remove proliferation of wait_on_bit() action functions
The current "wait_on_bit" interface requires an 'action'
function to be provided which does the actual waiting.
There are over 20 such functions, many of them identical.
Most cases can be satisfied by one of just two functions, one
which uses io_schedule() and one which just uses schedule().
So:
Rename wait_on_bit and wait_on_bit_lock to
wait_on_bit_action and wait_on_bit_lock_action
to make it explicit that they need an action function.
Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io
which are *not* given an action function but implicitly use
a standard one.
The decision to error-out if a signal is pending is now made
based on the 'mode' argument rather than being encoded in the action
function.
All instances of the old wait_on_bit and wait_on_bit_lock which
can use the new version have been changed accordingly and their
action functions have been discarded.
wait_on_bit{_lock} does not return any specific error code in the
event of a signal so the caller must check for non-zero and
interpolate their own error code as appropriate.
The wait_on_bit() call in __fscache_wait_on_invalidate() was
ambiguous as it specified TASK_UNINTERRUPTIBLE but used
fscache_wait_bit_interruptible as an action function.
David Howells confirms this should be uniformly
"uninterruptible"
The main remaining user of wait_on_bit{,_lock}_action is NFS
which needs to use a freezer-aware schedule() call.
A comment in fs/gfs2/glock.c notes that having multiple 'action'
functions is useful as they display differently in the 'wchan'
field of 'ps'. (and /proc/$PID/wchan).
As the new bit_wait{,_io} functions are tagged "__sched", they
will not show up at all, but something higher in the stack. So
the distinction will still be visible, only with different
function names (gds2_glock_wait versus gfs2_glock_dq_wait in the
gfs2/glock.c case).
Since first version of this patch (against 3.15) two new action
functions appeared, on in NFS and one in CIFS. CIFS also now
uses an action function that makes the same freezer aware
schedule call as NFS.
Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: David Howells <dhowells@redhat.com> (fscache, keys)
Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2)
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steve French <sfrench@samba.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 13:16:04 +08:00
|
|
|
wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK,
|
|
|
|
TASK_UNINTERRUPTIBLE);
|
2012-03-13 21:38:00 +08:00
|
|
|
}
|
|
|
|
|
Btrfs: fix unwritten extent buffers and hangs on future writeback attempts
The lock_extent_buffer_io() returns 1 to the caller to tell it everything
went fine and the callers needs to start writeback for the extent buffer
(submit a bio, etc), 0 to tell the caller everything went fine but it does
not need to start writeback for the extent buffer, and a negative value if
some error happened.
When it's about to return 1 it tries to lock all pages, and if a try lock
on a page fails, and we didn't flush any existing bio in our "epd", it
calls flush_write_bio(epd) and overwrites the return value of 1 to 0 or
an error. The page might have been locked elsewhere, not with the goal
of starting writeback of the extent buffer, and even by some code other
than btrfs, like page migration for example, so it does not mean the
writeback of the extent buffer was already started by some other task,
so returning a 0 tells the caller (btree_write_cache_pages()) to not
start writeback for the extent buffer. Note that epd might currently have
either no bio, so flush_write_bio() returns 0 (success) or it might have
a bio for another extent buffer with a lower index (logical address).
Since we return 0 with the EXTENT_BUFFER_WRITEBACK bit set on the
extent buffer and writeback is never started for the extent buffer,
future attempts to writeback the extent buffer will hang forever waiting
on that bit to be cleared, since it can only be cleared after writeback
completes. Such hang is reported with a trace like the following:
[49887.347053] INFO: task btrfs-transacti:1752 blocked for more than 122 seconds.
[49887.347059] Not tainted 5.2.13-gentoo #2
[49887.347060] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[49887.347062] btrfs-transacti D 0 1752 2 0x80004000
[49887.347064] Call Trace:
[49887.347069] ? __schedule+0x265/0x830
[49887.347071] ? bit_wait+0x50/0x50
[49887.347072] ? bit_wait+0x50/0x50
[49887.347074] schedule+0x24/0x90
[49887.347075] io_schedule+0x3c/0x60
[49887.347077] bit_wait_io+0x8/0x50
[49887.347079] __wait_on_bit+0x6c/0x80
[49887.347081] ? __lock_release.isra.29+0x155/0x2d0
[49887.347083] out_of_line_wait_on_bit+0x7b/0x80
[49887.347084] ? var_wake_function+0x20/0x20
[49887.347087] lock_extent_buffer_for_io+0x28c/0x390
[49887.347089] btree_write_cache_pages+0x18e/0x340
[49887.347091] do_writepages+0x29/0xb0
[49887.347093] ? kmem_cache_free+0x132/0x160
[49887.347095] ? convert_extent_bit+0x544/0x680
[49887.347097] filemap_fdatawrite_range+0x70/0x90
[49887.347099] btrfs_write_marked_extents+0x53/0x120
[49887.347100] btrfs_write_and_wait_transaction.isra.4+0x38/0xa0
[49887.347102] btrfs_commit_transaction+0x6bb/0x990
[49887.347103] ? start_transaction+0x33e/0x500
[49887.347105] transaction_kthread+0x139/0x15c
So fix this by not overwriting the return value (ret) with the result
from flush_write_bio(). We also need to clear the EXTENT_BUFFER_WRITEBACK
bit in case flush_write_bio() returns an error, otherwise it will hang
any future attempts to writeback the extent buffer, and undo all work
done before (set back EXTENT_BUFFER_DIRTY, etc).
This is a regression introduced in the 5.2 kernel.
Fixes: 2e3c25136adfb ("btrfs: extent_io: add proper error handling to lock_extent_buffer_for_io()")
Fixes: f4340622e0226 ("btrfs: extent_io: Move the BUG_ON() in flush_write_bio() one level up")
Reported-by: Zdenek Sojka <zsojka@seznam.cz>
Link: https://lore.kernel.org/linux-btrfs/GpO.2yos.3WGDOLpx6t%7D.1TUDYM@seznam.cz/T/#u
Reported-by: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
Link: https://lore.kernel.org/linux-btrfs/5c4688ac-10a7-fb07-70e8-c5d31a3fbb38@profihost.ag/T/#t
Reported-by: Drazen Kacar <drazen.kacar@oradian.com>
Link: https://lore.kernel.org/linux-btrfs/DB8PR03MB562876ECE2319B3E579590F799C80@DB8PR03MB5628.eurprd03.prod.outlook.com/
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204377
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2019-09-12 00:42:00 +08:00
|
|
|
static void end_extent_buffer_writeback(struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
|
|
|
|
smp_mb__after_atomic();
|
|
|
|
wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
|
|
|
|
}
|
|
|
|
|
2019-03-20 14:27:46 +08:00
|
|
|
/*
|
btrfs: fix the comment on lock_extent_buffer_for_io
The return value of that function is completely wrong.
That function only returns 0 if the extent buffer doesn't need to be
submitted. The "ret = 1" and "ret = 0" are determined by the return
value of "test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)".
And if we get ret == 1, it's because the extent buffer is dirty, and we
set its status to EXTENT_BUFFER_WRITE_BACK, and continue to page
locking.
While if we get ret == 0, it means the extent is not dirty from the
beginning, so we don't need to write it back.
The caller also follows this, in btree_write_cache_pages(), if
lock_extent_buffer_for_io() returns 0, we just skip the extent buffer
completely.
So the comment is completely wrong.
Since we're here, also change the description a little. The write bio
flushing won't be visible to the caller, thus it's not an major feature.
In the main description, only describe the locking part to make the
point more clear.
For reference, added in commit 2e3c25136adf ("btrfs: extent_io: add
proper error handling to lock_extent_buffer_for_io()")
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-21 14:24:49 +08:00
|
|
|
* Lock extent buffer status and pages for writeback.
|
2019-03-20 14:27:46 +08:00
|
|
|
*
|
btrfs: fix the comment on lock_extent_buffer_for_io
The return value of that function is completely wrong.
That function only returns 0 if the extent buffer doesn't need to be
submitted. The "ret = 1" and "ret = 0" are determined by the return
value of "test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)".
And if we get ret == 1, it's because the extent buffer is dirty, and we
set its status to EXTENT_BUFFER_WRITE_BACK, and continue to page
locking.
While if we get ret == 0, it means the extent is not dirty from the
beginning, so we don't need to write it back.
The caller also follows this, in btree_write_cache_pages(), if
lock_extent_buffer_for_io() returns 0, we just skip the extent buffer
completely.
So the comment is completely wrong.
Since we're here, also change the description a little. The write bio
flushing won't be visible to the caller, thus it's not an major feature.
In the main description, only describe the locking part to make the
point more clear.
For reference, added in commit 2e3c25136adf ("btrfs: extent_io: add
proper error handling to lock_extent_buffer_for_io()")
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-10-21 14:24:49 +08:00
|
|
|
* May try to flush write bio if we can't get the lock.
|
|
|
|
*
|
|
|
|
* Return 0 if the extent buffer doesn't need to be submitted.
|
|
|
|
* (E.g. the extent buffer is not dirty)
|
|
|
|
* Return >0 is the extent buffer is submitted to bio.
|
|
|
|
* Return <0 if something went wrong, no page is locked.
|
2019-03-20 14:27:46 +08:00
|
|
|
*/
|
2019-03-20 18:21:41 +08:00
|
|
|
static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb,
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl)
|
2012-03-13 21:38:00 +08:00
|
|
|
{
|
2019-03-20 18:21:41 +08:00
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
btrfs: avoid double clean up when submit_one_bio() failed
[BUG]
When running generic/475 with 64K page size and 4K sector size, it has a
very high chance (almost 100%) to hang, with mostly data page locked but
no one is going to unlock it.
[CAUSE]
With commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads"), if we failed to lookup checksum due to metadata IO error, we
will return error for btrfs_submit_data_bio().
This will cause the page to be unlocked twice in btrfs_do_readpage():
btrfs_do_readpage()
|- submit_extent_page()
| |- submit_one_bio()
| |- btrfs_submit_data_bio()
| |- if (ret) {
| |- bio->bi_status = ret;
| |- bio_endio(bio); }
| In the endio function, we will call end_page_read()
| and unlock_extent() to cleanup the subpage range.
|
|- if (ret) {
|- unlock_extent(); end_page_read() }
Here we unlock the extent and cleanup the subpage range
again.
For unlock_extent(), it's mostly double unlock safe.
But for end_page_read(), it's not, especially for subpage case,
as for subpage case we will call btrfs_subpage_end_reader() to reduce
the reader number, and use that to number to determine if we need to
unlock the full page.
If double accounted, it can underflow the number and leave the page
locked without anyone to unlock it.
[FIX]
The commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads") itself is completely fine, it's our existing code not properly
handling the error from bio submission hook properly.
This patch will make submit_one_bio() to return void so that the callers
will never be able to do cleanup when bio submission hook fails.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:13 +08:00
|
|
|
int i, num_pages;
|
2012-03-13 21:38:00 +08:00
|
|
|
int flush = 0;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
if (!btrfs_try_tree_write_lock(eb)) {
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(bio_ctrl, 0);
|
2019-03-20 14:27:46 +08:00
|
|
|
flush = 1;
|
2012-03-13 21:38:00 +08:00
|
|
|
btrfs_tree_lock(eb);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) {
|
|
|
|
btrfs_tree_unlock(eb);
|
2022-10-27 19:07:05 +08:00
|
|
|
if (!bio_ctrl->sync_io)
|
2012-03-13 21:38:00 +08:00
|
|
|
return 0;
|
|
|
|
if (!flush) {
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(bio_ctrl, 0);
|
2012-03-13 21:38:00 +08:00
|
|
|
flush = 1;
|
|
|
|
}
|
2012-03-22 00:09:56 +08:00
|
|
|
while (1) {
|
|
|
|
wait_on_extent_buffer_writeback(eb);
|
|
|
|
btrfs_tree_lock(eb);
|
|
|
|
if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags))
|
|
|
|
break;
|
2012-03-13 21:38:00 +08:00
|
|
|
btrfs_tree_unlock(eb);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-07-21 04:25:24 +08:00
|
|
|
/*
|
|
|
|
* We need to do this to prevent races in people who check if the eb is
|
|
|
|
* under IO since we can end up having no IO bits set for a short period
|
|
|
|
* of time.
|
|
|
|
*/
|
|
|
|
spin_lock(&eb->refs_lock);
|
2012-03-13 21:38:00 +08:00
|
|
|
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
|
|
|
|
set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
|
2012-07-21 04:25:24 +08:00
|
|
|
spin_unlock(&eb->refs_lock);
|
2012-03-13 21:38:00 +08:00
|
|
|
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
|
2017-06-21 02:01:20 +08:00
|
|
|
percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
|
|
|
|
-eb->len,
|
|
|
|
fs_info->dirty_metadata_batch);
|
2012-03-13 21:38:00 +08:00
|
|
|
ret = 1;
|
2012-07-21 04:25:24 +08:00
|
|
|
} else {
|
|
|
|
spin_unlock(&eb->refs_lock);
|
2012-03-13 21:38:00 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
btrfs_tree_unlock(eb);
|
|
|
|
|
2021-04-06 08:36:02 +08:00
|
|
|
/*
|
|
|
|
* Either we don't need to submit any tree block, or we're submitting
|
|
|
|
* subpage eb.
|
|
|
|
* Subpage metadata doesn't use page locking at all, so we can skip
|
|
|
|
* the page locking.
|
|
|
|
*/
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (!ret || fs_info->nodesize < PAGE_SIZE)
|
2012-03-13 21:38:00 +08:00
|
|
|
return ret;
|
|
|
|
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2012-03-13 21:38:00 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
struct page *p = eb->pages[i];
|
2012-03-13 21:38:00 +08:00
|
|
|
|
|
|
|
if (!trylock_page(p)) {
|
|
|
|
if (!flush) {
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(bio_ctrl, 0);
|
2012-03-13 21:38:00 +08:00
|
|
|
flush = 1;
|
|
|
|
}
|
|
|
|
lock_page(p);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-03-20 14:27:46 +08:00
|
|
|
return ret;
|
2012-03-13 21:38:00 +08:00
|
|
|
}
|
|
|
|
|
2021-03-25 15:14:44 +08:00
|
|
|
static void set_btree_ioerr(struct page *page, struct extent_buffer *eb)
|
Btrfs: be aware of btree inode write errors to avoid fs corruption
While we have a transaction ongoing, the VM might decide at any time
to call btree_inode->i_mapping->a_ops->writepages(), which will start
writeback of dirty pages belonging to btree nodes/leafs. This call
might return an error or the writeback might finish with an error
before we attempt to commit the running transaction. If this happens,
we might have no way of knowing that such error happened when we are
committing the transaction - because the pages might no longer be
marked dirty nor tagged for writeback (if a subsequent modification
to the extent buffer didn't happen before the transaction commit) which
makes filemap_fdata[write|wait]_range unable to find such pages (even
if they're marked with SetPageError).
So if this happens we must abort the transaction, otherwise we commit
a super block with btree roots that point to btree nodes/leafs whose
content on disk is invalid - either garbage or the content of some
node/leaf from a past generation that got cowed or deleted and is no
longer valid (for this later case we end up getting error messages like
"parent transid verify failed on 10826481664 wanted 25748 found 29562"
when reading btree nodes/leafs from disk).
Note that setting and checking AS_EIO/AS_ENOSPC in the btree inode's
i_mapping would not be enough because we need to distinguish between
log tree extents (not fatal) vs non-log tree extents (fatal) and
because the next call to filemap_fdatawait_range() will catch and clear
such errors in the mapping - and that call might be from a log sync and
not from a transaction commit, which means we would not know about the
error at transaction commit time. Also, checking for the eb flag
EXTENT_BUFFER_IOERR at transaction commit time isn't done and would
not be completely reliable, as the eb might be removed from memory and
read back when trying to get it, which clears that flag right before
reading the eb's pages from disk, making us not know about the previous
write error.
Using the new 3 flags for the btree inode also makes us achieve the
goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
writeback for all dirty pages and before filemap_fdatawait_range() is
called, the writeback for all dirty pages had already finished with
errors - because we were not using AS_EIO/AS_ENOSPC,
filemap_fdatawait_range() would return success, as it could not know
that writeback errors happened (the pages were no longer tagged for
writeback).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-26 19:25:56 +08:00
|
|
|
{
|
2021-03-25 15:14:44 +08:00
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
Btrfs: be aware of btree inode write errors to avoid fs corruption
While we have a transaction ongoing, the VM might decide at any time
to call btree_inode->i_mapping->a_ops->writepages(), which will start
writeback of dirty pages belonging to btree nodes/leafs. This call
might return an error or the writeback might finish with an error
before we attempt to commit the running transaction. If this happens,
we might have no way of knowing that such error happened when we are
committing the transaction - because the pages might no longer be
marked dirty nor tagged for writeback (if a subsequent modification
to the extent buffer didn't happen before the transaction commit) which
makes filemap_fdata[write|wait]_range unable to find such pages (even
if they're marked with SetPageError).
So if this happens we must abort the transaction, otherwise we commit
a super block with btree roots that point to btree nodes/leafs whose
content on disk is invalid - either garbage or the content of some
node/leaf from a past generation that got cowed or deleted and is no
longer valid (for this later case we end up getting error messages like
"parent transid verify failed on 10826481664 wanted 25748 found 29562"
when reading btree nodes/leafs from disk).
Note that setting and checking AS_EIO/AS_ENOSPC in the btree inode's
i_mapping would not be enough because we need to distinguish between
log tree extents (not fatal) vs non-log tree extents (fatal) and
because the next call to filemap_fdatawait_range() will catch and clear
such errors in the mapping - and that call might be from a log sync and
not from a transaction commit, which means we would not know about the
error at transaction commit time. Also, checking for the eb flag
EXTENT_BUFFER_IOERR at transaction commit time isn't done and would
not be completely reliable, as the eb might be removed from memory and
read back when trying to get it, which clears that flag right before
reading the eb's pages from disk, making us not know about the previous
write error.
Using the new 3 flags for the btree inode also makes us achieve the
goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
writeback for all dirty pages and before filemap_fdatawait_range() is
called, the writeback for all dirty pages had already finished with
errors - because we were not using AS_EIO/AS_ENOSPC,
filemap_fdatawait_range() would return success, as it could not know
that writeback errors happened (the pages were no longer tagged for
writeback).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-26 19:25:56 +08:00
|
|
|
|
2021-03-25 15:14:44 +08:00
|
|
|
btrfs_page_set_error(fs_info, page, eb->start, eb->len);
|
Btrfs: be aware of btree inode write errors to avoid fs corruption
While we have a transaction ongoing, the VM might decide at any time
to call btree_inode->i_mapping->a_ops->writepages(), which will start
writeback of dirty pages belonging to btree nodes/leafs. This call
might return an error or the writeback might finish with an error
before we attempt to commit the running transaction. If this happens,
we might have no way of knowing that such error happened when we are
committing the transaction - because the pages might no longer be
marked dirty nor tagged for writeback (if a subsequent modification
to the extent buffer didn't happen before the transaction commit) which
makes filemap_fdata[write|wait]_range unable to find such pages (even
if they're marked with SetPageError).
So if this happens we must abort the transaction, otherwise we commit
a super block with btree roots that point to btree nodes/leafs whose
content on disk is invalid - either garbage or the content of some
node/leaf from a past generation that got cowed or deleted and is no
longer valid (for this later case we end up getting error messages like
"parent transid verify failed on 10826481664 wanted 25748 found 29562"
when reading btree nodes/leafs from disk).
Note that setting and checking AS_EIO/AS_ENOSPC in the btree inode's
i_mapping would not be enough because we need to distinguish between
log tree extents (not fatal) vs non-log tree extents (fatal) and
because the next call to filemap_fdatawait_range() will catch and clear
such errors in the mapping - and that call might be from a log sync and
not from a transaction commit, which means we would not know about the
error at transaction commit time. Also, checking for the eb flag
EXTENT_BUFFER_IOERR at transaction commit time isn't done and would
not be completely reliable, as the eb might be removed from memory and
read back when trying to get it, which clears that flag right before
reading the eb's pages from disk, making us not know about the previous
write error.
Using the new 3 flags for the btree inode also makes us achieve the
goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
writeback for all dirty pages and before filemap_fdatawait_range() is
called, the writeback for all dirty pages had already finished with
errors - because we were not using AS_EIO/AS_ENOSPC,
filemap_fdatawait_range() would return success, as it could not know
that writeback errors happened (the pages were no longer tagged for
writeback).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-26 19:25:56 +08:00
|
|
|
if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
|
|
|
|
return;
|
|
|
|
|
2021-11-25 03:14:23 +08:00
|
|
|
/*
|
|
|
|
* A read may stumble upon this buffer later, make sure that it gets an
|
|
|
|
* error and knows there was an error.
|
|
|
|
*/
|
|
|
|
clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
|
|
|
|
|
2021-11-25 03:14:25 +08:00
|
|
|
/*
|
|
|
|
* We need to set the mapping with the io error as well because a write
|
|
|
|
* error will flip the file system readonly, and then syncfs() will
|
|
|
|
* return a 0 because we are readonly if we don't modify the err seq for
|
|
|
|
* the superblock.
|
|
|
|
*/
|
|
|
|
mapping_set_error(page->mapping, -EIO);
|
|
|
|
|
2019-09-13 21:54:07 +08:00
|
|
|
/*
|
|
|
|
* If we error out, we should add back the dirty_metadata_bytes
|
|
|
|
* to make it consistent.
|
|
|
|
*/
|
|
|
|
percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
|
|
|
|
eb->len, fs_info->dirty_metadata_batch);
|
|
|
|
|
Btrfs: be aware of btree inode write errors to avoid fs corruption
While we have a transaction ongoing, the VM might decide at any time
to call btree_inode->i_mapping->a_ops->writepages(), which will start
writeback of dirty pages belonging to btree nodes/leafs. This call
might return an error or the writeback might finish with an error
before we attempt to commit the running transaction. If this happens,
we might have no way of knowing that such error happened when we are
committing the transaction - because the pages might no longer be
marked dirty nor tagged for writeback (if a subsequent modification
to the extent buffer didn't happen before the transaction commit) which
makes filemap_fdata[write|wait]_range unable to find such pages (even
if they're marked with SetPageError).
So if this happens we must abort the transaction, otherwise we commit
a super block with btree roots that point to btree nodes/leafs whose
content on disk is invalid - either garbage or the content of some
node/leaf from a past generation that got cowed or deleted and is no
longer valid (for this later case we end up getting error messages like
"parent transid verify failed on 10826481664 wanted 25748 found 29562"
when reading btree nodes/leafs from disk).
Note that setting and checking AS_EIO/AS_ENOSPC in the btree inode's
i_mapping would not be enough because we need to distinguish between
log tree extents (not fatal) vs non-log tree extents (fatal) and
because the next call to filemap_fdatawait_range() will catch and clear
such errors in the mapping - and that call might be from a log sync and
not from a transaction commit, which means we would not know about the
error at transaction commit time. Also, checking for the eb flag
EXTENT_BUFFER_IOERR at transaction commit time isn't done and would
not be completely reliable, as the eb might be removed from memory and
read back when trying to get it, which clears that flag right before
reading the eb's pages from disk, making us not know about the previous
write error.
Using the new 3 flags for the btree inode also makes us achieve the
goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
writeback for all dirty pages and before filemap_fdatawait_range() is
called, the writeback for all dirty pages had already finished with
errors - because we were not using AS_EIO/AS_ENOSPC,
filemap_fdatawait_range() would return success, as it could not know
that writeback errors happened (the pages were no longer tagged for
writeback).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-26 19:25:56 +08:00
|
|
|
/*
|
|
|
|
* If writeback for a btree extent that doesn't belong to a log tree
|
|
|
|
* failed, increment the counter transaction->eb_write_errors.
|
|
|
|
* We do this because while the transaction is running and before it's
|
|
|
|
* committing (when we call filemap_fdata[write|wait]_range against
|
|
|
|
* the btree inode), we might have
|
|
|
|
* btree_inode->i_mapping->a_ops->writepages() called by the VM - if it
|
|
|
|
* returns an error or an error happens during writeback, when we're
|
|
|
|
* committing the transaction we wouldn't know about it, since the pages
|
|
|
|
* can be no longer dirty nor marked anymore for writeback (if a
|
|
|
|
* subsequent modification to the extent buffer didn't happen before the
|
|
|
|
* transaction commit), which makes filemap_fdata[write|wait]_range not
|
|
|
|
* able to find the pages tagged with SetPageError at transaction
|
|
|
|
* commit time. So if this happens we must abort the transaction,
|
|
|
|
* otherwise we commit a super block with btree roots that point to
|
|
|
|
* btree nodes/leafs whose content on disk is invalid - either garbage
|
|
|
|
* or the content of some node/leaf from a past generation that got
|
|
|
|
* cowed or deleted and is no longer valid.
|
|
|
|
*
|
|
|
|
* Note: setting AS_EIO/AS_ENOSPC in the btree inode's i_mapping would
|
|
|
|
* not be enough - we need to distinguish between log tree extents vs
|
|
|
|
* non-log tree extents, and the next filemap_fdatawait_range() call
|
|
|
|
* will catch and clear such errors in the mapping - and that call might
|
|
|
|
* be from a log sync and not from a transaction commit. Also, checking
|
|
|
|
* for the eb flag EXTENT_BUFFER_WRITE_ERR at transaction commit time is
|
|
|
|
* not done and would not be reliable - the eb might have been released
|
|
|
|
* from memory and reading it back again means that flag would not be
|
|
|
|
* set (since it's a runtime flag, not persisted on disk).
|
|
|
|
*
|
|
|
|
* Using the flags below in the btree inode also makes us achieve the
|
|
|
|
* goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
|
|
|
|
* writeback for all dirty pages and before filemap_fdatawait_range()
|
|
|
|
* is called, the writeback for all dirty pages had already finished
|
|
|
|
* with errors - because we were not using AS_EIO/AS_ENOSPC,
|
|
|
|
* filemap_fdatawait_range() would return success, as it could not know
|
|
|
|
* that writeback errors happened (the pages were no longer tagged for
|
|
|
|
* writeback).
|
|
|
|
*/
|
|
|
|
switch (eb->log_index) {
|
|
|
|
case -1:
|
2021-03-25 15:14:44 +08:00
|
|
|
set_bit(BTRFS_FS_BTREE_ERR, &fs_info->flags);
|
Btrfs: be aware of btree inode write errors to avoid fs corruption
While we have a transaction ongoing, the VM might decide at any time
to call btree_inode->i_mapping->a_ops->writepages(), which will start
writeback of dirty pages belonging to btree nodes/leafs. This call
might return an error or the writeback might finish with an error
before we attempt to commit the running transaction. If this happens,
we might have no way of knowing that such error happened when we are
committing the transaction - because the pages might no longer be
marked dirty nor tagged for writeback (if a subsequent modification
to the extent buffer didn't happen before the transaction commit) which
makes filemap_fdata[write|wait]_range unable to find such pages (even
if they're marked with SetPageError).
So if this happens we must abort the transaction, otherwise we commit
a super block with btree roots that point to btree nodes/leafs whose
content on disk is invalid - either garbage or the content of some
node/leaf from a past generation that got cowed or deleted and is no
longer valid (for this later case we end up getting error messages like
"parent transid verify failed on 10826481664 wanted 25748 found 29562"
when reading btree nodes/leafs from disk).
Note that setting and checking AS_EIO/AS_ENOSPC in the btree inode's
i_mapping would not be enough because we need to distinguish between
log tree extents (not fatal) vs non-log tree extents (fatal) and
because the next call to filemap_fdatawait_range() will catch and clear
such errors in the mapping - and that call might be from a log sync and
not from a transaction commit, which means we would not know about the
error at transaction commit time. Also, checking for the eb flag
EXTENT_BUFFER_IOERR at transaction commit time isn't done and would
not be completely reliable, as the eb might be removed from memory and
read back when trying to get it, which clears that flag right before
reading the eb's pages from disk, making us not know about the previous
write error.
Using the new 3 flags for the btree inode also makes us achieve the
goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
writeback for all dirty pages and before filemap_fdatawait_range() is
called, the writeback for all dirty pages had already finished with
errors - because we were not using AS_EIO/AS_ENOSPC,
filemap_fdatawait_range() would return success, as it could not know
that writeback errors happened (the pages were no longer tagged for
writeback).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-26 19:25:56 +08:00
|
|
|
break;
|
|
|
|
case 0:
|
2021-03-25 15:14:44 +08:00
|
|
|
set_bit(BTRFS_FS_LOG1_ERR, &fs_info->flags);
|
Btrfs: be aware of btree inode write errors to avoid fs corruption
While we have a transaction ongoing, the VM might decide at any time
to call btree_inode->i_mapping->a_ops->writepages(), which will start
writeback of dirty pages belonging to btree nodes/leafs. This call
might return an error or the writeback might finish with an error
before we attempt to commit the running transaction. If this happens,
we might have no way of knowing that such error happened when we are
committing the transaction - because the pages might no longer be
marked dirty nor tagged for writeback (if a subsequent modification
to the extent buffer didn't happen before the transaction commit) which
makes filemap_fdata[write|wait]_range unable to find such pages (even
if they're marked with SetPageError).
So if this happens we must abort the transaction, otherwise we commit
a super block with btree roots that point to btree nodes/leafs whose
content on disk is invalid - either garbage or the content of some
node/leaf from a past generation that got cowed or deleted and is no
longer valid (for this later case we end up getting error messages like
"parent transid verify failed on 10826481664 wanted 25748 found 29562"
when reading btree nodes/leafs from disk).
Note that setting and checking AS_EIO/AS_ENOSPC in the btree inode's
i_mapping would not be enough because we need to distinguish between
log tree extents (not fatal) vs non-log tree extents (fatal) and
because the next call to filemap_fdatawait_range() will catch and clear
such errors in the mapping - and that call might be from a log sync and
not from a transaction commit, which means we would not know about the
error at transaction commit time. Also, checking for the eb flag
EXTENT_BUFFER_IOERR at transaction commit time isn't done and would
not be completely reliable, as the eb might be removed from memory and
read back when trying to get it, which clears that flag right before
reading the eb's pages from disk, making us not know about the previous
write error.
Using the new 3 flags for the btree inode also makes us achieve the
goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
writeback for all dirty pages and before filemap_fdatawait_range() is
called, the writeback for all dirty pages had already finished with
errors - because we were not using AS_EIO/AS_ENOSPC,
filemap_fdatawait_range() would return success, as it could not know
that writeback errors happened (the pages were no longer tagged for
writeback).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-26 19:25:56 +08:00
|
|
|
break;
|
|
|
|
case 1:
|
2021-03-25 15:14:44 +08:00
|
|
|
set_bit(BTRFS_FS_LOG2_ERR, &fs_info->flags);
|
Btrfs: be aware of btree inode write errors to avoid fs corruption
While we have a transaction ongoing, the VM might decide at any time
to call btree_inode->i_mapping->a_ops->writepages(), which will start
writeback of dirty pages belonging to btree nodes/leafs. This call
might return an error or the writeback might finish with an error
before we attempt to commit the running transaction. If this happens,
we might have no way of knowing that such error happened when we are
committing the transaction - because the pages might no longer be
marked dirty nor tagged for writeback (if a subsequent modification
to the extent buffer didn't happen before the transaction commit) which
makes filemap_fdata[write|wait]_range unable to find such pages (even
if they're marked with SetPageError).
So if this happens we must abort the transaction, otherwise we commit
a super block with btree roots that point to btree nodes/leafs whose
content on disk is invalid - either garbage or the content of some
node/leaf from a past generation that got cowed or deleted and is no
longer valid (for this later case we end up getting error messages like
"parent transid verify failed on 10826481664 wanted 25748 found 29562"
when reading btree nodes/leafs from disk).
Note that setting and checking AS_EIO/AS_ENOSPC in the btree inode's
i_mapping would not be enough because we need to distinguish between
log tree extents (not fatal) vs non-log tree extents (fatal) and
because the next call to filemap_fdatawait_range() will catch and clear
such errors in the mapping - and that call might be from a log sync and
not from a transaction commit, which means we would not know about the
error at transaction commit time. Also, checking for the eb flag
EXTENT_BUFFER_IOERR at transaction commit time isn't done and would
not be completely reliable, as the eb might be removed from memory and
read back when trying to get it, which clears that flag right before
reading the eb's pages from disk, making us not know about the previous
write error.
Using the new 3 flags for the btree inode also makes us achieve the
goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
writeback for all dirty pages and before filemap_fdatawait_range() is
called, the writeback for all dirty pages had already finished with
errors - because we were not using AS_EIO/AS_ENOSPC,
filemap_fdatawait_range() would return success, as it could not know
that writeback errors happened (the pages were no longer tagged for
writeback).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-26 19:25:56 +08:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
BUG(); /* unexpected, logic error */
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-04-06 08:36:00 +08:00
|
|
|
/*
|
|
|
|
* The endio specific version which won't touch any unsafe spinlock in endio
|
|
|
|
* context.
|
|
|
|
*/
|
|
|
|
static struct extent_buffer *find_extent_buffer_nolock(
|
|
|
|
struct btrfs_fs_info *fs_info, u64 start)
|
|
|
|
{
|
|
|
|
struct extent_buffer *eb;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
2022-07-15 19:59:31 +08:00
|
|
|
eb = radix_tree_lookup(&fs_info->buffer_radix,
|
|
|
|
start >> fs_info->sectorsize_bits);
|
2021-04-06 08:36:00 +08:00
|
|
|
if (eb && atomic_inc_not_zero(&eb->refs)) {
|
|
|
|
rcu_read_unlock();
|
|
|
|
return eb;
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The endio function for subpage extent buffer write.
|
|
|
|
*
|
|
|
|
* Unlike end_bio_extent_buffer_writepage(), we only call end_page_writeback()
|
|
|
|
* after all extent buffers in the page has finished their writeback.
|
|
|
|
*/
|
2022-08-06 16:03:26 +08:00
|
|
|
static void end_bio_subpage_eb_writepage(struct btrfs_bio *bbio)
|
2021-04-06 08:36:00 +08:00
|
|
|
{
|
2022-08-06 16:03:26 +08:00
|
|
|
struct bio *bio = &bbio->bio;
|
2021-04-27 12:53:35 +08:00
|
|
|
struct btrfs_fs_info *fs_info;
|
2021-04-06 08:36:00 +08:00
|
|
|
struct bio_vec *bvec;
|
|
|
|
struct bvec_iter_all iter_all;
|
|
|
|
|
2021-04-27 12:53:35 +08:00
|
|
|
fs_info = btrfs_sb(bio_first_page_all(bio)->mapping->host->i_sb);
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
ASSERT(fs_info->nodesize < PAGE_SIZE);
|
2021-04-27 12:53:35 +08:00
|
|
|
|
2021-04-06 08:36:00 +08:00
|
|
|
ASSERT(!bio_flagged(bio, BIO_CLONED));
|
|
|
|
bio_for_each_segment_all(bvec, bio, iter_all) {
|
|
|
|
struct page *page = bvec->bv_page;
|
|
|
|
u64 bvec_start = page_offset(page) + bvec->bv_offset;
|
|
|
|
u64 bvec_end = bvec_start + bvec->bv_len - 1;
|
|
|
|
u64 cur_bytenr = bvec_start;
|
|
|
|
|
|
|
|
ASSERT(IS_ALIGNED(bvec->bv_len, fs_info->nodesize));
|
|
|
|
|
|
|
|
/* Iterate through all extent buffers in the range */
|
|
|
|
while (cur_bytenr <= bvec_end) {
|
|
|
|
struct extent_buffer *eb;
|
|
|
|
int done;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Here we can't use find_extent_buffer(), as it may
|
|
|
|
* try to lock eb->refs_lock, which is not safe in endio
|
|
|
|
* context.
|
|
|
|
*/
|
|
|
|
eb = find_extent_buffer_nolock(fs_info, cur_bytenr);
|
|
|
|
ASSERT(eb);
|
|
|
|
|
|
|
|
cur_bytenr = eb->start + eb->len;
|
|
|
|
|
|
|
|
ASSERT(test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags));
|
|
|
|
done = atomic_dec_and_test(&eb->io_pages);
|
|
|
|
ASSERT(done);
|
|
|
|
|
|
|
|
if (bio->bi_status ||
|
|
|
|
test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
|
|
|
|
ClearPageUptodate(page);
|
|
|
|
set_btree_ioerr(page, eb);
|
|
|
|
}
|
|
|
|
|
|
|
|
btrfs_subpage_clear_writeback(fs_info, page, eb->start,
|
|
|
|
eb->len);
|
|
|
|
end_extent_buffer_writeback(eb);
|
|
|
|
/*
|
|
|
|
* free_extent_buffer() will grab spinlock which is not
|
|
|
|
* safe in endio context. Thus here we manually dec
|
|
|
|
* the ref.
|
|
|
|
*/
|
|
|
|
atomic_dec(&eb->refs);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
bio_put(bio);
|
|
|
|
}
|
|
|
|
|
2022-08-06 16:03:26 +08:00
|
|
|
static void end_bio_extent_buffer_writepage(struct btrfs_bio *bbio)
|
2012-03-13 21:38:00 +08:00
|
|
|
{
|
2022-08-06 16:03:26 +08:00
|
|
|
struct bio *bio = &bbio->bio;
|
2013-11-08 04:20:26 +08:00
|
|
|
struct bio_vec *bvec;
|
2012-03-13 21:38:00 +08:00
|
|
|
struct extent_buffer *eb;
|
2019-04-25 15:03:00 +08:00
|
|
|
int done;
|
2019-02-15 19:13:19 +08:00
|
|
|
struct bvec_iter_all iter_all;
|
2012-03-13 21:38:00 +08:00
|
|
|
|
2017-07-14 00:10:07 +08:00
|
|
|
ASSERT(!bio_flagged(bio, BIO_CLONED));
|
2019-04-25 15:03:00 +08:00
|
|
|
bio_for_each_segment_all(bvec, bio, iter_all) {
|
2012-03-13 21:38:00 +08:00
|
|
|
struct page *page = bvec->bv_page;
|
|
|
|
|
|
|
|
eb = (struct extent_buffer *)page->private;
|
|
|
|
BUG_ON(!eb);
|
|
|
|
done = atomic_dec_and_test(&eb->io_pages);
|
|
|
|
|
2017-06-03 15:38:06 +08:00
|
|
|
if (bio->bi_status ||
|
2015-07-20 21:29:37 +08:00
|
|
|
test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
|
2012-03-13 21:38:00 +08:00
|
|
|
ClearPageUptodate(page);
|
2021-03-25 15:14:44 +08:00
|
|
|
set_btree_ioerr(page, eb);
|
2012-03-13 21:38:00 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
end_page_writeback(page);
|
|
|
|
|
|
|
|
if (!done)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
end_extent_buffer_writeback(eb);
|
2013-11-08 04:20:26 +08:00
|
|
|
}
|
2012-03-13 21:38:00 +08:00
|
|
|
|
|
|
|
bio_put(bio);
|
|
|
|
}
|
|
|
|
|
2021-04-27 12:53:35 +08:00
|
|
|
static void prepare_eb_write(struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
u32 nritems;
|
|
|
|
unsigned long start;
|
|
|
|
unsigned long end;
|
|
|
|
|
|
|
|
clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
|
|
|
|
atomic_set(&eb->io_pages, num_extent_pages(eb));
|
|
|
|
|
|
|
|
/* Set btree blocks beyond nritems with 0 to avoid stale content */
|
|
|
|
nritems = btrfs_header_nritems(eb);
|
|
|
|
if (btrfs_header_level(eb) > 0) {
|
|
|
|
end = btrfs_node_key_ptr_offset(nritems);
|
|
|
|
memzero_extent_buffer(eb, end, eb->len - end);
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* Leaf:
|
|
|
|
* header 0 1 2 .. N ... data_N .. data_2 data_1 data_0
|
|
|
|
*/
|
|
|
|
start = btrfs_item_nr_offset(nritems);
|
|
|
|
end = BTRFS_LEAF_DATA_OFFSET + leaf_data_end(eb);
|
|
|
|
memzero_extent_buffer(eb, start, end - start);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-04-06 08:36:01 +08:00
|
|
|
/*
|
|
|
|
* Unlike the work in write_one_eb(), we rely completely on extent locking.
|
|
|
|
* Page locking is only utilized at minimum to keep the VMM code happy.
|
|
|
|
*/
|
|
|
|
static int write_one_subpage_eb(struct extent_buffer *eb,
|
|
|
|
struct writeback_control *wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl)
|
2021-04-06 08:36:01 +08:00
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
|
|
|
struct page *page = eb->pages[0];
|
for-5.20-tag
-----BEGIN PGP SIGNATURE-----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=sS1q
-----END PGP SIGNATURE-----
Merge tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba:
"This brings some long awaited changes, the send protocol bump,
otherwise lots of small improvements and fixes. The main core part is
reworking bio handling, cleaning up the submission and endio and
improving error handling.
There are some changes outside of btrfs adding helpers or updating
API, listed at the end of the changelog.
Features:
- sysfs:
- export chunk size, in debug mode add tunable for setting its size
- show zoned among features (was only in debug mode)
- show commit stats (number, last/max/total duration)
- send protocol updated to 2
- new commands:
- ability write larger data chunks than 64K
- send raw compressed extents (uses the encoded data ioctls),
ie. no decompression on send side, no compression needed on
receive side if supported
- send 'otime' (inode creation time) among other timestamps
- send file attributes (a.k.a file flags and xflags)
- this is first version bump, backward compatibility on send and
receive side is provided
- there are still some known and wanted commands that will be
implemented in the near future, another version bump will be
needed, however we want to minimize that to avoid causing
usability issues
- print checksum type and implementation at mount time
- don't print some messages at mount (mentioned as people asked about
it), we want to print messages namely for new features so let's
make some space for that
- big metadata - this has been supported for a long time and is
not a feature that's worth mentioning
- skinny metadata - same reason, set by default by mkfs
Performance improvements:
- reduced amount of reserved metadata for delayed items
- when inserted items can be batched into one leaf
- when deleting batched directory index items
- when deleting delayed items used for deletion
- overall improved count of files/sec, decreased subvolume lock
contention
- metadata item access bounds checker micro-optimized, with a few
percent of improved runtime for metadata-heavy operations
- increase direct io limit for read to 256 sectors, improved
throughput by 3x on sample workload
Notable fixes:
- raid56
- reduce parity writes, skip sectors of stripe when there are no
data updates
- restore reading from on-disk data instead of using stripe cache,
this reduces chances to damage correct data due to RMW cycle
- refuse to replay log with unknown incompat read-only feature bit
set
- zoned
- fix page locking when COW fails in the middle of allocation
- improved tracking of active zones, ZNS drives may limit the
number and there are ENOSPC errors due to that limit and not
actual lack of space
- adjust maximum extent size for zone append so it does not cause
late ENOSPC due to underreservation
- mirror reading error messages show the mirror number
- don't fallback to buffered IO for NOWAIT direct IO writes, we don't
have the NOWAIT semantics for buffered io yet
- send, fix sending link commands for existing file paths when there
are deleted and created hardlinks for same files
- repair all mirrors for profiles with more than 1 copy (raid1c34)
- fix repair of compressed extents, unify where error detection and
repair happen
Core changes:
- bio completion cleanups
- don't double defer compression bios
- simplify endio workqueues
- add more data to btrfs_bio to avoid allocation for read requests
- rework bio error handling so it's same what block layer does,
the submission works and errors are consumed in endio
- when asynchronous bio offload fails fall back to synchronous
checksum calculation to avoid errors under writeback or memory
pressure
- new trace points
- raid56 events
- ordered extent operations
- super block log_root_transid deprecated (never used)
- mixed_backref and big_metadata sysfs feature files removed, they've
been default for sufficiently long time, there are no known users
and mixed_backref could be confused with mixed_groups
Non-btrfs changes, API updates:
- minor highmem API update to cover const arguments
- switch all kmap/kmap_atomic to kmap_local
- remove redundant flush_dcache_page()
- address_space_operations::writepage callback removed
- add bdev_max_segments() helper"
* tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (163 commits)
btrfs: don't call btrfs_page_set_checked in finish_compressed_bio_read
btrfs: fix repair of compressed extents
btrfs: remove the start argument to check_data_csum and export
btrfs: pass a btrfs_bio to btrfs_repair_one_sector
btrfs: simplify the pending I/O counting in struct compressed_bio
btrfs: repair all known bad mirrors
btrfs: merge btrfs_dev_stat_print_on_error with its only caller
btrfs: join running log transaction when logging new name
btrfs: simplify error handling in btrfs_lookup_dentry
btrfs: send: always use the rbtree based inode ref management infrastructure
btrfs: send: fix sending link commands for existing file paths
btrfs: send: introduce recorded_ref_alloc and recorded_ref_free
btrfs: zoned: wait until zone is finished when allocation didn't progress
btrfs: zoned: write out partially allocated region
btrfs: zoned: activate necessary block group
btrfs: zoned: activate metadata block group on flush_space
btrfs: zoned: disable metadata overcommit for zoned
btrfs: zoned: introduce space_info->active_total_bytes
btrfs: zoned: finish least available block group on data bg allocation
btrfs: let can_allocate_chunk return error
...
2022-08-04 05:54:52 +08:00
|
|
|
blk_opf_t write_flags = wbc_to_write_flags(wbc);
|
2021-04-06 08:36:01 +08:00
|
|
|
bool no_dirty_ebs = false;
|
|
|
|
int ret;
|
|
|
|
|
2021-04-27 12:53:35 +08:00
|
|
|
prepare_eb_write(eb);
|
|
|
|
|
2021-04-06 08:36:01 +08:00
|
|
|
/* clear_page_dirty_for_io() in subpage helper needs page locked */
|
|
|
|
lock_page(page);
|
|
|
|
btrfs_subpage_set_writeback(fs_info, page, eb->start, eb->len);
|
|
|
|
|
|
|
|
/* Check if this is the last dirty bit to update nr_written */
|
|
|
|
no_dirty_ebs = btrfs_subpage_clear_and_test_dirty(fs_info, page,
|
|
|
|
eb->start, eb->len);
|
|
|
|
if (no_dirty_ebs)
|
|
|
|
clear_page_dirty_for_io(page);
|
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
bio_ctrl->end_io_func = end_bio_subpage_eb_writepage;
|
2022-09-13 13:31:14 +08:00
|
|
|
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
bio_ctrl, eb->start, page, eb->len,
|
2022-09-13 13:31:14 +08:00
|
|
|
eb->start - page_offset(page), 0, false);
|
2021-04-06 08:36:01 +08:00
|
|
|
if (ret) {
|
|
|
|
btrfs_subpage_clear_writeback(fs_info, page, eb->start, eb->len);
|
|
|
|
set_btree_ioerr(page, eb);
|
|
|
|
unlock_page(page);
|
|
|
|
|
|
|
|
if (atomic_dec_and_test(&eb->io_pages))
|
|
|
|
end_extent_buffer_writeback(eb);
|
|
|
|
return -EIO;
|
|
|
|
}
|
|
|
|
unlock_page(page);
|
|
|
|
/*
|
|
|
|
* Submission finished without problem, if no range of the page is
|
|
|
|
* dirty anymore, we have submitted a page. Update nr_written in wbc.
|
|
|
|
*/
|
|
|
|
if (no_dirty_ebs)
|
2021-07-27 18:45:11 +08:00
|
|
|
wbc->nr_to_write--;
|
2021-04-06 08:36:01 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2014-05-20 11:55:27 +08:00
|
|
|
static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
|
2012-03-13 21:38:00 +08:00
|
|
|
struct writeback_control *wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl)
|
2012-03-13 21:38:00 +08:00
|
|
|
{
|
2021-01-06 09:01:40 +08:00
|
|
|
u64 disk_bytenr = eb->start;
|
2018-03-02 01:20:27 +08:00
|
|
|
int i, num_pages;
|
for-5.20-tag
-----BEGIN PGP SIGNATURE-----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=sS1q
-----END PGP SIGNATURE-----
Merge tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba:
"This brings some long awaited changes, the send protocol bump,
otherwise lots of small improvements and fixes. The main core part is
reworking bio handling, cleaning up the submission and endio and
improving error handling.
There are some changes outside of btrfs adding helpers or updating
API, listed at the end of the changelog.
Features:
- sysfs:
- export chunk size, in debug mode add tunable for setting its size
- show zoned among features (was only in debug mode)
- show commit stats (number, last/max/total duration)
- send protocol updated to 2
- new commands:
- ability write larger data chunks than 64K
- send raw compressed extents (uses the encoded data ioctls),
ie. no decompression on send side, no compression needed on
receive side if supported
- send 'otime' (inode creation time) among other timestamps
- send file attributes (a.k.a file flags and xflags)
- this is first version bump, backward compatibility on send and
receive side is provided
- there are still some known and wanted commands that will be
implemented in the near future, another version bump will be
needed, however we want to minimize that to avoid causing
usability issues
- print checksum type and implementation at mount time
- don't print some messages at mount (mentioned as people asked about
it), we want to print messages namely for new features so let's
make some space for that
- big metadata - this has been supported for a long time and is
not a feature that's worth mentioning
- skinny metadata - same reason, set by default by mkfs
Performance improvements:
- reduced amount of reserved metadata for delayed items
- when inserted items can be batched into one leaf
- when deleting batched directory index items
- when deleting delayed items used for deletion
- overall improved count of files/sec, decreased subvolume lock
contention
- metadata item access bounds checker micro-optimized, with a few
percent of improved runtime for metadata-heavy operations
- increase direct io limit for read to 256 sectors, improved
throughput by 3x on sample workload
Notable fixes:
- raid56
- reduce parity writes, skip sectors of stripe when there are no
data updates
- restore reading from on-disk data instead of using stripe cache,
this reduces chances to damage correct data due to RMW cycle
- refuse to replay log with unknown incompat read-only feature bit
set
- zoned
- fix page locking when COW fails in the middle of allocation
- improved tracking of active zones, ZNS drives may limit the
number and there are ENOSPC errors due to that limit and not
actual lack of space
- adjust maximum extent size for zone append so it does not cause
late ENOSPC due to underreservation
- mirror reading error messages show the mirror number
- don't fallback to buffered IO for NOWAIT direct IO writes, we don't
have the NOWAIT semantics for buffered io yet
- send, fix sending link commands for existing file paths when there
are deleted and created hardlinks for same files
- repair all mirrors for profiles with more than 1 copy (raid1c34)
- fix repair of compressed extents, unify where error detection and
repair happen
Core changes:
- bio completion cleanups
- don't double defer compression bios
- simplify endio workqueues
- add more data to btrfs_bio to avoid allocation for read requests
- rework bio error handling so it's same what block layer does,
the submission works and errors are consumed in endio
- when asynchronous bio offload fails fall back to synchronous
checksum calculation to avoid errors under writeback or memory
pressure
- new trace points
- raid56 events
- ordered extent operations
- super block log_root_transid deprecated (never used)
- mixed_backref and big_metadata sysfs feature files removed, they've
been default for sufficiently long time, there are no known users
and mixed_backref could be confused with mixed_groups
Non-btrfs changes, API updates:
- minor highmem API update to cover const arguments
- switch all kmap/kmap_atomic to kmap_local
- remove redundant flush_dcache_page()
- address_space_operations::writepage callback removed
- add bdev_max_segments() helper"
* tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (163 commits)
btrfs: don't call btrfs_page_set_checked in finish_compressed_bio_read
btrfs: fix repair of compressed extents
btrfs: remove the start argument to check_data_csum and export
btrfs: pass a btrfs_bio to btrfs_repair_one_sector
btrfs: simplify the pending I/O counting in struct compressed_bio
btrfs: repair all known bad mirrors
btrfs: merge btrfs_dev_stat_print_on_error with its only caller
btrfs: join running log transaction when logging new name
btrfs: simplify error handling in btrfs_lookup_dentry
btrfs: send: always use the rbtree based inode ref management infrastructure
btrfs: send: fix sending link commands for existing file paths
btrfs: send: introduce recorded_ref_alloc and recorded_ref_free
btrfs: zoned: wait until zone is finished when allocation didn't progress
btrfs: zoned: write out partially allocated region
btrfs: zoned: activate necessary block group
btrfs: zoned: activate metadata block group on flush_space
btrfs: zoned: disable metadata overcommit for zoned
btrfs: zoned: introduce space_info->active_total_bytes
btrfs: zoned: finish least available block group on data bg allocation
btrfs: let can_allocate_chunk return error
...
2022-08-04 05:54:52 +08:00
|
|
|
blk_opf_t write_flags = wbc_to_write_flags(wbc);
|
2012-04-24 02:00:51 +08:00
|
|
|
int ret = 0;
|
2012-03-13 21:38:00 +08:00
|
|
|
|
2021-04-27 12:53:35 +08:00
|
|
|
prepare_eb_write(eb);
|
2021-04-06 08:36:01 +08:00
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
bio_ctrl->end_io_func = end_bio_extent_buffer_writepage;
|
2022-09-13 13:31:14 +08:00
|
|
|
|
2021-04-27 12:53:35 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2012-03-13 21:38:00 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
struct page *p = eb->pages[i];
|
2012-03-13 21:38:00 +08:00
|
|
|
|
|
|
|
clear_page_dirty_for_io(p);
|
|
|
|
set_page_writeback(p);
|
2020-02-06 02:09:28 +08:00
|
|
|
ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
bio_ctrl, disk_bytenr, p,
|
2022-09-13 13:31:14 +08:00
|
|
|
PAGE_SIZE, 0, 0, false);
|
2012-03-13 21:38:00 +08:00
|
|
|
if (ret) {
|
2021-03-25 15:14:44 +08:00
|
|
|
set_btree_ioerr(p, eb);
|
Btrfs: add another missing end_page_writeback on submit_extent_page failure
If btrfs_bio_alloc fails in submit_extent_page, submit_extent_page returns
without clearing the writeback bit of the failed page.
__extent_writepage_io, that is a caller of submit_extent_page,
does not clear the remaining writeback bit anywhere.
As a result, this will cause the hang at filemap_fdatawait_range,
because it waits the writeback bit to be cleared from the failed page.
So, we have to call end_page_writeback to clear the writeback bit.
For reproducing the hang, we inject a fault like
if (should_failtest()) { // I define should_failtest()
bio = NULL;
}
else {
bio = btrfs_bio_alloc(...);
}
in submit_extent_page.
We should also check whether page has the bit before end_page_writeback,
to avoid the conflict against the other end_page_writeback in bio_endio.
Thus, we add PageWriteback checks not only in __extent_writepage_io,
but also in write_one_eb too, because it misses the check.
Signed-off-by: Takafumi Kubota <takafumi.kubota1012@sslab.ics.keio.ac.jp>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Cc: David Sterba <dsterba@suse.cz>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-02-09 16:24:33 +08:00
|
|
|
if (PageWriteback(p))
|
|
|
|
end_page_writeback(p);
|
2012-03-13 21:38:00 +08:00
|
|
|
if (atomic_sub_and_test(num_pages - i, &eb->io_pages))
|
|
|
|
end_extent_buffer_writeback(eb);
|
|
|
|
ret = -EIO;
|
|
|
|
break;
|
|
|
|
}
|
2021-01-06 09:01:40 +08:00
|
|
|
disk_bytenr += PAGE_SIZE;
|
2021-07-27 18:45:11 +08:00
|
|
|
wbc->nr_to_write--;
|
2012-03-13 21:38:00 +08:00
|
|
|
unlock_page(p);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (unlikely(ret)) {
|
|
|
|
for (; i < num_pages; i++) {
|
2014-10-05 00:56:45 +08:00
|
|
|
struct page *p = eb->pages[i];
|
2014-09-23 22:22:33 +08:00
|
|
|
clear_page_dirty_for_io(p);
|
2012-03-13 21:38:00 +08:00
|
|
|
unlock_page(p);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2021-04-06 08:36:03 +08:00
|
|
|
/*
|
|
|
|
* Submit one subpage btree page.
|
|
|
|
*
|
|
|
|
* The main difference to submit_eb_page() is:
|
|
|
|
* - Page locking
|
|
|
|
* For subpage, we don't rely on page locking at all.
|
|
|
|
*
|
|
|
|
* - Flush write bio
|
|
|
|
* We only flush bio if we may be unable to fit current extent buffers into
|
|
|
|
* current bio.
|
|
|
|
*
|
|
|
|
* Return >=0 for the number of submitted extent buffers.
|
|
|
|
* Return <0 for fatal error.
|
|
|
|
*/
|
|
|
|
static int submit_eb_subpage(struct page *page,
|
|
|
|
struct writeback_control *wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl)
|
2021-04-06 08:36:03 +08:00
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
|
|
|
|
int submitted = 0;
|
|
|
|
u64 page_start = page_offset(page);
|
|
|
|
int bit_start = 0;
|
|
|
|
int sectors_per_node = fs_info->nodesize >> fs_info->sectorsize_bits;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
/* Lock and write each dirty extent buffers in the range */
|
2021-08-17 17:38:52 +08:00
|
|
|
while (bit_start < fs_info->subpage_info->bitmap_nr_bits) {
|
2021-04-06 08:36:03 +08:00
|
|
|
struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
struct extent_buffer *eb;
|
|
|
|
unsigned long flags;
|
|
|
|
u64 start;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Take private lock to ensure the subpage won't be detached
|
|
|
|
* in the meantime.
|
|
|
|
*/
|
|
|
|
spin_lock(&page->mapping->private_lock);
|
|
|
|
if (!PagePrivate(page)) {
|
|
|
|
spin_unlock(&page->mapping->private_lock);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
spin_lock_irqsave(&subpage->lock, flags);
|
2021-08-17 17:38:52 +08:00
|
|
|
if (!test_bit(bit_start + fs_info->subpage_info->dirty_offset,
|
|
|
|
subpage->bitmaps)) {
|
2021-04-06 08:36:03 +08:00
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
spin_unlock(&page->mapping->private_lock);
|
|
|
|
bit_start++;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
start = page_start + bit_start * fs_info->sectorsize;
|
|
|
|
bit_start += sectors_per_node;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Here we just want to grab the eb without touching extra
|
|
|
|
* spin locks, so call find_extent_buffer_nolock().
|
|
|
|
*/
|
|
|
|
eb = find_extent_buffer_nolock(fs_info, start);
|
|
|
|
spin_unlock_irqrestore(&subpage->lock, flags);
|
|
|
|
spin_unlock(&page->mapping->private_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The eb has already reached 0 refs thus find_extent_buffer()
|
|
|
|
* doesn't return it. We don't need to write back such eb
|
|
|
|
* anyway.
|
|
|
|
*/
|
|
|
|
if (!eb)
|
|
|
|
continue;
|
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = lock_extent_buffer_for_io(eb, bio_ctrl);
|
2021-04-06 08:36:03 +08:00
|
|
|
if (ret == 0) {
|
|
|
|
free_extent_buffer(eb);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (ret < 0) {
|
|
|
|
free_extent_buffer(eb);
|
|
|
|
goto cleanup;
|
|
|
|
}
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = write_one_subpage_eb(eb, wbc, bio_ctrl);
|
2021-04-06 08:36:03 +08:00
|
|
|
free_extent_buffer(eb);
|
|
|
|
if (ret < 0)
|
|
|
|
goto cleanup;
|
|
|
|
submitted++;
|
|
|
|
}
|
|
|
|
return submitted;
|
|
|
|
|
|
|
|
cleanup:
|
|
|
|
/* We hit error, end bio for the submitted extent buffers */
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(bio_ctrl, ret);
|
2021-04-06 08:36:03 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2020-12-02 14:48:00 +08:00
|
|
|
/*
|
|
|
|
* Submit all page(s) of one extent buffer.
|
|
|
|
*
|
|
|
|
* @page: the page of one extent buffer
|
|
|
|
* @eb_context: to determine if we need to submit this page, if current page
|
|
|
|
* belongs to this eb, we don't need to submit
|
|
|
|
*
|
|
|
|
* The caller should pass each page in their bytenr order, and here we use
|
|
|
|
* @eb_context to determine if we have submitted pages of one extent buffer.
|
|
|
|
*
|
|
|
|
* If we have, we just skip until we hit a new page that doesn't belong to
|
|
|
|
* current @eb_context.
|
|
|
|
*
|
|
|
|
* If not, we submit all the page(s) of the extent buffer.
|
|
|
|
*
|
|
|
|
* Return >0 if we have submitted the extent buffer successfully.
|
|
|
|
* Return 0 if we don't need to submit the page, as it's already submitted by
|
|
|
|
* previous call.
|
|
|
|
* Return <0 for fatal error.
|
|
|
|
*/
|
|
|
|
static int submit_eb_page(struct page *page, struct writeback_control *wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl,
|
2020-12-02 14:48:00 +08:00
|
|
|
struct extent_buffer **eb_context)
|
|
|
|
{
|
|
|
|
struct address_space *mapping = page->mapping;
|
2021-02-04 18:22:08 +08:00
|
|
|
struct btrfs_block_group *cache = NULL;
|
2020-12-02 14:48:00 +08:00
|
|
|
struct extent_buffer *eb;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!PagePrivate(page))
|
|
|
|
return 0;
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
|
2022-10-27 19:07:05 +08:00
|
|
|
return submit_eb_subpage(page, wbc, bio_ctrl);
|
2021-04-06 08:36:03 +08:00
|
|
|
|
2020-12-02 14:48:00 +08:00
|
|
|
spin_lock(&mapping->private_lock);
|
|
|
|
if (!PagePrivate(page)) {
|
|
|
|
spin_unlock(&mapping->private_lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
eb = (struct extent_buffer *)page->private;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Shouldn't happen and normally this would be a BUG_ON but no point
|
|
|
|
* crashing the machine for something we can survive anyway.
|
|
|
|
*/
|
|
|
|
if (WARN_ON(!eb)) {
|
|
|
|
spin_unlock(&mapping->private_lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (eb == *eb_context) {
|
|
|
|
spin_unlock(&mapping->private_lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
ret = atomic_inc_not_zero(&eb->refs);
|
|
|
|
spin_unlock(&mapping->private_lock);
|
|
|
|
if (!ret)
|
|
|
|
return 0;
|
|
|
|
|
2021-02-04 18:22:08 +08:00
|
|
|
if (!btrfs_check_meta_write_pointer(eb->fs_info, eb, &cache)) {
|
|
|
|
/*
|
|
|
|
* If for_sync, this hole will be filled with
|
|
|
|
* trasnsaction commit.
|
|
|
|
*/
|
|
|
|
if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
|
|
|
|
ret = -EAGAIN;
|
|
|
|
else
|
|
|
|
ret = 0;
|
|
|
|
free_extent_buffer(eb);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2020-12-02 14:48:00 +08:00
|
|
|
*eb_context = eb;
|
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = lock_extent_buffer_for_io(eb, bio_ctrl);
|
2020-12-02 14:48:00 +08:00
|
|
|
if (ret <= 0) {
|
2021-02-04 18:22:08 +08:00
|
|
|
btrfs_revert_meta_write_pointer(cache, eb);
|
|
|
|
if (cache)
|
|
|
|
btrfs_put_block_group(cache);
|
2020-12-02 14:48:00 +08:00
|
|
|
free_extent_buffer(eb);
|
|
|
|
return ret;
|
|
|
|
}
|
2021-08-19 20:19:23 +08:00
|
|
|
if (cache) {
|
2022-03-07 21:30:02 +08:00
|
|
|
/*
|
|
|
|
* Implies write in zoned mode. Mark the last eb in a block group.
|
|
|
|
*/
|
2022-05-04 08:48:53 +08:00
|
|
|
btrfs_schedule_zone_finish_bg(cache, eb);
|
2022-03-07 21:30:02 +08:00
|
|
|
btrfs_put_block_group(cache);
|
2021-08-19 20:19:23 +08:00
|
|
|
}
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = write_one_eb(eb, wbc, bio_ctrl);
|
2020-12-02 14:48:00 +08:00
|
|
|
free_extent_buffer(eb);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2012-03-13 21:38:00 +08:00
|
|
|
int btree_write_cache_pages(struct address_space *mapping,
|
|
|
|
struct writeback_control *wbc)
|
|
|
|
{
|
2020-12-02 14:48:00 +08:00
|
|
|
struct extent_buffer *eb_context = NULL;
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl bio_ctrl = {
|
2012-03-13 21:38:00 +08:00
|
|
|
.extent_locked = 0,
|
2022-10-27 19:07:05 +08:00
|
|
|
.sync_io = (wbc->sync_mode == WB_SYNC_ALL),
|
2012-03-13 21:38:00 +08:00
|
|
|
};
|
btrfs: Don't submit any btree write bio if the fs has errors
[BUG]
There is a fuzzed image which could cause KASAN report at unmount time.
BUG: KASAN: use-after-free in btrfs_queue_work+0x2c1/0x390
Read of size 8 at addr ffff888067cf6848 by task umount/1922
CPU: 0 PID: 1922 Comm: umount Tainted: G W 5.0.21 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Call Trace:
dump_stack+0x5b/0x8b
print_address_description+0x70/0x280
kasan_report+0x13a/0x19b
btrfs_queue_work+0x2c1/0x390
btrfs_wq_submit_bio+0x1cd/0x240
btree_submit_bio_hook+0x18c/0x2a0
submit_one_bio+0x1be/0x320
flush_write_bio.isra.41+0x2c/0x70
btree_write_cache_pages+0x3bb/0x7f0
do_writepages+0x5c/0x130
__writeback_single_inode+0xa3/0x9a0
writeback_single_inode+0x23d/0x390
write_inode_now+0x1b5/0x280
iput+0x2ef/0x600
close_ctree+0x341/0x750
generic_shutdown_super+0x126/0x370
kill_anon_super+0x31/0x50
btrfs_kill_super+0x36/0x2b0
deactivate_locked_super+0x80/0xc0
deactivate_super+0x13c/0x150
cleanup_mnt+0x9a/0x130
task_work_run+0x11a/0x1b0
exit_to_usermode_loop+0x107/0x130
do_syscall_64+0x1e5/0x280
entry_SYSCALL_64_after_hwframe+0x44/0xa9
[CAUSE]
The fuzzed image has a completely screwd up extent tree:
leaf 29421568 gen 8 total ptrs 6 free space 3587 owner EXTENT_TREE
refs 2 lock (w:0 r:0 bw:0 br:0 sw:0 sr:0) lock_owner 0 current 5938
item 0 key (12587008 168 4096) itemoff 3942 itemsize 53
extent refs 1 gen 9 flags 1
ref#0: extent data backref root 5 objectid 259 offset 0 count 1
item 1 key (12591104 168 8192) itemoff 3889 itemsize 53
extent refs 1 gen 9 flags 1
ref#0: extent data backref root 5 objectid 271 offset 0 count 1
item 2 key (12599296 168 4096) itemoff 3836 itemsize 53
extent refs 1 gen 9 flags 1
ref#0: extent data backref root 5 objectid 259 offset 4096 count 1
item 3 key (29360128 169 0) itemoff 3803 itemsize 33
extent refs 1 gen 9 flags 2
ref#0: tree block backref root 5
item 4 key (29368320 169 1) itemoff 3770 itemsize 33
extent refs 1 gen 9 flags 2
ref#0: tree block backref root 5
item 5 key (29372416 169 0) itemoff 3737 itemsize 33
extent refs 1 gen 9 flags 2
ref#0: tree block backref root 5
Note that leaf 29421568 doesn't have its backref in the extent tree.
Thus extent allocator can re-allocate leaf 29421568 for other trees.
In short, the bug is caused by:
- Existing tree block gets allocated to log tree
This got its generation bumped.
- Log tree balance cleaned dirty bit of offending tree block
It will not be written back to disk, thus no WRITTEN flag.
- Original owner of the tree block gets COWed
Since the tree block has higher transid, no WRITTEN flag, it's reused,
and not traced by transaction::dirty_pages.
- Transaction aborted
Tree blocks get cleaned according to transaction::dirty_pages. But the
offending tree block is not recorded at all.
- Filesystem unmount
All pages are assumed to be are clean, destroying all workqueue, then
call iput(btree_inode).
But offending tree block is still dirty, which triggers writeback, and
causes use-after-free bug.
The detailed sequence looks like this:
- Initial status
eb: 29421568, header=WRITTEN bflags_dirty=0, page_dirty=0, gen=8,
not traced by any dirty extent_iot_tree.
- New tree block is allocated
Since there is no backref for 29421568, it's re-allocated as new tree
block.
Keep in mind that tree block 29421568 is still referred by extent
tree.
- Tree block 29421568 is filled for log tree
eb: 29421568, header=0 bflags_dirty=1, page_dirty=1, gen=9 << (gen bumped)
traced by btrfs_root::dirty_log_pages
- Some log tree operations
Since the fs is using node size 4096, the log tree can easily go a
level higher.
- Log tree needs balance
Tree block 29421568 gets all its content pushed to right, thus now
it is empty, and we don't need it.
btrfs_clean_tree_block() from __push_leaf_right() get called.
eb: 29421568, header=0 bflags_dirty=0, page_dirty=0, gen=9
traced by btrfs_root::dirty_log_pages
- Log tree write back
btree_write_cache_pages() goes through dirty pages ranges, but since
page of tree block 29421568 gets cleaned already, it's not written
back to disk. Thus it doesn't have WRITTEN bit set.
But ranges in dirty_log_pages are cleared.
eb: 29421568, header=0 bflags_dirty=0, page_dirty=0, gen=9
not traced by any dirty extent_iot_tree.
- Extent tree update when committing transaction
Since tree block 29421568 has transid equal to running trans, and has
no WRITTEN bit, should_cow_block() will use it directly without adding
it to btrfs_transaction::dirty_pages.
eb: 29421568, header=0 bflags_dirty=1, page_dirty=1, gen=9
not traced by any dirty extent_iot_tree.
At this stage, we're doomed. We have a dirty eb not tracked by any
extent io tree.
- Transaction gets aborted due to corrupted extent tree
Btrfs cleans up dirty pages according to transaction::dirty_pages and
btrfs_root::dirty_log_pages.
But since tree block 29421568 is not tracked by neither of them, it's
still dirty.
eb: 29421568, header=0 bflags_dirty=1, page_dirty=1, gen=9
not traced by any dirty extent_iot_tree.
- Filesystem unmount
Since all cleanup is assumed to be done, all workqueus are destroyed.
Then iput(btree_inode) is called, expecting no dirty pages.
But tree 29421568 is still dirty, thus triggering writeback.
Since all workqueues are already freed, we cause use-after-free.
This shows us that, log tree blocks + bad extent tree can cause wild
dirty pages.
[FIX]
To fix the problem, don't submit any btree write bio if the filesytem
has any error. This is the last safe net, just in case other cleanup
haven't caught catch it.
Link: https://github.com/bobfuzzer/CVE/tree/master/CVE-2019-19377
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-02-12 14:12:44 +08:00
|
|
|
struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info;
|
2012-03-13 21:38:00 +08:00
|
|
|
int ret = 0;
|
|
|
|
int done = 0;
|
|
|
|
int nr_to_write_done = 0;
|
|
|
|
struct pagevec pvec;
|
|
|
|
int nr_pages;
|
|
|
|
pgoff_t index;
|
|
|
|
pgoff_t end; /* Inclusive */
|
|
|
|
int scanned = 0;
|
2017-12-06 06:30:38 +08:00
|
|
|
xa_mark_t tag;
|
2012-03-13 21:38:00 +08:00
|
|
|
|
2017-11-16 09:37:52 +08:00
|
|
|
pagevec_init(&pvec);
|
2012-03-13 21:38:00 +08:00
|
|
|
if (wbc->range_cyclic) {
|
|
|
|
index = mapping->writeback_index; /* Start from prev offset */
|
|
|
|
end = -1;
|
2020-01-03 23:38:44 +08:00
|
|
|
/*
|
|
|
|
* Start from the beginning does not need to cycle over the
|
|
|
|
* range, mark it as scanned.
|
|
|
|
*/
|
|
|
|
scanned = (index == 0);
|
2012-03-13 21:38:00 +08:00
|
|
|
} else {
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
index = wbc->range_start >> PAGE_SHIFT;
|
|
|
|
end = wbc->range_end >> PAGE_SHIFT;
|
2012-03-13 21:38:00 +08:00
|
|
|
scanned = 1;
|
|
|
|
}
|
|
|
|
if (wbc->sync_mode == WB_SYNC_ALL)
|
|
|
|
tag = PAGECACHE_TAG_TOWRITE;
|
|
|
|
else
|
|
|
|
tag = PAGECACHE_TAG_DIRTY;
|
2021-02-04 18:22:08 +08:00
|
|
|
btrfs_zoned_meta_io_lock(fs_info);
|
2012-03-13 21:38:00 +08:00
|
|
|
retry:
|
|
|
|
if (wbc->sync_mode == WB_SYNC_ALL)
|
|
|
|
tag_pages_for_writeback(mapping, index, end);
|
|
|
|
while (!done && !nr_to_write_done && (index <= end) &&
|
2017-11-16 09:34:37 +08:00
|
|
|
(nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
|
2017-11-16 09:35:19 +08:00
|
|
|
tag))) {
|
2012-03-13 21:38:00 +08:00
|
|
|
unsigned i;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
|
|
struct page *page = pvec.pages[i];
|
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = submit_eb_page(page, wbc, &bio_ctrl, &eb_context);
|
2020-12-02 14:48:00 +08:00
|
|
|
if (ret == 0)
|
2012-03-13 21:38:00 +08:00
|
|
|
continue;
|
2020-12-02 14:48:00 +08:00
|
|
|
if (ret < 0) {
|
2012-03-13 21:38:00 +08:00
|
|
|
done = 1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* the filesystem may choose to bump up nr_to_write.
|
|
|
|
* We have to make sure to honor the new nr_to_write
|
|
|
|
* at any time
|
|
|
|
*/
|
|
|
|
nr_to_write_done = wbc->nr_to_write <= 0;
|
|
|
|
}
|
|
|
|
pagevec_release(&pvec);
|
|
|
|
cond_resched();
|
|
|
|
}
|
|
|
|
if (!scanned && !done) {
|
|
|
|
/*
|
|
|
|
* We hit the last page and there is more work to be done: wrap
|
|
|
|
* back to the start of the file
|
|
|
|
*/
|
|
|
|
scanned = 1;
|
|
|
|
index = 0;
|
|
|
|
goto retry;
|
|
|
|
}
|
btrfs: Don't submit any btree write bio if the fs has errors
[BUG]
There is a fuzzed image which could cause KASAN report at unmount time.
BUG: KASAN: use-after-free in btrfs_queue_work+0x2c1/0x390
Read of size 8 at addr ffff888067cf6848 by task umount/1922
CPU: 0 PID: 1922 Comm: umount Tainted: G W 5.0.21 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Call Trace:
dump_stack+0x5b/0x8b
print_address_description+0x70/0x280
kasan_report+0x13a/0x19b
btrfs_queue_work+0x2c1/0x390
btrfs_wq_submit_bio+0x1cd/0x240
btree_submit_bio_hook+0x18c/0x2a0
submit_one_bio+0x1be/0x320
flush_write_bio.isra.41+0x2c/0x70
btree_write_cache_pages+0x3bb/0x7f0
do_writepages+0x5c/0x130
__writeback_single_inode+0xa3/0x9a0
writeback_single_inode+0x23d/0x390
write_inode_now+0x1b5/0x280
iput+0x2ef/0x600
close_ctree+0x341/0x750
generic_shutdown_super+0x126/0x370
kill_anon_super+0x31/0x50
btrfs_kill_super+0x36/0x2b0
deactivate_locked_super+0x80/0xc0
deactivate_super+0x13c/0x150
cleanup_mnt+0x9a/0x130
task_work_run+0x11a/0x1b0
exit_to_usermode_loop+0x107/0x130
do_syscall_64+0x1e5/0x280
entry_SYSCALL_64_after_hwframe+0x44/0xa9
[CAUSE]
The fuzzed image has a completely screwd up extent tree:
leaf 29421568 gen 8 total ptrs 6 free space 3587 owner EXTENT_TREE
refs 2 lock (w:0 r:0 bw:0 br:0 sw:0 sr:0) lock_owner 0 current 5938
item 0 key (12587008 168 4096) itemoff 3942 itemsize 53
extent refs 1 gen 9 flags 1
ref#0: extent data backref root 5 objectid 259 offset 0 count 1
item 1 key (12591104 168 8192) itemoff 3889 itemsize 53
extent refs 1 gen 9 flags 1
ref#0: extent data backref root 5 objectid 271 offset 0 count 1
item 2 key (12599296 168 4096) itemoff 3836 itemsize 53
extent refs 1 gen 9 flags 1
ref#0: extent data backref root 5 objectid 259 offset 4096 count 1
item 3 key (29360128 169 0) itemoff 3803 itemsize 33
extent refs 1 gen 9 flags 2
ref#0: tree block backref root 5
item 4 key (29368320 169 1) itemoff 3770 itemsize 33
extent refs 1 gen 9 flags 2
ref#0: tree block backref root 5
item 5 key (29372416 169 0) itemoff 3737 itemsize 33
extent refs 1 gen 9 flags 2
ref#0: tree block backref root 5
Note that leaf 29421568 doesn't have its backref in the extent tree.
Thus extent allocator can re-allocate leaf 29421568 for other trees.
In short, the bug is caused by:
- Existing tree block gets allocated to log tree
This got its generation bumped.
- Log tree balance cleaned dirty bit of offending tree block
It will not be written back to disk, thus no WRITTEN flag.
- Original owner of the tree block gets COWed
Since the tree block has higher transid, no WRITTEN flag, it's reused,
and not traced by transaction::dirty_pages.
- Transaction aborted
Tree blocks get cleaned according to transaction::dirty_pages. But the
offending tree block is not recorded at all.
- Filesystem unmount
All pages are assumed to be are clean, destroying all workqueue, then
call iput(btree_inode).
But offending tree block is still dirty, which triggers writeback, and
causes use-after-free bug.
The detailed sequence looks like this:
- Initial status
eb: 29421568, header=WRITTEN bflags_dirty=0, page_dirty=0, gen=8,
not traced by any dirty extent_iot_tree.
- New tree block is allocated
Since there is no backref for 29421568, it's re-allocated as new tree
block.
Keep in mind that tree block 29421568 is still referred by extent
tree.
- Tree block 29421568 is filled for log tree
eb: 29421568, header=0 bflags_dirty=1, page_dirty=1, gen=9 << (gen bumped)
traced by btrfs_root::dirty_log_pages
- Some log tree operations
Since the fs is using node size 4096, the log tree can easily go a
level higher.
- Log tree needs balance
Tree block 29421568 gets all its content pushed to right, thus now
it is empty, and we don't need it.
btrfs_clean_tree_block() from __push_leaf_right() get called.
eb: 29421568, header=0 bflags_dirty=0, page_dirty=0, gen=9
traced by btrfs_root::dirty_log_pages
- Log tree write back
btree_write_cache_pages() goes through dirty pages ranges, but since
page of tree block 29421568 gets cleaned already, it's not written
back to disk. Thus it doesn't have WRITTEN bit set.
But ranges in dirty_log_pages are cleared.
eb: 29421568, header=0 bflags_dirty=0, page_dirty=0, gen=9
not traced by any dirty extent_iot_tree.
- Extent tree update when committing transaction
Since tree block 29421568 has transid equal to running trans, and has
no WRITTEN bit, should_cow_block() will use it directly without adding
it to btrfs_transaction::dirty_pages.
eb: 29421568, header=0 bflags_dirty=1, page_dirty=1, gen=9
not traced by any dirty extent_iot_tree.
At this stage, we're doomed. We have a dirty eb not tracked by any
extent io tree.
- Transaction gets aborted due to corrupted extent tree
Btrfs cleans up dirty pages according to transaction::dirty_pages and
btrfs_root::dirty_log_pages.
But since tree block 29421568 is not tracked by neither of them, it's
still dirty.
eb: 29421568, header=0 bflags_dirty=1, page_dirty=1, gen=9
not traced by any dirty extent_iot_tree.
- Filesystem unmount
Since all cleanup is assumed to be done, all workqueus are destroyed.
Then iput(btree_inode) is called, expecting no dirty pages.
But tree 29421568 is still dirty, thus triggering writeback.
Since all workqueues are already freed, we cause use-after-free.
This shows us that, log tree blocks + bad extent tree can cause wild
dirty pages.
[FIX]
To fix the problem, don't submit any btree write bio if the filesytem
has any error. This is the last safe net, just in case other cleanup
haven't caught catch it.
Link: https://github.com/bobfuzzer/CVE/tree/master/CVE-2019-19377
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-02-12 14:12:44 +08:00
|
|
|
/*
|
|
|
|
* If something went wrong, don't allow any metadata write bio to be
|
|
|
|
* submitted.
|
|
|
|
*
|
|
|
|
* This would prevent use-after-free if we had dirty pages not
|
|
|
|
* cleaned up, which can still happen by fuzzed images.
|
|
|
|
*
|
|
|
|
* - Bad extent tree
|
|
|
|
* Allowing existing tree block to be allocated for other trees.
|
|
|
|
*
|
|
|
|
* - Log tree operations
|
|
|
|
* Exiting tree blocks get allocated to log tree, bumps its
|
|
|
|
* generation, then get cleaned in tree re-balance.
|
|
|
|
* Such tree block will not be written back, since it's clean,
|
|
|
|
* thus no WRITTEN flag set.
|
|
|
|
* And after log writes back, this tree block is not traced by
|
|
|
|
* any dirty extent_io_tree.
|
|
|
|
*
|
|
|
|
* - Offending tree block gets re-dirtied from its original owner
|
|
|
|
* Since it has bumped generation, no WRITTEN flag, it can be
|
|
|
|
* reused without COWing. This tree block will not be traced
|
|
|
|
* by btrfs_transaction::dirty_pages.
|
|
|
|
*
|
|
|
|
* Now such dirty tree block will not be cleaned by any dirty
|
|
|
|
* extent io tree. Thus we don't want to submit such wild eb
|
|
|
|
* if the fs already has error.
|
2022-06-03 15:11:02 +08:00
|
|
|
*
|
btrfs: avoid double clean up when submit_one_bio() failed
[BUG]
When running generic/475 with 64K page size and 4K sector size, it has a
very high chance (almost 100%) to hang, with mostly data page locked but
no one is going to unlock it.
[CAUSE]
With commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads"), if we failed to lookup checksum due to metadata IO error, we
will return error for btrfs_submit_data_bio().
This will cause the page to be unlocked twice in btrfs_do_readpage():
btrfs_do_readpage()
|- submit_extent_page()
| |- submit_one_bio()
| |- btrfs_submit_data_bio()
| |- if (ret) {
| |- bio->bi_status = ret;
| |- bio_endio(bio); }
| In the endio function, we will call end_page_read()
| and unlock_extent() to cleanup the subpage range.
|
|- if (ret) {
|- unlock_extent(); end_page_read() }
Here we unlock the extent and cleanup the subpage range
again.
For unlock_extent(), it's mostly double unlock safe.
But for end_page_read(), it's not, especially for subpage case,
as for subpage case we will call btrfs_subpage_end_reader() to reduce
the reader number, and use that to number to determine if we need to
unlock the full page.
If double accounted, it can underflow the number and leave the page
locked without anyone to unlock it.
[FIX]
The commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads") itself is completely fine, it's our existing code not properly
handling the error from bio submission hook properly.
This patch will make submit_one_bio() to return void so that the callers
will never be able to do cleanup when bio submission hook fails.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:13 +08:00
|
|
|
* We can get ret > 0 from submit_extent_page() indicating how many ebs
|
|
|
|
* were submitted. Reset it to 0 to avoid false alerts for the caller.
|
|
|
|
*/
|
|
|
|
if (ret > 0)
|
|
|
|
ret = 0;
|
2022-06-03 15:11:02 +08:00
|
|
|
if (!ret && BTRFS_FS_ERROR(fs_info))
|
|
|
|
ret = -EROFS;
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(&bio_ctrl, ret);
|
2022-06-03 15:11:02 +08:00
|
|
|
|
|
|
|
btrfs_zoned_meta_io_unlock(fs_info);
|
2012-03-13 21:38:00 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
2021-01-22 17:58:03 +08:00
|
|
|
* Walk the list of dirty pages of the given address space and write all of them.
|
|
|
|
*
|
2022-10-27 19:07:05 +08:00
|
|
|
* @mapping: address space structure to write
|
|
|
|
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
|
|
|
|
* @bio_ctrl: holds context for the write, namely the bio
|
2008-01-25 05:13:08 +08:00
|
|
|
*
|
|
|
|
* If a page is already under I/O, write_cache_pages() skips it, even
|
|
|
|
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
|
|
|
|
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
|
|
|
|
* and msync() need to guarantee that all the data which was dirty at the time
|
|
|
|
* the call was made get new I/O started against them. If wbc->sync_mode is
|
|
|
|
* WB_SYNC_ALL then we were called for data integrity and we must wait for
|
|
|
|
* existing IO to complete.
|
|
|
|
*/
|
2017-02-11 02:38:24 +08:00
|
|
|
static int extent_write_cache_pages(struct address_space *mapping,
|
2008-09-08 23:18:08 +08:00
|
|
|
struct writeback_control *wbc,
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl *bio_ctrl)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2012-06-28 05:18:41 +08:00
|
|
|
struct inode *inode = mapping->host;
|
2008-01-25 05:13:08 +08:00
|
|
|
int ret = 0;
|
|
|
|
int done = 0;
|
2009-09-19 04:03:16 +08:00
|
|
|
int nr_to_write_done = 0;
|
2008-01-25 05:13:08 +08:00
|
|
|
struct pagevec pvec;
|
|
|
|
int nr_pages;
|
|
|
|
pgoff_t index;
|
|
|
|
pgoff_t end; /* Inclusive */
|
2016-03-08 08:56:21 +08:00
|
|
|
pgoff_t done_index;
|
|
|
|
int range_whole = 0;
|
2008-01-25 05:13:08 +08:00
|
|
|
int scanned = 0;
|
2017-12-06 06:30:38 +08:00
|
|
|
xa_mark_t tag;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2012-06-28 05:18:41 +08:00
|
|
|
/*
|
|
|
|
* We have to hold onto the inode so that ordered extents can do their
|
|
|
|
* work when the IO finishes. The alternative to this is failing to add
|
|
|
|
* an ordered extent if the igrab() fails there and that is a huge pain
|
|
|
|
* to deal with, so instead just hold onto the inode throughout the
|
|
|
|
* writepages operation. If it fails here we are freeing up the inode
|
|
|
|
* anyway and we'd rather not waste our time writing out stuff that is
|
|
|
|
* going to be truncated anyway.
|
|
|
|
*/
|
|
|
|
if (!igrab(inode))
|
|
|
|
return 0;
|
|
|
|
|
2017-11-16 09:37:52 +08:00
|
|
|
pagevec_init(&pvec);
|
2008-01-25 05:13:08 +08:00
|
|
|
if (wbc->range_cyclic) {
|
|
|
|
index = mapping->writeback_index; /* Start from prev offset */
|
|
|
|
end = -1;
|
2020-01-03 23:38:44 +08:00
|
|
|
/*
|
|
|
|
* Start from the beginning does not need to cycle over the
|
|
|
|
* range, mark it as scanned.
|
|
|
|
*/
|
|
|
|
scanned = (index == 0);
|
2008-01-25 05:13:08 +08:00
|
|
|
} else {
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
index = wbc->range_start >> PAGE_SHIFT;
|
|
|
|
end = wbc->range_end >> PAGE_SHIFT;
|
2016-03-08 08:56:21 +08:00
|
|
|
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
|
|
|
|
range_whole = 1;
|
2008-01-25 05:13:08 +08:00
|
|
|
scanned = 1;
|
|
|
|
}
|
2018-11-01 14:49:03 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We do the tagged writepage as long as the snapshot flush bit is set
|
|
|
|
* and we are the first one who do the filemap_flush() on this inode.
|
|
|
|
*
|
|
|
|
* The nr_to_write == LONG_MAX is needed to make sure other flushers do
|
|
|
|
* not race in and drop the bit.
|
|
|
|
*/
|
|
|
|
if (range_whole && wbc->nr_to_write == LONG_MAX &&
|
|
|
|
test_and_clear_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
|
|
|
|
&BTRFS_I(inode)->runtime_flags))
|
|
|
|
wbc->tagged_writepages = 1;
|
|
|
|
|
|
|
|
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
|
2011-07-16 05:26:38 +08:00
|
|
|
tag = PAGECACHE_TAG_TOWRITE;
|
|
|
|
else
|
|
|
|
tag = PAGECACHE_TAG_DIRTY;
|
2008-01-25 05:13:08 +08:00
|
|
|
retry:
|
2018-11-01 14:49:03 +08:00
|
|
|
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
|
2011-07-16 05:26:38 +08:00
|
|
|
tag_pages_for_writeback(mapping, index, end);
|
2016-03-08 08:56:21 +08:00
|
|
|
done_index = index;
|
2009-09-19 04:03:16 +08:00
|
|
|
while (!done && !nr_to_write_done && (index <= end) &&
|
2017-11-16 09:35:19 +08:00
|
|
|
(nr_pages = pagevec_lookup_range_tag(&pvec, mapping,
|
|
|
|
&index, end, tag))) {
|
2008-01-25 05:13:08 +08:00
|
|
|
unsigned i;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
|
|
struct page *page = pvec.pages[i];
|
|
|
|
|
btrfs: Avoid getting stuck during cyclic writebacks
During a cyclic writeback, extent_write_cache_pages() uses done_index
to update the writeback_index after the current run is over. However,
instead of current index + 1, it gets to to the current index itself.
Unfortunately, this, combined with returning on EOF instead of looping
back, can lead to the following pathlogical behavior.
1. There is a single file which has accumulated enough dirty pages to
trigger balance_dirty_pages() and the writer appending to the file
with a series of short writes.
2. balance_dirty_pages kicks in, wakes up background writeback and sleeps.
3. Writeback kicks in and the cursor is on the last page of the dirty
file. Writeback is started or skipped if already in progress. As
it's EOF, extent_write_cache_pages() returns and the cursor is set
to done_index which is pointing to the last page.
4. Writeback is done. Nothing happens till balance_dirty_pages
finishes, at which point we go back to #1.
This can almost completely stall out writing back of the file and keep
the system over dirty threshold for a long time which can mess up the
whole system. We encountered this issue in production with a package
handling application which can reliably reproduce the issue when
running under tight memory limits.
Reading the comment in the error handling section, this seems to be to
avoid accidentally skipping a page in case the write attempt on the
page doesn't succeed. However, this concern seems bogus.
On each page, the code either:
* Skips and moves onto the next page.
* Fails issue and sets done_index to index + 1.
* Successfully issues and continue to the next page if budget allows
and not EOF.
IOW, as long as it's not EOF and there's budget, the code never
retries writing back the same page. Only when a page happens to be
the last page of a particular run, we end up retrying the page, which
can't possibly guarantee anything data integrity related. Besides,
cyclic writes are only used for non-syncing writebacks meaning that
there's no data integrity implication to begin with.
Fix it by always setting done_index past the current page being
processed.
Note that this problem exists in other writepages too.
CC: stable@vger.kernel.org # 4.19+
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2019-10-03 22:27:13 +08:00
|
|
|
done_index = page->index + 1;
|
2008-01-25 05:13:08 +08:00
|
|
|
/*
|
2018-04-11 07:36:56 +08:00
|
|
|
* At this point we hold neither the i_pages lock nor
|
|
|
|
* the page lock: the page may be truncated or
|
|
|
|
* invalidated (changing page->mapping to NULL),
|
|
|
|
* or even swizzled back from swapper_space to
|
|
|
|
* tmpfs file mapping
|
2008-01-25 05:13:08 +08:00
|
|
|
*/
|
2013-02-12 00:33:00 +08:00
|
|
|
if (!trylock_page(page)) {
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(bio_ctrl, 0);
|
2013-02-12 00:33:00 +08:00
|
|
|
lock_page(page);
|
2011-11-01 22:08:06 +08:00
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
|
|
|
|
if (unlikely(page->mapping != mapping)) {
|
|
|
|
unlock_page(page);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2008-11-20 01:44:22 +08:00
|
|
|
if (wbc->sync_mode != WB_SYNC_NONE) {
|
btrfs: avoid double clean up when submit_one_bio() failed
[BUG]
When running generic/475 with 64K page size and 4K sector size, it has a
very high chance (almost 100%) to hang, with mostly data page locked but
no one is going to unlock it.
[CAUSE]
With commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads"), if we failed to lookup checksum due to metadata IO error, we
will return error for btrfs_submit_data_bio().
This will cause the page to be unlocked twice in btrfs_do_readpage():
btrfs_do_readpage()
|- submit_extent_page()
| |- submit_one_bio()
| |- btrfs_submit_data_bio()
| |- if (ret) {
| |- bio->bi_status = ret;
| |- bio_endio(bio); }
| In the endio function, we will call end_page_read()
| and unlock_extent() to cleanup the subpage range.
|
|- if (ret) {
|- unlock_extent(); end_page_read() }
Here we unlock the extent and cleanup the subpage range
again.
For unlock_extent(), it's mostly double unlock safe.
But for end_page_read(), it's not, especially for subpage case,
as for subpage case we will call btrfs_subpage_end_reader() to reduce
the reader number, and use that to number to determine if we need to
unlock the full page.
If double accounted, it can underflow the number and leave the page
locked without anyone to unlock it.
[FIX]
The commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads") itself is completely fine, it's our existing code not properly
handling the error from bio submission hook properly.
This patch will make submit_one_bio() to return void so that the callers
will never be able to do cleanup when bio submission hook fails.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:13 +08:00
|
|
|
if (PageWriteback(page))
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(bio_ctrl, 0);
|
2008-01-25 05:13:08 +08:00
|
|
|
wait_on_page_writeback(page);
|
2008-11-20 01:44:22 +08:00
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
|
|
|
|
if (PageWriteback(page) ||
|
|
|
|
!clear_page_dirty_for_io(page)) {
|
|
|
|
unlock_page(page);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = __extent_writepage(page, wbc, bio_ctrl);
|
2016-03-08 08:56:21 +08:00
|
|
|
if (ret < 0) {
|
|
|
|
done = 1;
|
|
|
|
break;
|
|
|
|
}
|
2009-09-19 04:03:16 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* the filesystem may choose to bump up nr_to_write.
|
|
|
|
* We have to make sure to honor the new nr_to_write
|
|
|
|
* at any time
|
|
|
|
*/
|
|
|
|
nr_to_write_done = wbc->nr_to_write <= 0;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
pagevec_release(&pvec);
|
|
|
|
cond_resched();
|
|
|
|
}
|
2016-03-08 08:56:22 +08:00
|
|
|
if (!scanned && !done) {
|
2008-01-25 05:13:08 +08:00
|
|
|
/*
|
|
|
|
* We hit the last page and there is more work to be done: wrap
|
|
|
|
* back to the start of the file
|
|
|
|
*/
|
|
|
|
scanned = 1;
|
|
|
|
index = 0;
|
2020-01-24 04:33:02 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If we're looping we could run into a page that is locked by a
|
|
|
|
* writer and that writer could be waiting on writeback for a
|
|
|
|
* page in our current bio, and thus deadlock, so flush the
|
|
|
|
* write bio here.
|
|
|
|
*/
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(bio_ctrl, 0);
|
btrfs: avoid double clean up when submit_one_bio() failed
[BUG]
When running generic/475 with 64K page size and 4K sector size, it has a
very high chance (almost 100%) to hang, with mostly data page locked but
no one is going to unlock it.
[CAUSE]
With commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads"), if we failed to lookup checksum due to metadata IO error, we
will return error for btrfs_submit_data_bio().
This will cause the page to be unlocked twice in btrfs_do_readpage():
btrfs_do_readpage()
|- submit_extent_page()
| |- submit_one_bio()
| |- btrfs_submit_data_bio()
| |- if (ret) {
| |- bio->bi_status = ret;
| |- bio_endio(bio); }
| In the endio function, we will call end_page_read()
| and unlock_extent() to cleanup the subpage range.
|
|- if (ret) {
|- unlock_extent(); end_page_read() }
Here we unlock the extent and cleanup the subpage range
again.
For unlock_extent(), it's mostly double unlock safe.
But for end_page_read(), it's not, especially for subpage case,
as for subpage case we will call btrfs_subpage_end_reader() to reduce
the reader number, and use that to number to determine if we need to
unlock the full page.
If double accounted, it can underflow the number and leave the page
locked without anyone to unlock it.
[FIX]
The commit 1784b7d502a9 ("btrfs: handle csum lookup errors properly on
reads") itself is completely fine, it's our existing code not properly
handling the error from bio submission hook properly.
This patch will make submit_one_bio() to return void so that the callers
will never be able to do cleanup when bio submission hook fails.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-04-12 20:30:13 +08:00
|
|
|
goto retry;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
2016-03-08 08:56:21 +08:00
|
|
|
|
|
|
|
if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
|
|
|
|
mapping->writeback_index = done_index;
|
|
|
|
|
2022-10-28 09:53:04 +08:00
|
|
|
btrfs_add_delayed_iput(BTRFS_I(inode));
|
2016-03-08 08:56:22 +08:00
|
|
|
return ret;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
/*
|
|
|
|
* Submit the pages in the range to bio for call sites which delalloc range has
|
|
|
|
* already been ran (aka, ordered extent inserted) and all pages are still
|
|
|
|
* locked.
|
|
|
|
*/
|
|
|
|
int extent_write_locked_range(struct inode *inode, u64 start, u64 end)
|
2008-11-07 11:02:51 +08:00
|
|
|
{
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
bool found_error = false;
|
|
|
|
int first_error = 0;
|
2008-11-07 11:02:51 +08:00
|
|
|
int ret = 0;
|
|
|
|
struct address_space *mapping = inode->i_mapping;
|
|
|
|
struct page *page;
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
u64 cur = start;
|
2021-09-27 15:22:02 +08:00
|
|
|
unsigned long nr_pages;
|
|
|
|
const u32 sectorsize = btrfs_sb(inode->i_sb)->sectorsize;
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl bio_ctrl = {
|
2008-11-07 11:02:51 +08:00
|
|
|
.extent_locked = 1,
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
.sync_io = 1,
|
2008-11-07 11:02:51 +08:00
|
|
|
};
|
|
|
|
struct writeback_control wbc_writepages = {
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
.sync_mode = WB_SYNC_ALL,
|
2008-11-07 11:02:51 +08:00
|
|
|
.range_start = start,
|
|
|
|
.range_end = end + 1,
|
2019-07-11 03:28:17 +08:00
|
|
|
/* We're called from an async helper function */
|
|
|
|
.punt_to_cgroup = 1,
|
|
|
|
.no_cgroup_owner = 1,
|
2008-11-07 11:02:51 +08:00
|
|
|
};
|
|
|
|
|
2021-09-27 15:22:02 +08:00
|
|
|
ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(end + 1, sectorsize));
|
|
|
|
nr_pages = (round_up(end, PAGE_SIZE) - round_down(start, PAGE_SIZE)) >>
|
|
|
|
PAGE_SHIFT;
|
|
|
|
wbc_writepages.nr_to_write = nr_pages * 2;
|
|
|
|
|
2019-07-11 03:28:18 +08:00
|
|
|
wbc_attach_fdatawrite_inode(&wbc_writepages, inode);
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
while (cur <= end) {
|
2021-09-27 15:22:02 +08:00
|
|
|
u64 cur_end = min(round_down(cur, PAGE_SIZE) + PAGE_SIZE - 1, end);
|
|
|
|
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
page = find_get_page(mapping, cur >> PAGE_SHIFT);
|
|
|
|
/*
|
|
|
|
* All pages in the range are locked since
|
|
|
|
* btrfs_run_delalloc_range(), thus there is no way to clear
|
|
|
|
* the page dirty flag.
|
|
|
|
*/
|
2021-09-27 15:22:02 +08:00
|
|
|
ASSERT(PageLocked(page));
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
ASSERT(PageDirty(page));
|
|
|
|
clear_page_dirty_for_io(page);
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = __extent_writepage(page, &wbc_writepages, &bio_ctrl);
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
ASSERT(ret <= 0);
|
|
|
|
if (ret < 0) {
|
|
|
|
found_error = true;
|
|
|
|
first_error = ret;
|
2008-11-07 11:02:51 +08:00
|
|
|
}
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
put_page(page);
|
2021-09-27 15:22:02 +08:00
|
|
|
cur = cur_end + 1;
|
2008-11-07 11:02:51 +08:00
|
|
|
}
|
|
|
|
|
2022-10-27 19:07:05 +08:00
|
|
|
submit_write_bio(&bio_ctrl, found_error ? ret : 0);
|
2019-07-11 03:28:18 +08:00
|
|
|
|
|
|
|
wbc_detach_inode(&wbc_writepages);
|
btrfs: cleanup for extent_write_locked_range()
There are several cleanups for extent_write_locked_range(), most of them
are pure cleanups, but with some preparation for future subpage support.
- Add a proper comment for which call sites are suitable
Unlike regular synchronized extent write back, if async COW or zoned
COW happens, we have all pages in the range still locked.
Thus for those (only) two call sites, we need this function to submit
page content into bios and submit them.
- Remove @mode parameter
All the existing two call sites pass WB_SYNC_ALL. No need for @mode
parameter.
- Better error handling
Currently if we hit an error during the page iteration loop, we
overwrite @ret, causing only the last error can be recorded.
Here we add @found_error and @first_error variable to record if we hit
any error, and the first error we hit.
So the first error won't get lost.
- Don't reuse @start as the cursor
We reuse the parameter @start as the cursor to iterate the range, not
a big problem, but since we're here, introduce a proper @cur as the
cursor.
- Remove impossible branch
Since all pages are still locked after the ordered extent is inserted,
there is no way that pages can get its dirty bit cleared.
Remove the branch where page is not dirty and replace it with an
ASSERT().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-09-27 15:21:58 +08:00
|
|
|
if (found_error)
|
|
|
|
return first_error;
|
2008-11-07 11:02:51 +08:00
|
|
|
return ret;
|
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2018-04-19 15:46:38 +08:00
|
|
|
int extent_writepages(struct address_space *mapping,
|
2008-01-25 05:13:08 +08:00
|
|
|
struct writeback_control *wbc)
|
|
|
|
{
|
2021-09-09 00:19:27 +08:00
|
|
|
struct inode *inode = mapping->host;
|
2008-01-25 05:13:08 +08:00
|
|
|
int ret = 0;
|
2022-10-27 19:07:05 +08:00
|
|
|
struct btrfs_bio_ctrl bio_ctrl = {
|
2008-11-07 11:02:51 +08:00
|
|
|
.extent_locked = 0,
|
2022-10-27 19:07:05 +08:00
|
|
|
.sync_io = (wbc->sync_mode == WB_SYNC_ALL),
|
2008-01-25 05:13:08 +08:00
|
|
|
};
|
|
|
|
|
2021-09-09 00:19:27 +08:00
|
|
|
/*
|
|
|
|
* Allow only a single thread to do the reloc work in zoned mode to
|
|
|
|
* protect the write pointer updates.
|
|
|
|
*/
|
2021-12-07 22:28:34 +08:00
|
|
|
btrfs_zoned_data_reloc_lock(BTRFS_I(inode));
|
2022-10-27 19:07:05 +08:00
|
|
|
ret = extent_write_cache_pages(mapping, wbc, &bio_ctrl);
|
|
|
|
submit_write_bio(&bio_ctrl, ret);
|
2022-06-07 15:08:30 +08:00
|
|
|
btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
|
2008-01-25 05:13:08 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2020-06-02 12:47:05 +08:00
|
|
|
void extent_readahead(struct readahead_control *rac)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
struct btrfs_bio_ctrl bio_ctrl = { 0 };
|
Btrfs: improve multi-thread buffer read
While testing with my buffer read fio jobs[1], I find that btrfs does not
perform well enough.
Here is a scenario in fio jobs:
We have 4 threads, "t1 t2 t3 t4", starting to buffer read a same file,
and all of them will race on add_to_page_cache_lru(), and if one thread
successfully puts its page into the page cache, it takes the responsibility
to read the page's data.
And what's more, reading a page needs a period of time to finish, in which
other threads can slide in and process rest pages:
t1 t2 t3 t4
add Page1
read Page1 add Page2
| read Page2 add Page3
| | read Page3 add Page4
| | | read Page4
-----|------------|-----------|-----------|--------
v v v v
bio bio bio bio
Now we have four bios, each of which holds only one page since we need to
maintain consecutive pages in bio. Thus, we can end up with far more bios
than we need.
Here we're going to
a) delay the real read-page section and
b) try to put more pages into page cache.
With that said, we can make each bio hold more pages and reduce the number
of bios we need.
Here is some numbers taken from fio results:
w/o patch w patch
------------- -------- ---------------
READ: 745MB/s +25% 934MB/s
[1]:
[global]
group_reporting
thread
numjobs=4
bs=32k
rw=read
ioengine=sync
directory=/mnt/btrfs/
[READ]
filename=foobar
size=2000M
invalidate=1
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
2012-07-21 11:43:09 +08:00
|
|
|
struct page *pagepool[16];
|
2013-07-25 19:22:37 +08:00
|
|
|
struct extent_map *em_cached = NULL;
|
2015-09-28 16:56:26 +08:00
|
|
|
u64 prev_em_start = (u64)-1;
|
2020-06-02 12:47:05 +08:00
|
|
|
int nr;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-06-02 12:47:05 +08:00
|
|
|
while ((nr = readahead_page_batch(rac, pagepool))) {
|
2021-03-22 05:03:11 +08:00
|
|
|
u64 contig_start = readahead_pos(rac);
|
|
|
|
u64 contig_end = contig_start + readahead_batch_length(rac) - 1;
|
2019-03-11 15:55:38 +08:00
|
|
|
|
2020-06-02 12:47:05 +08:00
|
|
|
contiguous_readpages(pagepool, nr, contig_start, contig_end,
|
btrfs: refactor submit_extent_page() to make bio and its flag tracing easier
There is a lot of code inside extent_io.c needs both "struct bio
**bio_ret" and "unsigned long prev_bio_flags", along with some
parameters like "unsigned long bio_flags".
Such strange parameters are here for bio assembly.
For example, we have such inode page layout:
0 4K 8K 12K
|<-- Extent A-->|<- EB->|
Then what we do is:
- Page [0, 4K)
*bio_ret = NULL
So we allocate a new bio to bio_ret,
Add page [0, 4K) to *bio_ret.
- Page [4K, 8K)
*bio_ret != NULL
We found this page is continuous to *bio_ret,
and if we're not at stripe boundary, we
add page [4K, 8K) to *bio_ret.
- Page [8K, 12K)
*bio_ret != NULL
But we found this page is not continuous, so
we submit *bio_ret, then allocate a new bio,
and add page [8K, 12K) to the new bio.
This means we need to record both the bio and its bio_flag, but we
record them manually using those strange parameter list, other than
encapsulating them into their own structure.
So this patch will introduce a new structure, btrfs_bio_ctrl, to record
both the bio, and its bio_flags.
Also, in above case, for all pages added to the bio, we need to check if
the new page crosses stripe boundary. This check itself can be time
consuming, and we don't really need to do that for each page.
This patch also integrates the stripe boundary check into btrfs_bio_ctrl.
When a new bio is allocated, the stripe and ordered extent boundary is
also calculated, so no matter how large the bio will be, we only
calculate the boundaries once, to save some CPU time.
The following functions/structures are affected:
- struct extent_page_data
Replace its bio pointer with structure btrfs_bio_ctrl (embedded
structure, not pointer)
- end_write_bio()
- flush_write_bio()
Just change how bio is fetched
- btrfs_bio_add_page()
Use pre-calculated boundaries instead of re-calculating them.
And use @bio_ctrl to replace @bio and @prev_bio_flags.
- calc_bio_boundaries()
New function
- submit_extent_page() callers
- btrfs_do_readpage() callers
- contiguous_readpages() callers
To Use @bio_ctrl to replace @bio and @prev_bio_flags, and how to grab
bio.
- btrfs_bio_fits_in_ordered_extent()
Removed, as now the ordered extent size limit is done at bio
allocation time, no need to check for each page range.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-04-14 16:42:15 +08:00
|
|
|
&em_cached, &bio_ctrl, &prev_em_start);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
Btrfs: improve multi-thread buffer read
While testing with my buffer read fio jobs[1], I find that btrfs does not
perform well enough.
Here is a scenario in fio jobs:
We have 4 threads, "t1 t2 t3 t4", starting to buffer read a same file,
and all of them will race on add_to_page_cache_lru(), and if one thread
successfully puts its page into the page cache, it takes the responsibility
to read the page's data.
And what's more, reading a page needs a period of time to finish, in which
other threads can slide in and process rest pages:
t1 t2 t3 t4
add Page1
read Page1 add Page2
| read Page2 add Page3
| | read Page3 add Page4
| | | read Page4
-----|------------|-----------|-----------|--------
v v v v
bio bio bio bio
Now we have four bios, each of which holds only one page since we need to
maintain consecutive pages in bio. Thus, we can end up with far more bios
than we need.
Here we're going to
a) delay the real read-page section and
b) try to put more pages into page cache.
With that said, we can make each bio hold more pages and reduce the number
of bios we need.
Here is some numbers taken from fio results:
w/o patch w patch
------------- -------- ---------------
READ: 745MB/s +25% 934MB/s
[1]:
[global]
group_reporting
thread
numjobs=4
bs=32k
rw=read
ioengine=sync
directory=/mnt/btrfs/
[READ]
filename=foobar
size=2000M
invalidate=1
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
2012-07-21 11:43:09 +08:00
|
|
|
|
2013-07-25 19:22:37 +08:00
|
|
|
if (em_cached)
|
|
|
|
free_extent_map(em_cached);
|
2022-06-03 15:11:03 +08:00
|
|
|
submit_one_bio(&bio_ctrl);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2022-02-10 04:21:39 +08:00
|
|
|
* basic invalidate_folio code, this waits on any locked or writeback
|
|
|
|
* ranges corresponding to the folio, and then deletes any extent state
|
2008-01-25 05:13:08 +08:00
|
|
|
* records from the tree
|
|
|
|
*/
|
2022-02-10 04:21:39 +08:00
|
|
|
int extent_invalidate_folio(struct extent_io_tree *tree,
|
|
|
|
struct folio *folio, size_t offset)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2010-02-04 03:33:23 +08:00
|
|
|
struct extent_state *cached_state = NULL;
|
2022-02-10 04:21:39 +08:00
|
|
|
u64 start = folio_pos(folio);
|
|
|
|
u64 end = start + folio_size(folio) - 1;
|
|
|
|
size_t blocksize = folio->mapping->host->i_sb->s_blocksize;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-11-13 20:51:39 +08:00
|
|
|
/* This function is only called for the btree inode */
|
|
|
|
ASSERT(tree->owner == IO_TREE_BTREE_INODE_IO);
|
|
|
|
|
2013-02-26 16:10:22 +08:00
|
|
|
start += ALIGN(offset, blocksize);
|
2008-01-25 05:13:08 +08:00
|
|
|
if (start > end)
|
|
|
|
return 0;
|
|
|
|
|
2022-09-10 05:53:43 +08:00
|
|
|
lock_extent(tree, start, end, &cached_state);
|
2022-02-10 04:21:39 +08:00
|
|
|
folio_wait_writeback(folio);
|
2020-11-13 20:51:39 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Currently for btree io tree, only EXTENT_LOCKED is utilized,
|
|
|
|
* so here we only need to unlock the extent range to free any
|
|
|
|
* existing extent state.
|
|
|
|
*/
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(tree, start, end, &cached_state);
|
2008-01-25 05:13:08 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-04-18 22:29:50 +08:00
|
|
|
/*
|
2022-05-01 11:15:16 +08:00
|
|
|
* a helper for release_folio, this tests for areas of the page that
|
2008-04-18 22:29:50 +08:00
|
|
|
* are locked or under IO and drops the related state bits if it is safe
|
|
|
|
* to drop the page.
|
|
|
|
*/
|
2018-04-19 15:46:35 +08:00
|
|
|
static int try_release_extent_state(struct extent_io_tree *tree,
|
2013-04-26 04:41:01 +08:00
|
|
|
struct page *page, gfp_t mask)
|
2008-04-18 22:29:50 +08:00
|
|
|
{
|
2012-12-21 17:17:45 +08:00
|
|
|
u64 start = page_offset(page);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
u64 end = start + PAGE_SIZE - 1;
|
2008-04-18 22:29:50 +08:00
|
|
|
int ret = 1;
|
|
|
|
|
2019-03-14 21:28:31 +08:00
|
|
|
if (test_range_bit(tree, start, end, EXTENT_LOCKED, 0, NULL)) {
|
2008-04-18 22:29:50 +08:00
|
|
|
ret = 0;
|
2019-03-14 21:28:31 +08:00
|
|
|
} else {
|
2022-09-10 05:53:46 +08:00
|
|
|
u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM |
|
|
|
|
EXTENT_DELALLOC_NEW | EXTENT_CTLBITS);
|
|
|
|
|
2009-09-24 08:28:46 +08:00
|
|
|
/*
|
btrfs: update the number of bytes used by an inode atomically
There are several occasions where we do not update the inode's number of
used bytes atomically, resulting in a concurrent stat(2) syscall to report
a value of used blocks that does not correspond to a valid value, that is,
a value that does not match neither what we had before the operation nor
what we get after the operation completes.
In extreme cases it can result in stat(2) reporting zero used blocks, which
can cause problems for some userspace tools where they can consider a file
with a non-zero size and zero used blocks as completely sparse and skip
reading data, as reported/discussed a long time ago in some threads like
the following:
https://lists.gnu.org/archive/html/bug-tar/2016-07/msg00001.html
The cases where this can happen are the following:
-> Case 1
If we do a write (buffered or direct IO) against a file region for which
there is already an allocated extent (or multiple extents), then we have a
short time window where we can report a number of used blocks to stat(2)
that does not take into account the file region being overwritten. This
short time window happens when completing the ordered extent(s).
This happens because when we drop the extents in the write range we
decrement the inode's number of bytes and later on when we insert the new
extent(s) we increment the number of bytes in the inode, resulting in a
short time window where a stat(2) syscall can get an incorrect number of
used blocks.
If we do writes that overwrite an entire file, then we have a short time
window where we report 0 used blocks to stat(2).
Example reproducer:
$ cat reproducer-1.sh
#!/bin/bash
MNT=/mnt/sdi
DEV=/dev/sdi
stat_loop()
{
trap "wait; exit" SIGTERM
local filepath=$1
local expected=$2
local got
while :; do
got=$(stat -c %b $filepath)
if [ $got -ne $expected ]; then
echo -n "ERROR: unexpected used blocks"
echo " (got: $got expected: $expected)"
fi
done
}
mkfs.btrfs -f $DEV > /dev/null
# mkfs.xfs -f $DEV > /dev/null
# mkfs.ext4 -F $DEV > /dev/null
# mkfs.f2fs -f $DEV > /dev/null
# mkfs.reiserfs -f $DEV > /dev/null
mount $DEV $MNT
xfs_io -f -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null
expected=$(stat -c %b $MNT/foobar)
# Create a process to keep calling stat(2) on the file and see if the
# reported number of blocks used (disk space used) changes, it should
# not because we are not increasing the file size nor punching holes.
stat_loop $MNT/foobar $expected &
loop_pid=$!
for ((i = 0; i < 50000; i++)); do
xfs_io -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null
done
kill $loop_pid &> /dev/null
wait
umount $DEV
$ ./reproducer-1.sh
ERROR: unexpected used blocks (got: 0 expected: 128)
ERROR: unexpected used blocks (got: 0 expected: 128)
(...)
Note that since this is a short time window where the race can happen, the
reproducer may not be able to always trigger the bug in one run, or it may
trigger it multiple times.
-> Case 2
If we do a buffered write against a file region that does not have any
allocated extents, like a hole or beyond EOF, then during ordered extent
completion we have a short time window where a concurrent stat(2) syscall
can report a number of used blocks that does not correspond to the value
before or after the write operation, a value that is actually larger than
the value after the write completes.
This happens because once we start a buffered write into an unallocated
file range we increment the inode's 'new_delalloc_bytes', to make sure
any stat(2) call gets a correct used blocks value before delalloc is
flushed and completes. However at ordered extent completion, after we
inserted the new extent, we increment the inode's number of bytes used
with the size of the new extent, and only later, when clearing the range
in the inode's iotree, we decrement the inode's 'new_delalloc_bytes'
counter with the size of the extent. So this results in a short time
window where a concurrent stat(2) syscall can report a number of used
blocks that accounts for the new extent twice.
Example reproducer:
$ cat reproducer-2.sh
#!/bin/bash
MNT=/mnt/sdi
DEV=/dev/sdi
stat_loop()
{
trap "wait; exit" SIGTERM
local filepath=$1
local expected=$2
local got
while :; do
got=$(stat -c %b $filepath)
if [ $got -ne $expected ]; then
echo -n "ERROR: unexpected used blocks"
echo " (got: $got expected: $expected)"
fi
done
}
mkfs.btrfs -f $DEV > /dev/null
# mkfs.xfs -f $DEV > /dev/null
# mkfs.ext4 -F $DEV > /dev/null
# mkfs.f2fs -f $DEV > /dev/null
# mkfs.reiserfs -f $DEV > /dev/null
mount $DEV $MNT
touch $MNT/foobar
write_size=$((64 * 1024))
for ((i = 0; i < 16384; i++)); do
offset=$(($i * $write_size))
xfs_io -c "pwrite -S 0xab $offset $write_size" $MNT/foobar >/dev/null
blocks_used=$(stat -c %b $MNT/foobar)
# Fsync the file to trigger writeback and keep calling stat(2) on it
# to see if the number of blocks used changes.
stat_loop $MNT/foobar $blocks_used &
loop_pid=$!
xfs_io -c "fsync" $MNT/foobar
kill $loop_pid &> /dev/null
wait $loop_pid
done
umount $DEV
$ ./reproducer-2.sh
ERROR: unexpected used blocks (got: 265472 expected: 265344)
ERROR: unexpected used blocks (got: 284032 expected: 283904)
(...)
Note that since this is a short time window where the race can happen, the
reproducer may not be able to always trigger the bug in one run, or it may
trigger it multiple times.
-> Case 3
Another case where such problems happen is during other operations that
replace extents in a file range with other extents. Those operations are
extent cloning, deduplication and fallocate's zero range operation.
The cause of the problem is similar to the first case. When we drop the
extents from a range, we decrement the inode's number of bytes, and later
on, after inserting the new extents we increment it. Since this is not
done atomically, a concurrent stat(2) call can see and return a number of
used blocks that is smaller than it should be, does not match the number
of used blocks before or after the clone/deduplication/zero operation.
Like for the first case, when doing a clone, deduplication or zero range
operation against an entire file, we end up having a time window where we
can report 0 used blocks to a stat(2) call.
Example reproducer:
$ cat reproducer-3.sh
#!/bin/bash
MNT=/mnt/sdi
DEV=/dev/sdi
mkfs.btrfs -f $DEV > /dev/null
# mkfs.xfs -f -m reflink=1 $DEV > /dev/null
mount $DEV $MNT
extent_size=$((64 * 1024))
num_extents=16384
file_size=$(($extent_size * $num_extents))
# File foo has many small extents.
xfs_io -f -s -c "pwrite -S 0xab -b $extent_size 0 $file_size" $MNT/foo \
> /dev/null
# File bar has much less extents and has exactly the same data as foo.
xfs_io -f -c "pwrite -S 0xab 0 $file_size" $MNT/bar > /dev/null
expected=$(stat -c %b $MNT/foo)
# Now deduplicate bar into foo. While the deduplication is in progres,
# the number of used blocks/file size reported by stat should not change
xfs_io -c "dedupe $MNT/bar 0 0 $file_size" $MNT/foo > /dev/null &
dedupe_pid=$!
while [ -n "$(ps -p $dedupe_pid -o pid=)" ]; do
used=$(stat -c %b $MNT/foo)
if [ $used -ne $expected ]; then
echo "Unexpected blocks used: $used (expected: $expected)"
fi
done
umount $DEV
$ ./reproducer-3.sh
Unexpected blocks used: 2076800 (expected: 2097152)
Unexpected blocks used: 2097024 (expected: 2097152)
Unexpected blocks used: 2079872 (expected: 2097152)
(...)
Note that since this is a short time window where the race can happen, the
reproducer may not be able to always trigger the bug in one run, or it may
trigger it multiple times.
So fix this by:
1) Making btrfs_drop_extents() not decrement the VFS inode's number of
bytes, and instead return the number of bytes;
2) Making any code that drops extents and adds new extents update the
inode's number of bytes atomically, while holding the btrfs inode's
spinlock, which is also used by the stat(2) callback to get the inode's
number of bytes;
3) For ranges in the inode's iotree that are marked as 'delalloc new',
corresponding to previously unallocated ranges, increment the inode's
number of bytes when clearing the 'delalloc new' bit from the range,
in the same critical section that decrements the inode's
'new_delalloc_bytes' counter, delimited by the btrfs inode's spinlock.
An alternative would be to have btrfs_getattr() wait for any IO (ordered
extents in progress) and locking the whole range (0 to (u64)-1) while it
it computes the number of blocks used. But that would mean blocking
stat(2), which is a very used syscall and expected to be fast, waiting
for writes, clone/dedupe, fallocate, page reads, fiemap, etc.
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-04 19:07:34 +08:00
|
|
|
* At this point we can safely clear everything except the
|
|
|
|
* locked bit, the nodatasum bit and the delalloc new bit.
|
|
|
|
* The delalloc new bit will be cleared by ordered extent
|
|
|
|
* completion.
|
2009-09-24 08:28:46 +08:00
|
|
|
*/
|
2022-09-10 05:53:47 +08:00
|
|
|
ret = __clear_extent_bit(tree, start, end, clear_bits, NULL,
|
2022-09-10 05:53:46 +08:00
|
|
|
mask, NULL);
|
2011-02-15 01:52:08 +08:00
|
|
|
|
|
|
|
/* if clear_extent_bit failed for enomem reasons,
|
|
|
|
* we can't allow the release to continue.
|
|
|
|
*/
|
|
|
|
if (ret < 0)
|
|
|
|
ret = 0;
|
|
|
|
else
|
|
|
|
ret = 1;
|
2008-04-18 22:29:50 +08:00
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
/*
|
2022-05-01 11:15:16 +08:00
|
|
|
* a helper for release_folio. As long as there are no locked extents
|
2008-01-25 05:13:08 +08:00
|
|
|
* in the range corresponding to the page, both state records and extent
|
|
|
|
* map records are removed
|
|
|
|
*/
|
2018-04-19 15:46:34 +08:00
|
|
|
int try_release_extent_mapping(struct page *page, gfp_t mask)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
struct extent_map *em;
|
2012-12-21 17:17:45 +08:00
|
|
|
u64 start = page_offset(page);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
u64 end = start + PAGE_SIZE - 1;
|
Btrfs: fix file data corruption after cloning a range and fsync
When we clone a range into a file we can end up dropping existing
extent maps (or trimming them) and replacing them with new ones if the
range to be cloned overlaps with a range in the destination inode.
When that happens we add the new extent maps to the list of modified
extents in the inode's extent map tree, so that a "fast" fsync (the flag
BTRFS_INODE_NEEDS_FULL_SYNC not set in the inode) will see the extent maps
and log corresponding extent items. However, at the end of range cloning
operation we do truncate all the pages in the affected range (in order to
ensure future reads will not get stale data). Sometimes this truncation
will release the corresponding extent maps besides the pages from the page
cache. If this happens, then a "fast" fsync operation will miss logging
some extent items, because it relies exclusively on the extent maps being
present in the inode's extent tree, leading to data loss/corruption if
the fsync ends up using the same transaction used by the clone operation
(that transaction was not committed in the meanwhile). An extent map is
released through the callback btrfs_invalidatepage(), which gets called by
truncate_inode_pages_range(), and it calls __btrfs_releasepage(). The
later ends up calling try_release_extent_mapping() which will release the
extent map if some conditions are met, like the file size being greater
than 16Mb, gfp flags allow blocking and the range not being locked (which
is the case during the clone operation) nor being the extent map flagged
as pinned (also the case for cloning).
The following example, turned into a test for fstests, reproduces the
issue:
$ mkfs.btrfs -f /dev/sdb
$ mount /dev/sdb /mnt
$ xfs_io -f -c "pwrite -S 0x18 9000K 6908K" /mnt/foo
$ xfs_io -f -c "pwrite -S 0x20 2572K 156K" /mnt/bar
$ xfs_io -c "fsync" /mnt/bar
# reflink destination offset corresponds to the size of file bar,
# 2728Kb minus 4Kb.
$ xfs_io -c ""reflink ${SCRATCH_MNT}/foo 0 2724K 15908K" /mnt/bar
$ xfs_io -c "fsync" /mnt/bar
$ md5sum /mnt/bar
95a95813a8c2abc9aa75a6c2914a077e /mnt/bar
<power fail>
$ mount /dev/sdb /mnt
$ md5sum /mnt/bar
207fd8d0b161be8a84b945f0df8d5f8d /mnt/bar
# digest should be 95a95813a8c2abc9aa75a6c2914a077e like before the
# power failure
In the above example, the destination offset of the clone operation
corresponds to the size of the "bar" file minus 4Kb. So during the clone
operation, the extent map covering the range from 2572Kb to 2728Kb gets
trimmed so that it ends at offset 2724Kb, and a new extent map covering
the range from 2724Kb to 11724Kb is created. So at the end of the clone
operation when we ask to truncate the pages in the range from 2724Kb to
2724Kb + 15908Kb, the page invalidation callback ends up removing the new
extent map (through try_release_extent_mapping()) when the page at offset
2724Kb is passed to that callback.
Fix this by setting the bit BTRFS_INODE_NEEDS_FULL_SYNC whenever an extent
map is removed at try_release_extent_mapping(), forcing the next fsync to
search for modified extents in the fs/subvolume tree instead of relying on
the presence of extent maps in memory. This way we can continue doing a
"fast" fsync if the destination range of a clone operation does not
overlap with an existing range or if any of the criteria necessary to
remove an extent map at try_release_extent_mapping() is not met (file
size not bigger then 16Mb or gfp flags do not allow blocking).
CC: stable@vger.kernel.org # 3.16+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2018-07-12 08:36:43 +08:00
|
|
|
struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host);
|
|
|
|
struct extent_io_tree *tree = &btrfs_inode->io_tree;
|
|
|
|
struct extent_map_tree *map = &btrfs_inode->extent_tree;
|
2008-04-18 22:29:50 +08:00
|
|
|
|
2015-11-07 08:28:21 +08:00
|
|
|
if (gfpflags_allow_blocking(mask) &&
|
2015-12-15 00:42:10 +08:00
|
|
|
page->mapping->host->i_size > SZ_16M) {
|
2008-02-15 23:40:50 +08:00
|
|
|
u64 len;
|
2008-01-29 22:59:12 +08:00
|
|
|
while (start <= end) {
|
2020-07-22 19:28:52 +08:00
|
|
|
struct btrfs_fs_info *fs_info;
|
|
|
|
u64 cur_gen;
|
|
|
|
|
2008-02-15 23:40:50 +08:00
|
|
|
len = end - start + 1;
|
2009-09-03 04:24:52 +08:00
|
|
|
write_lock(&map->lock);
|
2008-02-15 23:40:50 +08:00
|
|
|
em = lookup_extent_mapping(map, start, len);
|
2012-02-16 15:23:58 +08:00
|
|
|
if (!em) {
|
2009-09-03 04:24:52 +08:00
|
|
|
write_unlock(&map->lock);
|
2008-01-29 22:59:12 +08:00
|
|
|
break;
|
|
|
|
}
|
2008-07-19 00:01:11 +08:00
|
|
|
if (test_bit(EXTENT_FLAG_PINNED, &em->flags) ||
|
|
|
|
em->start != start) {
|
2009-09-03 04:24:52 +08:00
|
|
|
write_unlock(&map->lock);
|
2008-01-29 22:59:12 +08:00
|
|
|
free_extent_map(em);
|
|
|
|
break;
|
|
|
|
}
|
btrfs: fix race between page release and a fast fsync
When releasing an extent map, done through the page release callback, we
can race with an ongoing fast fsync and cause the fsync to miss a new
extent and not log it. The steps for this to happen are the following:
1) A page is dirtied for some inode I;
2) Writeback for that page is triggered by a path other than fsync, for
example by the system due to memory pressure;
3) When the ordered extent for the extent (a single 4K page) finishes,
we unpin the corresponding extent map and set its generation to N,
the current transaction's generation;
4) The btrfs_releasepage() callback is invoked by the system due to
memory pressure for that no longer dirty page of inode I;
5) At the same time, some task calls fsync on inode I, joins transaction
N, and at btrfs_log_inode() it sees that the inode does not have the
full sync flag set, so we proceed with a fast fsync. But before we get
into btrfs_log_changed_extents() and lock the inode's extent map tree:
6) Through btrfs_releasepage() we end up at try_release_extent_mapping()
and we remove the extent map for the new 4Kb extent, because it is
neither pinned anymore nor locked. By calling remove_extent_mapping(),
we remove the extent map from the list of modified extents, since the
extent map does not have the logging flag set. We unlock the inode's
extent map tree;
7) The task doing the fast fsync now enters btrfs_log_changed_extents(),
locks the inode's extent map tree and iterates its list of modified
extents, which no longer has the 4Kb extent in it, so it does not log
the extent;
8) The fsync finishes;
9) Before transaction N is committed, a power failure happens. After
replaying the log, the 4K extent of inode I will be missing, since
it was not logged due to the race with try_release_extent_mapping().
So fix this by teaching try_release_extent_mapping() to not remove an
extent map if it's still in the list of modified extents.
Fixes: ff44c6e36dc9dc ("Btrfs: do not hold the write_lock on the extent tree while logging")
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-22 19:28:37 +08:00
|
|
|
if (test_range_bit(tree, em->start,
|
|
|
|
extent_map_end(em) - 1,
|
|
|
|
EXTENT_LOCKED, 0, NULL))
|
|
|
|
goto next;
|
|
|
|
/*
|
|
|
|
* If it's not in the list of modified extents, used
|
|
|
|
* by a fast fsync, we can remove it. If it's being
|
|
|
|
* logged we can safely remove it since fsync took an
|
|
|
|
* extra reference on the em.
|
|
|
|
*/
|
|
|
|
if (list_empty(&em->list) ||
|
2020-07-22 19:28:52 +08:00
|
|
|
test_bit(EXTENT_FLAG_LOGGING, &em->flags))
|
|
|
|
goto remove_em;
|
|
|
|
/*
|
|
|
|
* If it's in the list of modified extents, remove it
|
|
|
|
* only if its generation is older then the current one,
|
|
|
|
* in which case we don't need it for a fast fsync.
|
|
|
|
* Otherwise don't remove it, we could be racing with an
|
|
|
|
* ongoing fast fsync that could miss the new extent.
|
|
|
|
*/
|
|
|
|
fs_info = btrfs_inode->root->fs_info;
|
|
|
|
spin_lock(&fs_info->trans_lock);
|
|
|
|
cur_gen = fs_info->generation;
|
|
|
|
spin_unlock(&fs_info->trans_lock);
|
|
|
|
if (em->generation >= cur_gen)
|
|
|
|
goto next;
|
|
|
|
remove_em:
|
btrfs: do not set the full sync flag on the inode during page release
When removing an extent map at try_release_extent_mapping(), called through
the page release callback (btrfs_releasepage()), we always set the full
sync flag on the inode, which forces the next fsync to use a slower code
path.
This hurts performance for workloads that dirty an amount of data that
exceeds or is very close to the system's RAM memory and do frequent fsync
operations (like database servers can for example). In particular if there
are concurrent fsyncs against different files, by falling back to a full
fsync we do a lot more checksum lookups in the checksums btree, as we do
it for all the extents created in the current transaction, instead of only
the new ones since the last fsync. These checksums lookups not only take
some time but, more importantly, they also cause contention on the
checksums btree locks due to the concurrency with checksum insertions in
the btree by ordered extents from other inodes.
We actually don't need to set the full sync flag on the inode, because we
only remove extent maps that are in the list of modified extents if they
were created in a past transaction, in which case an fsync skips them as
it's pointless to log them. So stop setting the full fsync flag on the
inode whenever we remove an extent map.
This patch is part of a patchset that consists of 3 patches, which have
the following subjects:
1/3 btrfs: fix race between page release and a fast fsync
2/3 btrfs: release old extent maps during page release
3/3 btrfs: do not set the full sync flag on the inode during page release
Performance tests were ran against a branch (misc-next) containing the
whole patchset. The test exercises a workload where there are multiple
processes writing to files and fsyncing them (each writing and fsyncing
its own file), and in total the amount of data dirtied ranges from 2x to
4x the system's RAM memory (16GiB), so that the page release callback is
invoked frequently.
The following script, using fio, was used to perform the tests:
$ cat test-fsync.sh
#!/bin/bash
DEV=/dev/sdk
MNT=/mnt/sdk
MOUNT_OPTIONS="-o ssd"
MKFS_OPTIONS="-d single -m single"
if [ $# -ne 3 ]; then
echo "Use $0 NUM_JOBS FILE_SIZE FSYNC_FREQ"
exit 1
fi
NUM_JOBS=$1
FILE_SIZE=$2
FSYNC_FREQ=$3
cat <<EOF > /tmp/fio-job.ini
[writers]
rw=write
fsync=$FSYNC_FREQ
fallocate=none
group_reporting=1
direct=0
bs=64k
ioengine=sync
size=$FILE_SIZE
directory=$MNT
numjobs=$NUM_JOBS
thread
EOF
echo "Using config:"
echo
cat /tmp/fio-job.ini
echo
mkfs.btrfs -f $MKFS_OPTIONS $DEV &> /dev/null
mount $MOUNT_OPTIONS $DEV $MNT
fio /tmp/fio-job.ini
umount $MNT
The tests were performed for different numbers of jobs, file sizes and
fsync frequency. A qemu VM using kvm was used, with 8 cores (the host has
12 cores, with cpu governance set to performance mode on all cores), 16GiB
of ram (the host has 64GiB) and using a NVMe device directly (without an
intermediary filesystem in the host). While running the tests, the host
was not used for anything else, to avoid disturbing the tests.
The obtained results were the following, and the last line printed by
fio is pasted (includes aggregated throughput and test run time).
*****************************************************
**** 1 job, 32GiB file, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=29.1MiB/s (30.5MB/s), 29.1MiB/s-29.1MiB/s (30.5MB/s-30.5MB/s), io=32.0GiB (34.4GB), run=1127557-1127557msec
After patchset:
WRITE: bw=29.3MiB/s (30.7MB/s), 29.3MiB/s-29.3MiB/s (30.7MB/s-30.7MB/s), io=32.0GiB (34.4GB), run=1119042-1119042msec
(+0.7% throughput, -0.8% run time)
*****************************************************
**** 2 jobs, 16GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=33.5MiB/s (35.1MB/s), 33.5MiB/s-33.5MiB/s (35.1MB/s-35.1MB/s), io=32.0GiB (34.4GB), run=979000-979000msec
After patchset:
WRITE: bw=39.9MiB/s (41.8MB/s), 39.9MiB/s-39.9MiB/s (41.8MB/s-41.8MB/s), io=32.0GiB (34.4GB), run=821283-821283msec
(+19.1% throughput, -16.1% runtime)
*****************************************************
**** 4 jobs, 8GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=52.1MiB/s (54.6MB/s), 52.1MiB/s-52.1MiB/s (54.6MB/s-54.6MB/s), io=32.0GiB (34.4GB), run=629130-629130msec
After patchset:
WRITE: bw=71.8MiB/s (75.3MB/s), 71.8MiB/s-71.8MiB/s (75.3MB/s-75.3MB/s), io=32.0GiB (34.4GB), run=456357-456357msec
(+37.8% throughput, -27.5% runtime)
*****************************************************
**** 8 jobs, 4GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=76.1MiB/s (79.8MB/s), 76.1MiB/s-76.1MiB/s (79.8MB/s-79.8MB/s), io=32.0GiB (34.4GB), run=430708-430708msec
After patchset:
WRITE: bw=133MiB/s (140MB/s), 133MiB/s-133MiB/s (140MB/s-140MB/s), io=32.0GiB (34.4GB), run=245458-245458msec
(+74.7% throughput, -43.0% run time)
*****************************************************
**** 16 jobs, 2GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=74.7MiB/s (78.3MB/s), 74.7MiB/s-74.7MiB/s (78.3MB/s-78.3MB/s), io=32.0GiB (34.4GB), run=438625-438625msec
After patchset:
WRITE: bw=184MiB/s (193MB/s), 184MiB/s-184MiB/s (193MB/s-193MB/s), io=32.0GiB (34.4GB), run=177864-177864msec
(+146.3% throughput, -59.5% run time)
*****************************************************
**** 32 jobs, 2GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=72.6MiB/s (76.1MB/s), 72.6MiB/s-72.6MiB/s (76.1MB/s-76.1MB/s), io=64.0GiB (68.7GB), run=902615-902615msec
After patchset:
WRITE: bw=227MiB/s (238MB/s), 227MiB/s-227MiB/s (238MB/s-238MB/s), io=64.0GiB (68.7GB), run=288936-288936msec
(+212.7% throughput, -68.0% run time)
*****************************************************
**** 64 jobs, 1GiB files, fsync frequency 1 ****
*****************************************************
Before patchset:
WRITE: bw=98.8MiB/s (104MB/s), 98.8MiB/s-98.8MiB/s (104MB/s-104MB/s), io=64.0GiB (68.7GB), run=663126-663126msec
After patchset:
WRITE: bw=294MiB/s (308MB/s), 294MiB/s-294MiB/s (308MB/s-308MB/s), io=64.0GiB (68.7GB), run=222940-222940msec
(+197.6% throughput, -66.4% run time)
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-22 19:29:01 +08:00
|
|
|
/*
|
|
|
|
* We only remove extent maps that are not in the list of
|
|
|
|
* modified extents or that are in the list but with a
|
|
|
|
* generation lower then the current generation, so there
|
|
|
|
* is no need to set the full fsync flag on the inode (it
|
|
|
|
* hurts the fsync performance for workloads with a data
|
|
|
|
* size that exceeds or is close to the system's memory).
|
|
|
|
*/
|
2020-07-22 19:28:52 +08:00
|
|
|
remove_extent_mapping(map, em);
|
|
|
|
/* once for the rb tree */
|
|
|
|
free_extent_map(em);
|
btrfs: fix race between page release and a fast fsync
When releasing an extent map, done through the page release callback, we
can race with an ongoing fast fsync and cause the fsync to miss a new
extent and not log it. The steps for this to happen are the following:
1) A page is dirtied for some inode I;
2) Writeback for that page is triggered by a path other than fsync, for
example by the system due to memory pressure;
3) When the ordered extent for the extent (a single 4K page) finishes,
we unpin the corresponding extent map and set its generation to N,
the current transaction's generation;
4) The btrfs_releasepage() callback is invoked by the system due to
memory pressure for that no longer dirty page of inode I;
5) At the same time, some task calls fsync on inode I, joins transaction
N, and at btrfs_log_inode() it sees that the inode does not have the
full sync flag set, so we proceed with a fast fsync. But before we get
into btrfs_log_changed_extents() and lock the inode's extent map tree:
6) Through btrfs_releasepage() we end up at try_release_extent_mapping()
and we remove the extent map for the new 4Kb extent, because it is
neither pinned anymore nor locked. By calling remove_extent_mapping(),
we remove the extent map from the list of modified extents, since the
extent map does not have the logging flag set. We unlock the inode's
extent map tree;
7) The task doing the fast fsync now enters btrfs_log_changed_extents(),
locks the inode's extent map tree and iterates its list of modified
extents, which no longer has the 4Kb extent in it, so it does not log
the extent;
8) The fsync finishes;
9) Before transaction N is committed, a power failure happens. After
replaying the log, the 4K extent of inode I will be missing, since
it was not logged due to the race with try_release_extent_mapping().
So fix this by teaching try_release_extent_mapping() to not remove an
extent map if it's still in the list of modified extents.
Fixes: ff44c6e36dc9dc ("Btrfs: do not hold the write_lock on the extent tree while logging")
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-22 19:28:37 +08:00
|
|
|
next:
|
2008-01-29 22:59:12 +08:00
|
|
|
start = extent_map_end(em);
|
2009-09-03 04:24:52 +08:00
|
|
|
write_unlock(&map->lock);
|
2008-01-29 22:59:12 +08:00
|
|
|
|
|
|
|
/* once for us */
|
2008-01-25 05:13:08 +08:00
|
|
|
free_extent_map(em);
|
2020-05-09 05:15:37 +08:00
|
|
|
|
|
|
|
cond_resched(); /* Allow large-extent preemption. */
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
}
|
2018-04-19 15:46:35 +08:00
|
|
|
return try_release_extent_state(tree, page, mask);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
/*
|
|
|
|
* To cache previous fiemap extent
|
|
|
|
*
|
|
|
|
* Will be used for merging fiemap extent
|
|
|
|
*/
|
|
|
|
struct fiemap_cache {
|
|
|
|
u64 offset;
|
|
|
|
u64 phys;
|
|
|
|
u64 len;
|
|
|
|
u32 flags;
|
|
|
|
bool cached;
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Helper to submit fiemap extent.
|
|
|
|
*
|
|
|
|
* Will try to merge current fiemap extent specified by @offset, @phys,
|
|
|
|
* @len and @flags with cached one.
|
|
|
|
* And only when we fails to merge, cached one will be submitted as
|
|
|
|
* fiemap extent.
|
|
|
|
*
|
|
|
|
* Return value is the same as fiemap_fill_next_extent().
|
|
|
|
*/
|
|
|
|
static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
|
|
|
|
struct fiemap_cache *cache,
|
|
|
|
u64 offset, u64 phys, u64 len, u32 flags)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
/* Set at the end of extent_fiemap(). */
|
|
|
|
ASSERT((flags & FIEMAP_EXTENT_LAST) == 0);
|
|
|
|
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
if (!cache->cached)
|
|
|
|
goto assign;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Sanity check, extent_fiemap() should have ensured that new
|
2018-11-28 19:05:13 +08:00
|
|
|
* fiemap extent won't overlap with cached one.
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
* Not recoverable.
|
|
|
|
*
|
|
|
|
* NOTE: Physical address can overlap, due to compression
|
|
|
|
*/
|
|
|
|
if (cache->offset + cache->len > offset) {
|
|
|
|
WARN_ON(1);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Only merges fiemap extents if
|
|
|
|
* 1) Their logical addresses are continuous
|
|
|
|
*
|
|
|
|
* 2) Their physical addresses are continuous
|
|
|
|
* So truly compressed (physical size smaller than logical size)
|
|
|
|
* extents won't get merged with each other
|
|
|
|
*
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
* 3) Share same flags
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
*/
|
|
|
|
if (cache->offset + cache->len == offset &&
|
|
|
|
cache->phys + cache->len == phys &&
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
cache->flags == flags) {
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
cache->len += len;
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
return 0;
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Not mergeable, need to submit cached one */
|
|
|
|
ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
|
|
|
|
cache->len, cache->flags);
|
|
|
|
cache->cached = false;
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
assign:
|
|
|
|
cache->cached = true;
|
|
|
|
cache->offset = offset;
|
|
|
|
cache->phys = phys;
|
|
|
|
cache->len = len;
|
|
|
|
cache->flags = flags;
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
|
|
|
|
return 0;
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2017-06-22 10:01:21 +08:00
|
|
|
* Emit last fiemap cache
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
*
|
2017-06-22 10:01:21 +08:00
|
|
|
* The last fiemap cache may still be cached in the following case:
|
|
|
|
* 0 4k 8k
|
|
|
|
* |<- Fiemap range ->|
|
|
|
|
* |<------------ First extent ----------->|
|
|
|
|
*
|
|
|
|
* In this case, the first extent range will be cached but not emitted.
|
|
|
|
* So we must emit it before ending extent_fiemap().
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
*/
|
2019-03-20 18:29:46 +08:00
|
|
|
static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo,
|
2017-06-22 10:01:21 +08:00
|
|
|
struct fiemap_cache *cache)
|
btrfs: fiemap: Cache and merge fiemap extent before submit it to user
[BUG]
Cycle mount btrfs can cause fiemap to return different result.
Like:
# mount /dev/vdb5 /mnt/btrfs
# dd if=/dev/zero bs=16K count=4 oflag=dsync of=/mnt/btrfs/file
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
# umount /mnt/btrfs
# mount /dev/vdb5 /mnt/btrfs
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..31]: 25088..25119 32 0x0
1: [32..63]: 25120..25151 32 0x0
2: [64..95]: 25152..25183 32 0x0
3: [96..127]: 25184..25215 32 0x1
But after above fiemap, we get correct merged result if we call fiemap
again.
# xfs_io -c "fiemap -v" /mnt/btrfs/file
/mnt/test/file:
EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS
0: [0..127]: 25088..25215 128 0x1
[REASON]
Btrfs will try to merge extent map when inserting new extent map.
btrfs_fiemap(start=0 len=(u64)-1)
|- extent_fiemap(start=0 len=(u64)-1)
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=0 len=64k)
| | Found on-disk (ino, EXTENT_DATA, 0)
| |- add_extent_mapping()
| |- Return (em->start=0, len=16k)
|
|- fiemap_fill_next_extent(logic=0 phys=X len=16k)
|
|- get_extent_skip_holes(start=0 len=64k)
| |- btrfs_get_extent_fiemap(start=0 len=64k)
| |- btrfs_get_extent(start=16k len=48k)
| | Found on-disk (ino, EXTENT_DATA, 16k)
| |- add_extent_mapping()
| | |- try_merge_map()
| | Merge with previous em start=0 len=16k
| | resulting em start=0 len=32k
| |- Return (em->start=0, len=32K) << Merged result
|- Stripe off the unrelated range (0~16K) of return em
|- fiemap_fill_next_extent(logic=16K phys=X+16K len=16K)
^^^ Causing split fiemap extent.
And since in add_extent_mapping(), em is already merged, in next
fiemap() call, we will get merged result.
[FIX]
Here we introduce a new structure, fiemap_cache, which records previous
fiemap extent.
And will always try to merge current fiemap_cache result before calling
fiemap_fill_next_extent().
Only when we failed to merge current fiemap extent with cached one, we
will call fiemap_fill_next_extent() to submit cached one.
So by this method, we can merge all fiemap extents.
It can also be done in fs/ioctl.c, however the problem is if
fieinfo->fi_extents_max == 0, we have no space to cache previous fiemap
extent.
So I choose to merge it in btrfs.
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-04-07 10:43:15 +08:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!cache->cached)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
|
|
|
|
cache->len, cache->flags);
|
|
|
|
cache->cached = false;
|
|
|
|
if (ret > 0)
|
|
|
|
ret = 0;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *path)
|
2009-01-22 03:39:14 +08:00
|
|
|
{
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
struct extent_buffer *clone;
|
|
|
|
struct btrfs_key key;
|
|
|
|
int slot;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
path->slots[0]++;
|
|
|
|
if (path->slots[0] < btrfs_header_nritems(path->nodes[0]))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
ret = btrfs_next_leaf(inode->root, path);
|
|
|
|
if (ret != 0)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Don't bother with cloning if there are no more file extent items for
|
|
|
|
* our inode.
|
|
|
|
*/
|
|
|
|
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
|
|
|
|
if (key.objectid != btrfs_ino(inode) || key.type != BTRFS_EXTENT_DATA_KEY)
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
/* See the comment at fiemap_search_slot() about why we clone. */
|
|
|
|
clone = btrfs_clone_extent_buffer(path->nodes[0]);
|
|
|
|
if (!clone)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
slot = path->slots[0];
|
|
|
|
btrfs_release_path(path);
|
|
|
|
path->nodes[0] = clone;
|
|
|
|
path->slots[0] = slot;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Search for the first file extent item that starts at a given file offset or
|
|
|
|
* the one that starts immediately before that offset.
|
|
|
|
* Returns: 0 on success, < 0 on error, 1 if not found.
|
|
|
|
*/
|
|
|
|
static int fiemap_search_slot(struct btrfs_inode *inode, struct btrfs_path *path,
|
|
|
|
u64 file_offset)
|
|
|
|
{
|
|
|
|
const u64 ino = btrfs_ino(inode);
|
2020-08-31 19:42:49 +08:00
|
|
|
struct btrfs_root *root = inode->root;
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
struct extent_buffer *clone;
|
|
|
|
struct btrfs_key key;
|
|
|
|
int slot;
|
|
|
|
int ret;
|
2009-01-22 03:39:14 +08:00
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
key.objectid = ino;
|
|
|
|
key.type = BTRFS_EXTENT_DATA_KEY;
|
|
|
|
key.offset = file_offset;
|
|
|
|
|
|
|
|
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
if (ret > 0 && path->slots[0] > 0) {
|
|
|
|
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1);
|
|
|
|
if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY)
|
|
|
|
path->slots[0]--;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
|
|
|
|
ret = btrfs_next_leaf(root, path);
|
|
|
|
if (ret != 0)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
|
|
|
|
if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY)
|
|
|
|
return 1;
|
2019-05-15 21:31:04 +08:00
|
|
|
}
|
|
|
|
|
2021-04-07 06:31:18 +08:00
|
|
|
/*
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
* We clone the leaf and use it during fiemap. This is because while
|
|
|
|
* using the leaf we do expensive things like checking if an extent is
|
|
|
|
* shared, which can take a long time. In order to prevent blocking
|
|
|
|
* other tasks for too long, we use a clone of the leaf. We have locked
|
|
|
|
* the file range in the inode's io tree, so we know none of our file
|
|
|
|
* extent items can change. This way we avoid blocking other tasks that
|
|
|
|
* want to insert items for other inodes in the same leaf or b+tree
|
|
|
|
* rebalance operations (triggered for example when someone is trying
|
|
|
|
* to push items into this leaf when trying to insert an item in a
|
|
|
|
* neighbour leaf).
|
|
|
|
* We also need the private clone because holding a read lock on an
|
|
|
|
* extent buffer of the subvolume's b+tree will make lockdep unhappy
|
|
|
|
* when we call fiemap_fill_next_extent(), because that may cause a page
|
|
|
|
* fault when filling the user space buffer with fiemap data.
|
2021-04-07 06:31:18 +08:00
|
|
|
*/
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
clone = btrfs_clone_extent_buffer(path->nodes[0]);
|
|
|
|
if (!clone)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
slot = path->slots[0];
|
|
|
|
btrfs_release_path(path);
|
|
|
|
path->nodes[0] = clone;
|
|
|
|
path->slots[0] = slot;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Process a range which is a hole or a prealloc extent in the inode's subvolume
|
|
|
|
* btree. If @disk_bytenr is 0, we are dealing with a hole, otherwise a prealloc
|
|
|
|
* extent. The end offset (@end) is inclusive.
|
|
|
|
*/
|
|
|
|
static int fiemap_process_hole(struct btrfs_inode *inode,
|
|
|
|
struct fiemap_extent_info *fieinfo,
|
|
|
|
struct fiemap_cache *cache,
|
2022-10-11 20:17:02 +08:00
|
|
|
struct btrfs_backref_share_check_ctx *backref_ctx,
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
u64 disk_bytenr, u64 extent_offset,
|
|
|
|
u64 extent_gen,
|
|
|
|
u64 start, u64 end)
|
|
|
|
{
|
|
|
|
const u64 i_size = i_size_read(&inode->vfs_inode);
|
|
|
|
u64 cur_offset = start;
|
|
|
|
u64 last_delalloc_end = 0;
|
|
|
|
u32 prealloc_flags = FIEMAP_EXTENT_UNWRITTEN;
|
|
|
|
bool checked_extent_shared = false;
|
|
|
|
int ret;
|
2011-11-18 00:34:31 +08:00
|
|
|
|
2011-02-24 05:23:20 +08:00
|
|
|
/*
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
* There can be no delalloc past i_size, so don't waste time looking for
|
|
|
|
* it beyond i_size.
|
2011-02-24 05:23:20 +08:00
|
|
|
*/
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
while (cur_offset < end && cur_offset < i_size) {
|
|
|
|
u64 delalloc_start;
|
|
|
|
u64 delalloc_end;
|
|
|
|
u64 prealloc_start;
|
|
|
|
u64 prealloc_len = 0;
|
|
|
|
bool delalloc;
|
|
|
|
|
|
|
|
delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end,
|
|
|
|
&delalloc_start,
|
|
|
|
&delalloc_end);
|
|
|
|
if (!delalloc)
|
|
|
|
break;
|
2016-05-18 08:21:48 +08:00
|
|
|
|
2011-02-24 05:23:20 +08:00
|
|
|
/*
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
* If this is a prealloc extent we have to report every section
|
|
|
|
* of it that has no delalloc.
|
2011-02-24 05:23:20 +08:00
|
|
|
*/
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
if (disk_bytenr != 0) {
|
|
|
|
if (last_delalloc_end == 0) {
|
|
|
|
prealloc_start = start;
|
|
|
|
prealloc_len = delalloc_start - start;
|
|
|
|
} else {
|
|
|
|
prealloc_start = last_delalloc_end + 1;
|
|
|
|
prealloc_len = delalloc_start - prealloc_start;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (prealloc_len > 0) {
|
|
|
|
if (!checked_extent_shared && fieinfo->fi_extents_max) {
|
2022-10-11 20:17:01 +08:00
|
|
|
ret = btrfs_is_data_extent_shared(inode,
|
2022-10-11 20:17:03 +08:00
|
|
|
disk_bytenr,
|
|
|
|
extent_gen,
|
|
|
|
backref_ctx);
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
else if (ret > 0)
|
|
|
|
prealloc_flags |= FIEMAP_EXTENT_SHARED;
|
|
|
|
|
|
|
|
checked_extent_shared = true;
|
|
|
|
}
|
|
|
|
ret = emit_fiemap_extent(fieinfo, cache, prealloc_start,
|
|
|
|
disk_bytenr + extent_offset,
|
|
|
|
prealloc_len, prealloc_flags);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
extent_offset += prealloc_len;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = emit_fiemap_extent(fieinfo, cache, delalloc_start, 0,
|
|
|
|
delalloc_end + 1 - delalloc_start,
|
|
|
|
FIEMAP_EXTENT_DELALLOC |
|
|
|
|
FIEMAP_EXTENT_UNKNOWN);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
last_delalloc_end = delalloc_end;
|
|
|
|
cur_offset = delalloc_end + 1;
|
|
|
|
extent_offset += cur_offset - delalloc_start;
|
|
|
|
cond_resched();
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Either we found no delalloc for the whole prealloc extent or we have
|
|
|
|
* a prealloc extent that spans i_size or starts at or after i_size.
|
|
|
|
*/
|
|
|
|
if (disk_bytenr != 0 && last_delalloc_end < end) {
|
|
|
|
u64 prealloc_start;
|
|
|
|
u64 prealloc_len;
|
|
|
|
|
|
|
|
if (last_delalloc_end == 0) {
|
|
|
|
prealloc_start = start;
|
|
|
|
prealloc_len = end + 1 - start;
|
|
|
|
} else {
|
|
|
|
prealloc_start = last_delalloc_end + 1;
|
|
|
|
prealloc_len = end + 1 - prealloc_start;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!checked_extent_shared && fieinfo->fi_extents_max) {
|
2022-10-11 20:17:01 +08:00
|
|
|
ret = btrfs_is_data_extent_shared(inode,
|
|
|
|
disk_bytenr,
|
2022-10-11 20:17:03 +08:00
|
|
|
extent_gen,
|
2022-10-11 20:17:02 +08:00
|
|
|
backref_ctx);
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
else if (ret > 0)
|
|
|
|
prealloc_flags |= FIEMAP_EXTENT_SHARED;
|
|
|
|
}
|
|
|
|
ret = emit_fiemap_extent(fieinfo, cache, prealloc_start,
|
|
|
|
disk_bytenr + extent_offset,
|
|
|
|
prealloc_len, prealloc_flags);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int fiemap_find_last_extent_offset(struct btrfs_inode *inode,
|
|
|
|
struct btrfs_path *path,
|
|
|
|
u64 *last_extent_end_ret)
|
|
|
|
{
|
|
|
|
const u64 ino = btrfs_ino(inode);
|
|
|
|
struct btrfs_root *root = inode->root;
|
|
|
|
struct extent_buffer *leaf;
|
|
|
|
struct btrfs_file_extent_item *ei;
|
|
|
|
struct btrfs_key key;
|
|
|
|
u64 disk_bytenr;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Lookup the last file extent. We're not using i_size here because
|
|
|
|
* there might be preallocation past i_size.
|
|
|
|
*/
|
|
|
|
ret = btrfs_lookup_file_extent(NULL, root, path, ino, (u64)-1, 0);
|
|
|
|
/* There can't be a file extent item at offset (u64)-1 */
|
|
|
|
ASSERT(ret != 0);
|
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For a non-existing key, btrfs_search_slot() always leaves us at a
|
|
|
|
* slot > 0, except if the btree is empty, which is impossible because
|
|
|
|
* at least it has the inode item for this inode and all the items for
|
|
|
|
* the root inode 256.
|
|
|
|
*/
|
|
|
|
ASSERT(path->slots[0] > 0);
|
|
|
|
path->slots[0]--;
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
|
|
|
|
if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) {
|
|
|
|
/* No file extent items in the subvolume tree. */
|
|
|
|
*last_extent_end_ret = 0;
|
|
|
|
return 0;
|
2010-11-24 03:36:57 +08:00
|
|
|
}
|
|
|
|
|
2011-02-24 05:23:20 +08:00
|
|
|
/*
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
* For an inline extent, the disk_bytenr is where inline data starts at,
|
|
|
|
* so first check if we have an inline extent item before checking if we
|
|
|
|
* have an implicit hole (disk_bytenr == 0).
|
2011-02-24 05:23:20 +08:00
|
|
|
*/
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item);
|
|
|
|
if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) {
|
|
|
|
*last_extent_end_ret = btrfs_file_extent_end(path);
|
|
|
|
return 0;
|
2011-02-24 05:23:20 +08:00
|
|
|
}
|
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
/*
|
|
|
|
* Find the last file extent item that is not a hole (when NO_HOLES is
|
|
|
|
* not enabled). This should take at most 2 iterations in the worst
|
|
|
|
* case: we have one hole file extent item at slot 0 of a leaf and
|
|
|
|
* another hole file extent item as the last item in the previous leaf.
|
|
|
|
* This is because we merge file extent items that represent holes.
|
|
|
|
*/
|
|
|
|
disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei);
|
|
|
|
while (disk_bytenr == 0) {
|
|
|
|
ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY);
|
|
|
|
if (ret < 0) {
|
|
|
|
return ret;
|
|
|
|
} else if (ret > 0) {
|
|
|
|
/* No file extent items that are not holes. */
|
|
|
|
*last_extent_end_ret = 0;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
leaf = path->nodes[0];
|
|
|
|
ei = btrfs_item_ptr(leaf, path->slots[0],
|
|
|
|
struct btrfs_file_extent_item);
|
|
|
|
disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei);
|
|
|
|
}
|
2011-02-24 05:23:20 +08:00
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
*last_extent_end_ret = btrfs_file_extent_end(path);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
|
|
|
|
u64 start, u64 len)
|
|
|
|
{
|
|
|
|
const u64 ino = btrfs_ino(inode);
|
|
|
|
struct extent_state *cached_state = NULL;
|
|
|
|
struct btrfs_path *path;
|
|
|
|
struct fiemap_cache cache = { 0 };
|
2022-10-11 20:17:02 +08:00
|
|
|
struct btrfs_backref_share_check_ctx *backref_ctx;
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
u64 last_extent_end;
|
|
|
|
u64 prev_extent_end;
|
|
|
|
u64 lockstart;
|
|
|
|
u64 lockend;
|
|
|
|
bool stopped = false;
|
|
|
|
int ret;
|
|
|
|
|
2022-10-11 20:17:03 +08:00
|
|
|
backref_ctx = btrfs_alloc_backref_share_check_ctx();
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
path = btrfs_alloc_path();
|
2022-10-11 20:17:03 +08:00
|
|
|
if (!backref_ctx || !path) {
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
ret = -ENOMEM;
|
2009-01-22 03:39:14 +08:00
|
|
|
goto out;
|
|
|
|
}
|
2010-11-24 03:36:57 +08:00
|
|
|
|
2022-10-11 20:17:01 +08:00
|
|
|
lockstart = round_down(start, inode->root->fs_info->sectorsize);
|
|
|
|
lockend = round_up(start + len, inode->root->fs_info->sectorsize);
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
prev_extent_end = lockstart;
|
2011-03-09 00:54:40 +08:00
|
|
|
|
2022-09-10 05:53:43 +08:00
|
|
|
lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
|
2011-03-09 00:54:40 +08:00
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end);
|
|
|
|
if (ret < 0)
|
|
|
|
goto out_unlock;
|
|
|
|
btrfs_release_path(path);
|
2009-01-22 03:39:14 +08:00
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
path->reada = READA_FORWARD;
|
|
|
|
ret = fiemap_search_slot(inode, path, lockstart);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto out_unlock;
|
|
|
|
} else if (ret > 0) {
|
2011-03-09 00:54:40 +08:00
|
|
|
/*
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
* No file extent item found, but we may have delalloc between
|
|
|
|
* the current offset and i_size. So check for that.
|
2011-03-09 00:54:40 +08:00
|
|
|
*/
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
ret = 0;
|
|
|
|
goto check_eof_delalloc;
|
|
|
|
}
|
|
|
|
|
|
|
|
while (prev_extent_end < lockend) {
|
|
|
|
struct extent_buffer *leaf = path->nodes[0];
|
|
|
|
struct btrfs_file_extent_item *ei;
|
|
|
|
struct btrfs_key key;
|
|
|
|
u64 extent_end;
|
|
|
|
u64 extent_len;
|
|
|
|
u64 extent_offset = 0;
|
|
|
|
u64 extent_gen;
|
|
|
|
u64 disk_bytenr = 0;
|
|
|
|
u64 flags = 0;
|
|
|
|
int extent_type;
|
|
|
|
u8 compression;
|
|
|
|
|
|
|
|
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
|
|
|
|
if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY)
|
|
|
|
break;
|
|
|
|
|
|
|
|
extent_end = btrfs_file_extent_end(path);
|
2009-01-22 03:39:14 +08:00
|
|
|
|
2011-03-09 00:54:40 +08:00
|
|
|
/*
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
* The first iteration can leave us at an extent item that ends
|
|
|
|
* before our range's start. Move to the next item.
|
2011-03-09 00:54:40 +08:00
|
|
|
*/
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
if (extent_end <= lockstart)
|
|
|
|
goto next_item;
|
2013-09-22 12:54:23 +08:00
|
|
|
|
btrfs: avoid duplicated resolution of indirect backrefs during fiemap
During fiemap, when determining if a data extent is shared or not, if we
don't find the extent is directly shared, then we need to determine if
it's shared through subtrees. For that we need to resolve the indirect
reference we found in order to figure out the path in the inode's fs tree,
which is a path starting at the fs tree's root node and going down to the
leaf that contains the file extent item that points to the data extent.
We then proceed to determine if any extent buffer in that path is shared
with other trees or not.
Currently whenever we find the data extent that a file extent item points
to is not directly shared, we always resolve the path in the fs tree, and
then check if any extent buffer in the path is shared. This is a lot of
work and when we have file extent items that belong to the same leaf, we
have the same path, so we only need to calculate it once.
This change does that, it keeps track of the current and previous leaf,
and when we find that a data extent is not directly shared, we try to
compute the fs tree path only once and then use it for every other file
extent item in the same leaf, using the existing cached path result for
the leaf as long as the cache results are valid.
This saves us from doing expensive b+tree searches in the fs tree of our
target inode, as well as other minor work.
The following test was run on a non-debug kernel (Debian's default kernel
config):
$ cat test-with-snapshots.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
umount $DEV &> /dev/null
mkfs.btrfs -f $DEV
# Use compression to quickly create files with a lot of extents
# (each with a size of 128K).
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 extents, each with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 40G" $MNT/foobar
# Add some more files to increase the size of the fs and extent
# trees (in the real world there's a lot of files and extents
# from other files).
xfs_io -f -c "pwrite -S 0xcd -b 1M 0 20G" $MNT/file1
xfs_io -f -c "pwrite -S 0xef -b 1M 0 20G" $MNT/file2
xfs_io -f -c "pwrite -S 0x73 -b 1M 0 20G" $MNT/file3
# Create a snapshot so all the extents become indirectly shared
# through subtrees, with a generation less than or equals to the
# generation used to create the snapshot.
btrfs subvolume snapshot -r $MNT $MNT/snap1
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
echo
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Result before applying this patch:
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1204 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 729 milliseconds (metadata cached)
Result after applying this patch:
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 732 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 421 milliseconds (metadata cached)
That's a -46.1% total reduction for the metadata not cached case, and
a -42.2% reduction for the cached metadata case.
The test is somewhat limited in the sense the gains may be higher in
practice, because in the test the filesystem is small, so we have small
fs and extent trees, plus there's no concurrent access to the trees as
well, therefore no lock contention there.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-10-11 20:17:08 +08:00
|
|
|
backref_ctx->curr_leaf_bytenr = leaf->start;
|
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
/* We have in implicit hole (NO_HOLES feature enabled). */
|
|
|
|
if (prev_extent_end < key.offset) {
|
|
|
|
const u64 range_end = min(key.offset, lockend) - 1;
|
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
During fiemap, for each file extent we find, we must check if it's shared
or not. The sharedness check starts by verifying if the extent is directly
shared (its refcount in the extent tree is > 1), and if it is not directly
shared, then we will check if every node in the subvolume b+tree leading
from the root to the leaf that has the file extent item (in reverse order),
is shared (through snapshots).
However this second step is not needed if our extent was created in a
transaction more recent than the last transaction where a snapshot of the
inode's root happened, because it can't be shared indirectly (through
shared subtrees) without a snapshot created in a more recent transaction.
So grab the generation of the extent from the extent map and pass it to
btrfs_is_data_extent_shared(), which will skip this second phase when the
generation is more recent than the root's last snapshot value. Note that
we skip this optimization if the extent map is the result of merging 2
or more extent maps, because in this case its generation is the maximum
of the generations of all merged extent maps.
The fact the we use extent maps and they can be merged despite the
underlying extents being distinct (different file extent items in the
subvolume b+tree and different extent items in the extent b+tree), can
result in some bugs when reporting shared extents. But this is a problem
of the current implementation of fiemap relying on extent maps.
One example where we get incorrect results is:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This is z problem that existed before this change, and remains after this
change, as it can't be easily fixed. The next patch in the series reworks
fiemap to primarily use file extent items instead of extent maps (except
for checking for delalloc ranges), with the goal of improving its
scalability and performance, but it also ends up fixing this particular
bug caused by extent map merging.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:29 +08:00
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
ret = fiemap_process_hole(inode, fieinfo, &cache,
|
2022-10-11 20:17:02 +08:00
|
|
|
backref_ctx, 0, 0, 0,
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
prev_extent_end, range_end);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto out_unlock;
|
|
|
|
} else if (ret > 0) {
|
|
|
|
/* fiemap_fill_next_extent() told us to stop. */
|
|
|
|
stopped = true;
|
|
|
|
break;
|
|
|
|
}
|
2009-01-22 03:39:14 +08:00
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
/* We've reached the end of the fiemap range, stop. */
|
|
|
|
if (key.offset >= lockend) {
|
|
|
|
stopped = true;
|
|
|
|
break;
|
|
|
|
}
|
2009-01-22 03:39:14 +08:00
|
|
|
}
|
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
extent_len = extent_end - key.offset;
|
|
|
|
ei = btrfs_item_ptr(leaf, path->slots[0],
|
|
|
|
struct btrfs_file_extent_item);
|
|
|
|
compression = btrfs_file_extent_compression(leaf, ei);
|
|
|
|
extent_type = btrfs_file_extent_type(leaf, ei);
|
|
|
|
extent_gen = btrfs_file_extent_generation(leaf, ei);
|
|
|
|
|
|
|
|
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
|
|
|
|
disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei);
|
|
|
|
if (compression == BTRFS_COMPRESS_NONE)
|
|
|
|
extent_offset = btrfs_file_extent_offset(leaf, ei);
|
2011-02-24 05:23:20 +08:00
|
|
|
}
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
|
|
|
|
if (compression != BTRFS_COMPRESS_NONE)
|
|
|
|
flags |= FIEMAP_EXTENT_ENCODED;
|
|
|
|
|
|
|
|
if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
|
|
|
|
flags |= FIEMAP_EXTENT_DATA_INLINE;
|
|
|
|
flags |= FIEMAP_EXTENT_NOT_ALIGNED;
|
|
|
|
ret = emit_fiemap_extent(fieinfo, &cache, key.offset, 0,
|
|
|
|
extent_len, flags);
|
|
|
|
} else if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
|
|
|
|
ret = fiemap_process_hole(inode, fieinfo, &cache,
|
2022-10-11 20:17:02 +08:00
|
|
|
backref_ctx,
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
disk_bytenr, extent_offset,
|
2022-10-11 20:17:03 +08:00
|
|
|
extent_gen, key.offset,
|
|
|
|
extent_end - 1);
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
} else if (disk_bytenr == 0) {
|
|
|
|
/* We have an explicit hole. */
|
|
|
|
ret = fiemap_process_hole(inode, fieinfo, &cache,
|
2022-10-11 20:17:02 +08:00
|
|
|
backref_ctx, 0, 0, 0,
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
key.offset, extent_end - 1);
|
|
|
|
} else {
|
|
|
|
/* We have a regular extent. */
|
|
|
|
if (fieinfo->fi_extents_max) {
|
2022-10-11 20:17:01 +08:00
|
|
|
ret = btrfs_is_data_extent_shared(inode,
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
disk_bytenr,
|
|
|
|
extent_gen,
|
2022-10-11 20:17:02 +08:00
|
|
|
backref_ctx);
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
if (ret < 0)
|
|
|
|
goto out_unlock;
|
|
|
|
else if (ret > 0)
|
|
|
|
flags |= FIEMAP_EXTENT_SHARED;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = emit_fiemap_extent(fieinfo, &cache, key.offset,
|
|
|
|
disk_bytenr + extent_offset,
|
|
|
|
extent_len, flags);
|
2010-11-24 03:36:57 +08:00
|
|
|
}
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
|
|
|
|
if (ret < 0) {
|
|
|
|
goto out_unlock;
|
|
|
|
} else if (ret > 0) {
|
|
|
|
/* fiemap_fill_next_extent() told us to stop. */
|
|
|
|
stopped = true;
|
|
|
|
break;
|
2015-03-25 06:12:56 +08:00
|
|
|
}
|
2022-09-01 21:18:26 +08:00
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
prev_extent_end = extent_end;
|
|
|
|
next_item:
|
2022-09-01 21:18:26 +08:00
|
|
|
if (fatal_signal_pending(current)) {
|
|
|
|
ret = -EINTR;
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
goto out_unlock;
|
2022-09-01 21:18:26 +08:00
|
|
|
}
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
|
|
|
|
ret = fiemap_next_leaf_item(inode, path);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto out_unlock;
|
|
|
|
} else if (ret > 0) {
|
|
|
|
/* No more file extent items for this inode. */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
cond_resched();
|
2009-01-22 03:39:14 +08:00
|
|
|
}
|
2019-05-15 21:31:04 +08:00
|
|
|
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
check_eof_delalloc:
|
|
|
|
/*
|
|
|
|
* Release (and free) the path before emitting any final entries to
|
|
|
|
* fiemap_fill_next_extent() to keep lockdep happy. This is because
|
|
|
|
* once we find no more file extent items exist, we may have a
|
|
|
|
* non-cloned leaf, and fiemap_fill_next_extent() can trigger page
|
|
|
|
* faults when copying data to the user space buffer.
|
|
|
|
*/
|
|
|
|
btrfs_free_path(path);
|
|
|
|
path = NULL;
|
|
|
|
|
|
|
|
if (!stopped && prev_extent_end < lockend) {
|
2022-10-11 20:17:02 +08:00
|
|
|
ret = fiemap_process_hole(inode, fieinfo, &cache, backref_ctx,
|
2022-10-11 20:17:03 +08:00
|
|
|
0, 0, 0, prev_extent_end, lockend - 1);
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
if (ret < 0)
|
|
|
|
goto out_unlock;
|
|
|
|
prev_extent_end = lockend;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (cache.cached && cache.offset + cache.len >= last_extent_end) {
|
|
|
|
const u64 i_size = i_size_read(&inode->vfs_inode);
|
|
|
|
|
|
|
|
if (prev_extent_end < i_size) {
|
|
|
|
u64 delalloc_start;
|
|
|
|
u64 delalloc_end;
|
|
|
|
bool delalloc;
|
|
|
|
|
|
|
|
delalloc = btrfs_find_delalloc_in_range(inode,
|
|
|
|
prev_extent_end,
|
|
|
|
i_size - 1,
|
|
|
|
&delalloc_start,
|
|
|
|
&delalloc_end);
|
|
|
|
if (!delalloc)
|
|
|
|
cache.flags |= FIEMAP_EXTENT_LAST;
|
|
|
|
} else {
|
|
|
|
cache.flags |= FIEMAP_EXTENT_LAST;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = emit_last_fiemap_cache(fieinfo, &cache);
|
|
|
|
|
|
|
|
out_unlock:
|
2022-09-10 05:53:43 +08:00
|
|
|
unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
|
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-01 21:18:30 +08:00
|
|
|
out:
|
2022-10-11 20:17:03 +08:00
|
|
|
btrfs_free_backref_share_ctx(backref_ctx);
|
2019-07-05 15:26:24 +08:00
|
|
|
btrfs_free_path(path);
|
2009-01-22 03:39:14 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2010-08-07 01:21:20 +08:00
|
|
|
static void __free_extent_buffer(struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
kmem_cache_free(extent_buffer_cache, eb);
|
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
int extent_buffer_under_io(const struct extent_buffer *eb)
|
2013-08-08 02:54:37 +08:00
|
|
|
{
|
|
|
|
return (atomic_read(&eb->io_pages) ||
|
|
|
|
test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
|
|
|
|
test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
|
|
|
|
}
|
|
|
|
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page)
|
2013-08-08 02:54:37 +08:00
|
|
|
{
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
struct btrfs_subpage *subpage;
|
2013-08-08 02:54:37 +08:00
|
|
|
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
lockdep_assert_held(&page->mapping->private_lock);
|
2013-08-08 02:54:37 +08:00
|
|
|
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
if (PagePrivate(page)) {
|
|
|
|
subpage = (struct btrfs_subpage *)page->private;
|
|
|
|
if (atomic_read(&subpage->eb_refs))
|
|
|
|
return true;
|
btrfs: subpage: fix a rare race between metadata endio and eb freeing
[BUG]
There is a very rare ASSERT() triggering during full fstests run for
subpage rw support.
No other reproducer so far.
The ASSERT() gets triggered for metadata read in
btrfs_page_set_uptodate() inside end_page_read().
[CAUSE]
There is still a small race window for metadata only, the race could
happen like this:
T1 | T2
------------------------------------+-----------------------------
end_bio_extent_readpage() |
|- btrfs_validate_metadata_buffer() |
| |- free_extent_buffer() |
| Still have 2 refs |
|- end_page_read() |
|- if (unlikely(PagePrivate()) |
| The page still has Private |
| | free_extent_buffer()
| | | Only one ref 1, will be
| | | released
| | |- detach_extent_buffer_page()
| | |- btrfs_detach_subpage()
|- btrfs_set_page_uptodate() |
The page no longer has Private|
>>> ASSERT() triggered <<< |
This race window is super small, thus pretty hard to hit, even with so
many runs of fstests.
But the race window is still there, we have to go another way to solve
it other than relying on random PagePrivate() check.
Data path is not affected, as it will lock the page before reading,
while unlocking the page after the last read has finished, thus no race
window.
[FIX]
This patch will fix the bug by repurposing btrfs_subpage::readers.
Now btrfs_subpage::readers will be a member shared by both metadata and
data.
For metadata path, we don't do the page unlock as metadata only relies
on extent locking.
At the same time, teach page_range_has_eb() to take
btrfs_subpage::readers into consideration.
So that even if the last eb of a page gets freed, page::private won't be
detached as long as there still are pending end_page_read() calls.
By this we eliminate the race window, this will slight increase the
metadata memory usage, as the page may not be released as frequently as
usual. But it should not be a big deal.
The code got introduced in ("btrfs: submit read time repair only for
each corrupted sector"), but the fix is in a separate patch to keep the
problem description and the crash is rare so it should not hurt
bisectability.
Signed-off-by: Qu Wegruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-06-07 17:02:58 +08:00
|
|
|
/*
|
|
|
|
* Even there is no eb refs here, we may still have
|
|
|
|
* end_page_read() call relying on page::private.
|
|
|
|
*/
|
|
|
|
if (atomic_read(&subpage->readers))
|
|
|
|
return true;
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
2013-08-08 02:54:37 +08:00
|
|
|
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *page)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
|
|
|
const bool mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For mapped eb, we're going to change the page private, which should
|
|
|
|
* be done under the private_lock.
|
|
|
|
*/
|
|
|
|
if (mapped)
|
|
|
|
spin_lock(&page->mapping->private_lock);
|
|
|
|
|
|
|
|
if (!PagePrivate(page)) {
|
2015-02-09 17:31:45 +08:00
|
|
|
if (mapped)
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
spin_unlock(&page->mapping->private_lock);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (fs_info->nodesize >= PAGE_SIZE) {
|
2015-02-09 17:31:45 +08:00
|
|
|
/*
|
|
|
|
* We do this since we'll remove the pages after we've
|
|
|
|
* removed the eb from the radix tree, so we could race
|
|
|
|
* and have this page now attached to the new eb. So
|
|
|
|
* only clear page_private if it's still connected to
|
|
|
|
* this eb.
|
|
|
|
*/
|
|
|
|
if (PagePrivate(page) &&
|
|
|
|
page->private == (unsigned long)eb) {
|
|
|
|
BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
|
|
|
|
BUG_ON(PageDirty(page));
|
|
|
|
BUG_ON(PageWriteback(page));
|
2013-08-08 02:54:37 +08:00
|
|
|
/*
|
2015-02-09 17:31:45 +08:00
|
|
|
* We need to make sure we haven't be attached
|
|
|
|
* to a new eb.
|
2013-08-08 02:54:37 +08:00
|
|
|
*/
|
2020-06-02 12:47:45 +08:00
|
|
|
detach_page_private(page);
|
2013-08-08 02:54:37 +08:00
|
|
|
}
|
2015-02-09 17:31:45 +08:00
|
|
|
if (mapped)
|
|
|
|
spin_unlock(&page->mapping->private_lock);
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For subpage, we can have dummy eb with page private. In this case,
|
|
|
|
* we can directly detach the private as such page is only attached to
|
|
|
|
* one dummy eb, no sharing.
|
|
|
|
*/
|
|
|
|
if (!mapped) {
|
|
|
|
btrfs_detach_subpage(fs_info, page);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
btrfs_page_dec_eb_refs(fs_info, page);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We can only detach the page private if there are no other ebs in the
|
btrfs: subpage: fix a rare race between metadata endio and eb freeing
[BUG]
There is a very rare ASSERT() triggering during full fstests run for
subpage rw support.
No other reproducer so far.
The ASSERT() gets triggered for metadata read in
btrfs_page_set_uptodate() inside end_page_read().
[CAUSE]
There is still a small race window for metadata only, the race could
happen like this:
T1 | T2
------------------------------------+-----------------------------
end_bio_extent_readpage() |
|- btrfs_validate_metadata_buffer() |
| |- free_extent_buffer() |
| Still have 2 refs |
|- end_page_read() |
|- if (unlikely(PagePrivate()) |
| The page still has Private |
| | free_extent_buffer()
| | | Only one ref 1, will be
| | | released
| | |- detach_extent_buffer_page()
| | |- btrfs_detach_subpage()
|- btrfs_set_page_uptodate() |
The page no longer has Private|
>>> ASSERT() triggered <<< |
This race window is super small, thus pretty hard to hit, even with so
many runs of fstests.
But the race window is still there, we have to go another way to solve
it other than relying on random PagePrivate() check.
Data path is not affected, as it will lock the page before reading,
while unlocking the page after the last read has finished, thus no race
window.
[FIX]
This patch will fix the bug by repurposing btrfs_subpage::readers.
Now btrfs_subpage::readers will be a member shared by both metadata and
data.
For metadata path, we don't do the page unlock as metadata only relies
on extent locking.
At the same time, teach page_range_has_eb() to take
btrfs_subpage::readers into consideration.
So that even if the last eb of a page gets freed, page::private won't be
detached as long as there still are pending end_page_read() calls.
By this we eliminate the race window, this will slight increase the
metadata memory usage, as the page may not be released as frequently as
usual. But it should not be a big deal.
The code got introduced in ("btrfs: submit read time repair only for
each corrupted sector"), but the fix is in a separate patch to keep the
problem description and the crash is rare so it should not hurt
bisectability.
Signed-off-by: Qu Wegruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-06-07 17:02:58 +08:00
|
|
|
* page range and no unfinished IO.
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
*/
|
|
|
|
if (!page_range_has_eb(fs_info, page))
|
|
|
|
btrfs_detach_subpage(fs_info, page);
|
|
|
|
|
|
|
|
spin_unlock(&page->mapping->private_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Release all pages attached to the extent buffer */
|
|
|
|
static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
int num_pages;
|
|
|
|
|
|
|
|
ASSERT(!extent_buffer_under_io(eb));
|
|
|
|
|
|
|
|
num_pages = num_extent_pages(eb);
|
|
|
|
for (i = 0; i < num_pages; i++) {
|
|
|
|
struct page *page = eb->pages[i];
|
|
|
|
|
|
|
|
if (!page)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
detach_extent_buffer_page(eb, page);
|
2015-02-09 17:31:45 +08:00
|
|
|
|
2016-05-20 09:18:45 +08:00
|
|
|
/* One for when we allocated the page */
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
put_page(page);
|
2018-06-27 21:38:22 +08:00
|
|
|
}
|
2013-08-08 02:54:37 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Helper for releasing the extent buffer.
|
|
|
|
*/
|
|
|
|
static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
|
|
|
|
{
|
2018-07-19 23:24:32 +08:00
|
|
|
btrfs_release_extent_buffer_pages(eb);
|
2022-09-10 05:53:19 +08:00
|
|
|
btrfs_leak_debug_del_eb(eb);
|
2013-08-08 02:54:37 +08:00
|
|
|
__free_extent_buffer(eb);
|
|
|
|
}
|
|
|
|
|
2013-12-17 02:24:27 +08:00
|
|
|
static struct extent_buffer *
|
|
|
|
__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
|
2014-06-15 08:55:29 +08:00
|
|
|
unsigned long len)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
struct extent_buffer *eb = NULL;
|
|
|
|
|
2015-08-19 20:17:40 +08:00
|
|
|
eb = kmem_cache_zalloc(extent_buffer_cache, GFP_NOFS|__GFP_NOFAIL);
|
2008-01-25 05:13:08 +08:00
|
|
|
eb->start = start;
|
|
|
|
eb->len = len;
|
2013-12-17 02:24:27 +08:00
|
|
|
eb->fs_info = fs_info;
|
btrfs: switch extent buffer tree lock to rw_semaphore
Historically we've implemented our own locking because we wanted to be
able to selectively spin or sleep based on what we were doing in the
tree. For instance, if all of our nodes were in cache then there's
rarely a reason to need to sleep waiting for node locks, as they'll
likely become available soon. At the time this code was written the
rw_semaphore didn't do adaptive spinning, and thus was orders of
magnitude slower than our home grown locking.
However now the opposite is the case. There are a few problems with how
we implement blocking locks, namely that we use a normal waitqueue and
simply wake everybody up in reverse sleep order. This leads to some
suboptimal performance behavior, and a lot of context switches in highly
contended cases. The rw_semaphores actually do this properly, and also
have adaptive spinning that works relatively well.
The locking code is also a bit of a bear to understand, and we lose the
benefit of lockdep for the most part because the blocking states of the
lock are simply ad-hoc and not mapped into lockdep.
So rework the locking code to drop all of this custom locking stuff, and
simply use a rw_semaphore for everything. This makes the locking much
simpler for everything, as we can now drop a lot of cruft and blocking
transitions. The performance numbers vary depending on the workload,
because generally speaking there doesn't tend to be a lot of contention
on the btree. However, on my test system which is an 80 core single
socket system with 256GiB of RAM and a 2TiB NVMe drive I get the
following results (with all debug options off):
dbench 200 baseline
Throughput 216.056 MB/sec 200 clients 200 procs max_latency=1471.197 ms
dbench 200 with patch
Throughput 737.188 MB/sec 200 clients 200 procs max_latency=714.346 ms
Previously we also used fs_mark to test this sort of contention, and
those results are far less impressive, mostly because there's not enough
tasks to really stress the locking
fs_mark -d /d[0-15] -S 0 -L 20 -n 100000 -s 0 -t 16
baseline
Average Files/sec: 160166.7
p50 Files/sec: 165832
p90 Files/sec: 123886
p99 Files/sec: 123495
real 3m26.527s
user 2m19.223s
sys 48m21.856s
patched
Average Files/sec: 164135.7
p50 Files/sec: 171095
p90 Files/sec: 122889
p99 Files/sec: 113819
real 3m29.660s
user 2m19.990s
sys 44m12.259s
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:09 +08:00
|
|
|
init_rwsem(&eb->lock);
|
Btrfs: Change btree locking to use explicit blocking points
Most of the btrfs metadata operations can be protected by a spinlock,
but some operations still need to schedule.
So far, btrfs has been using a mutex along with a trylock loop,
most of the time it is able to avoid going for the full mutex, so
the trylock loop is a big performance gain.
This commit is step one for getting rid of the blocking locks entirely.
btrfs_tree_lock takes a spinlock, and the code explicitly switches
to a blocking lock when it starts an operation that can schedule.
We'll be able get rid of the blocking locks in smaller pieces over time.
Tracing allows us to find the most common cause of blocking, so we
can start with the hot spots first.
The basic idea is:
btrfs_tree_lock() returns with the spin lock held
btrfs_set_lock_blocking() sets the EXTENT_BUFFER_BLOCKING bit in
the extent buffer flags, and then drops the spin lock. The buffer is
still considered locked by all of the btrfs code.
If btrfs_tree_lock gets the spinlock but finds the blocking bit set, it drops
the spin lock and waits on a wait queue for the blocking bit to go away.
Much of the code that needs to set the blocking bit finishes without actually
blocking a good percentage of the time. So, an adaptive spin is still
used against the blocking bit to avoid very high context switch rates.
btrfs_clear_lock_blocking() clears the blocking bit and returns
with the spinlock held again.
btrfs_tree_unlock() can be called on either blocking or spinning locks,
it does the right thing based on the blocking bit.
ctree.c has a helper function to set/clear all the locked buffers in a
path as blocking.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-02-04 22:25:08 +08:00
|
|
|
|
2022-09-10 05:53:19 +08:00
|
|
|
btrfs_leak_debug_add_eb(eb);
|
2021-02-04 18:21:54 +08:00
|
|
|
INIT_LIST_HEAD(&eb->release_list);
|
2013-04-23 00:12:31 +08:00
|
|
|
|
2012-03-10 05:01:49 +08:00
|
|
|
spin_lock_init(&eb->refs_lock);
|
2008-01-25 05:13:08 +08:00
|
|
|
atomic_set(&eb->refs, 1);
|
2012-03-13 21:38:00 +08:00
|
|
|
atomic_set(&eb->io_pages, 0);
|
2010-08-07 01:21:20 +08:00
|
|
|
|
2020-12-02 14:48:01 +08:00
|
|
|
ASSERT(len <= BTRFS_MAX_METADATA_BLOCKSIZE);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
|
|
|
return eb;
|
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src)
|
2012-05-16 23:00:02 +08:00
|
|
|
{
|
2018-03-02 01:20:27 +08:00
|
|
|
int i;
|
2012-05-16 23:00:02 +08:00
|
|
|
struct extent_buffer *new;
|
2018-03-02 01:20:27 +08:00
|
|
|
int num_pages = num_extent_pages(src);
|
2022-03-31 04:11:22 +08:00
|
|
|
int ret;
|
2012-05-16 23:00:02 +08:00
|
|
|
|
2014-06-15 09:20:26 +08:00
|
|
|
new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
|
2012-05-16 23:00:02 +08:00
|
|
|
if (new == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
2021-01-26 16:33:46 +08:00
|
|
|
/*
|
|
|
|
* Set UNMAPPED before calling btrfs_release_extent_buffer(), as
|
|
|
|
* btrfs_release_extent_buffer() have different behavior for
|
|
|
|
* UNMAPPED subpage extent buffer.
|
|
|
|
*/
|
|
|
|
set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
|
|
|
|
|
2022-03-31 04:11:22 +08:00
|
|
|
ret = btrfs_alloc_page_array(num_pages, new->pages);
|
|
|
|
if (ret) {
|
|
|
|
btrfs_release_extent_buffer(new);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2012-05-16 23:00:02 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2021-01-26 16:33:48 +08:00
|
|
|
int ret;
|
2022-03-31 04:11:22 +08:00
|
|
|
struct page *p = new->pages[i];
|
2021-01-26 16:33:48 +08:00
|
|
|
|
|
|
|
ret = attach_extent_buffer_page(new, p, NULL);
|
|
|
|
if (ret < 0) {
|
|
|
|
btrfs_release_extent_buffer(new);
|
|
|
|
return NULL;
|
|
|
|
}
|
2012-05-16 23:00:02 +08:00
|
|
|
WARN_ON(PageDirty(p));
|
2016-11-09 00:56:24 +08:00
|
|
|
copy_page(page_address(p), page_address(src->pages[i]));
|
2012-05-16 23:00:02 +08:00
|
|
|
}
|
2021-01-26 16:33:55 +08:00
|
|
|
set_extent_buffer_uptodate(new);
|
2012-05-16 23:00:02 +08:00
|
|
|
|
|
|
|
return new;
|
|
|
|
}
|
|
|
|
|
2015-09-30 11:50:31 +08:00
|
|
|
struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
|
|
|
|
u64 start, unsigned long len)
|
2012-05-16 23:00:02 +08:00
|
|
|
{
|
|
|
|
struct extent_buffer *eb;
|
2018-03-02 01:20:27 +08:00
|
|
|
int num_pages;
|
|
|
|
int i;
|
2022-03-31 04:11:22 +08:00
|
|
|
int ret;
|
2012-05-16 23:00:02 +08:00
|
|
|
|
2014-06-15 09:20:26 +08:00
|
|
|
eb = __alloc_extent_buffer(fs_info, start, len);
|
2012-05-16 23:00:02 +08:00
|
|
|
if (!eb)
|
|
|
|
return NULL;
|
|
|
|
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2022-03-31 04:11:22 +08:00
|
|
|
ret = btrfs_alloc_page_array(num_pages, eb->pages);
|
|
|
|
if (ret)
|
|
|
|
goto err;
|
|
|
|
|
2012-05-16 23:00:02 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2022-03-31 04:11:22 +08:00
|
|
|
struct page *p = eb->pages[i];
|
2021-01-26 16:33:51 +08:00
|
|
|
|
2022-03-31 04:11:22 +08:00
|
|
|
ret = attach_extent_buffer_page(eb, p, NULL);
|
2021-01-26 16:33:51 +08:00
|
|
|
if (ret < 0)
|
|
|
|
goto err;
|
2012-05-16 23:00:02 +08:00
|
|
|
}
|
2022-03-31 04:11:22 +08:00
|
|
|
|
2012-05-16 23:00:02 +08:00
|
|
|
set_extent_buffer_uptodate(eb);
|
|
|
|
btrfs_set_header_nritems(eb, 0);
|
2018-06-27 21:38:24 +08:00
|
|
|
set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
|
2012-05-16 23:00:02 +08:00
|
|
|
|
|
|
|
return eb;
|
|
|
|
err:
|
2022-03-31 04:11:22 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
|
|
|
if (eb->pages[i]) {
|
|
|
|
detach_extent_buffer_page(eb, eb->pages[i]);
|
|
|
|
__free_page(eb->pages[i]);
|
|
|
|
}
|
2021-01-26 16:33:51 +08:00
|
|
|
}
|
2012-05-16 23:00:02 +08:00
|
|
|
__free_extent_buffer(eb);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2015-09-30 11:50:31 +08:00
|
|
|
struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
|
2016-06-15 21:22:56 +08:00
|
|
|
u64 start)
|
2015-09-30 11:50:31 +08:00
|
|
|
{
|
2016-06-15 21:22:56 +08:00
|
|
|
return __alloc_dummy_extent_buffer(fs_info, start, fs_info->nodesize);
|
2015-09-30 11:50:31 +08:00
|
|
|
}
|
|
|
|
|
2012-03-13 21:38:00 +08:00
|
|
|
static void check_buffer_tree_ref(struct extent_buffer *eb)
|
|
|
|
{
|
2013-01-30 06:49:37 +08:00
|
|
|
int refs;
|
btrfs: fix fatal extent_buffer readahead vs releasepage race
Under somewhat convoluted conditions, it is possible to attempt to
release an extent_buffer that is under io, which triggers a BUG_ON in
btrfs_release_extent_buffer_pages.
This relies on a few different factors. First, extent_buffer reads done
as readahead for searching use WAIT_NONE, so they free the local extent
buffer reference while the io is outstanding. However, they should still
be protected by TREE_REF. However, if the system is doing signficant
reclaim, and simultaneously heavily accessing the extent_buffers, it is
possible for releasepage to race with two concurrent readahead attempts
in a way that leaves TREE_REF unset when the readahead extent buffer is
released.
Essentially, if two tasks race to allocate a new extent_buffer, but the
winner who attempts the first io is rebuffed by a page being locked
(likely by the reclaim itself) then the loser will still go ahead with
issuing the readahead. The loser's call to find_extent_buffer must also
race with the reclaim task reading the extent_buffer's refcount as 1 in
a way that allows the reclaim to re-clear the TREE_REF checked by
find_extent_buffer.
The following represents an example execution demonstrating the race:
CPU0 CPU1 CPU2
reada_for_search reada_for_search
readahead_tree_block readahead_tree_block
find_create_tree_block find_create_tree_block
alloc_extent_buffer alloc_extent_buffer
find_extent_buffer // not found
allocates eb
lock pages
associate pages to eb
insert eb into radix tree
set TREE_REF, refs == 2
unlock pages
read_extent_buffer_pages // WAIT_NONE
not uptodate (brand new eb)
lock_page
if !trylock_page
goto unlock_exit // not an error
free_extent_buffer
release_extent_buffer
atomic_dec_and_test refs to 1
find_extent_buffer // found
try_release_extent_buffer
take refs_lock
reads refs == 1; no io
atomic_inc_not_zero refs to 2
mark_buffer_accessed
check_buffer_tree_ref
// not STALE, won't take refs_lock
refs == 2; TREE_REF set // no action
read_extent_buffer_pages // WAIT_NONE
clear TREE_REF
release_extent_buffer
atomic_dec_and_test refs to 1
unlock_page
still not uptodate (CPU1 read failed on trylock_page)
locks pages
set io_pages > 0
submit io
return
free_extent_buffer
release_extent_buffer
dec refs to 0
delete from radix tree
btrfs_release_extent_buffer_pages
BUG_ON(io_pages > 0)!!!
We observe this at a very low rate in production and were also able to
reproduce it in a test environment by introducing some spurious delays
and by introducing probabilistic trylock_page failures.
To fix it, we apply check_tree_ref at a point where it could not
possibly be unset by a competing task: after io_pages has been
incremented. All the codepaths that clear TREE_REF check for io, so they
would not be able to clear it after this point until the io is done.
Stack trace, for reference:
[1417839.424739] ------------[ cut here ]------------
[1417839.435328] kernel BUG at fs/btrfs/extent_io.c:4841!
[1417839.447024] invalid opcode: 0000 [#1] SMP
[1417839.502972] RIP: 0010:btrfs_release_extent_buffer_pages+0x20/0x1f0
[1417839.517008] Code: ed e9 ...
[1417839.558895] RSP: 0018:ffffc90020bcf798 EFLAGS: 00010202
[1417839.570816] RAX: 0000000000000002 RBX: ffff888102d6def0 RCX: 0000000000000028
[1417839.586962] RDX: 0000000000000002 RSI: ffff8887f0296482 RDI: ffff888102d6def0
[1417839.603108] RBP: ffff88885664a000 R08: 0000000000000046 R09: 0000000000000238
[1417839.619255] R10: 0000000000000028 R11: ffff88885664af68 R12: 0000000000000000
[1417839.635402] R13: 0000000000000000 R14: ffff88875f573ad0 R15: ffff888797aafd90
[1417839.651549] FS: 00007f5a844fa700(0000) GS:ffff88885f680000(0000) knlGS:0000000000000000
[1417839.669810] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1417839.682887] CR2: 00007f7884541fe0 CR3: 000000049f609002 CR4: 00000000003606e0
[1417839.699037] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[1417839.715187] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[1417839.731320] Call Trace:
[1417839.737103] release_extent_buffer+0x39/0x90
[1417839.746913] read_block_for_search.isra.38+0x2a3/0x370
[1417839.758645] btrfs_search_slot+0x260/0x9b0
[1417839.768054] btrfs_lookup_file_extent+0x4a/0x70
[1417839.778427] btrfs_get_extent+0x15f/0x830
[1417839.787665] ? submit_extent_page+0xc4/0x1c0
[1417839.797474] ? __do_readpage+0x299/0x7a0
[1417839.806515] __do_readpage+0x33b/0x7a0
[1417839.815171] ? btrfs_releasepage+0x70/0x70
[1417839.824597] extent_readpages+0x28f/0x400
[1417839.833836] read_pages+0x6a/0x1c0
[1417839.841729] ? startup_64+0x2/0x30
[1417839.849624] __do_page_cache_readahead+0x13c/0x1a0
[1417839.860590] filemap_fault+0x6c7/0x990
[1417839.869252] ? xas_load+0x8/0x80
[1417839.876756] ? xas_find+0x150/0x190
[1417839.884839] ? filemap_map_pages+0x295/0x3b0
[1417839.894652] __do_fault+0x32/0x110
[1417839.902540] __handle_mm_fault+0xacd/0x1000
[1417839.912156] handle_mm_fault+0xaa/0x1c0
[1417839.921004] __do_page_fault+0x242/0x4b0
[1417839.930044] ? page_fault+0x8/0x30
[1417839.937933] page_fault+0x1e/0x30
[1417839.945631] RIP: 0033:0x33c4bae
[1417839.952927] Code: Bad RIP value.
[1417839.960411] RSP: 002b:00007f5a844f7350 EFLAGS: 00010206
[1417839.972331] RAX: 000000000000006e RBX: 1614b3ff6a50398a RCX: 0000000000000000
[1417839.988477] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000002
[1417840.004626] RBP: 00007f5a844f7420 R08: 000000000000006e R09: 00007f5a94aeccb8
[1417840.020784] R10: 00007f5a844f7350 R11: 0000000000000000 R12: 00007f5a94aecc79
[1417840.036932] R13: 00007f5a94aecc78 R14: 00007f5a94aecc90 R15: 00007f5a94aecc40
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-06-18 02:35:19 +08:00
|
|
|
/*
|
|
|
|
* The TREE_REF bit is first set when the extent_buffer is added
|
|
|
|
* to the radix tree. It is also reset, if unset, when a new reference
|
|
|
|
* is created by find_extent_buffer.
|
2012-03-13 21:38:00 +08:00
|
|
|
*
|
btrfs: fix fatal extent_buffer readahead vs releasepage race
Under somewhat convoluted conditions, it is possible to attempt to
release an extent_buffer that is under io, which triggers a BUG_ON in
btrfs_release_extent_buffer_pages.
This relies on a few different factors. First, extent_buffer reads done
as readahead for searching use WAIT_NONE, so they free the local extent
buffer reference while the io is outstanding. However, they should still
be protected by TREE_REF. However, if the system is doing signficant
reclaim, and simultaneously heavily accessing the extent_buffers, it is
possible for releasepage to race with two concurrent readahead attempts
in a way that leaves TREE_REF unset when the readahead extent buffer is
released.
Essentially, if two tasks race to allocate a new extent_buffer, but the
winner who attempts the first io is rebuffed by a page being locked
(likely by the reclaim itself) then the loser will still go ahead with
issuing the readahead. The loser's call to find_extent_buffer must also
race with the reclaim task reading the extent_buffer's refcount as 1 in
a way that allows the reclaim to re-clear the TREE_REF checked by
find_extent_buffer.
The following represents an example execution demonstrating the race:
CPU0 CPU1 CPU2
reada_for_search reada_for_search
readahead_tree_block readahead_tree_block
find_create_tree_block find_create_tree_block
alloc_extent_buffer alloc_extent_buffer
find_extent_buffer // not found
allocates eb
lock pages
associate pages to eb
insert eb into radix tree
set TREE_REF, refs == 2
unlock pages
read_extent_buffer_pages // WAIT_NONE
not uptodate (brand new eb)
lock_page
if !trylock_page
goto unlock_exit // not an error
free_extent_buffer
release_extent_buffer
atomic_dec_and_test refs to 1
find_extent_buffer // found
try_release_extent_buffer
take refs_lock
reads refs == 1; no io
atomic_inc_not_zero refs to 2
mark_buffer_accessed
check_buffer_tree_ref
// not STALE, won't take refs_lock
refs == 2; TREE_REF set // no action
read_extent_buffer_pages // WAIT_NONE
clear TREE_REF
release_extent_buffer
atomic_dec_and_test refs to 1
unlock_page
still not uptodate (CPU1 read failed on trylock_page)
locks pages
set io_pages > 0
submit io
return
free_extent_buffer
release_extent_buffer
dec refs to 0
delete from radix tree
btrfs_release_extent_buffer_pages
BUG_ON(io_pages > 0)!!!
We observe this at a very low rate in production and were also able to
reproduce it in a test environment by introducing some spurious delays
and by introducing probabilistic trylock_page failures.
To fix it, we apply check_tree_ref at a point where it could not
possibly be unset by a competing task: after io_pages has been
incremented. All the codepaths that clear TREE_REF check for io, so they
would not be able to clear it after this point until the io is done.
Stack trace, for reference:
[1417839.424739] ------------[ cut here ]------------
[1417839.435328] kernel BUG at fs/btrfs/extent_io.c:4841!
[1417839.447024] invalid opcode: 0000 [#1] SMP
[1417839.502972] RIP: 0010:btrfs_release_extent_buffer_pages+0x20/0x1f0
[1417839.517008] Code: ed e9 ...
[1417839.558895] RSP: 0018:ffffc90020bcf798 EFLAGS: 00010202
[1417839.570816] RAX: 0000000000000002 RBX: ffff888102d6def0 RCX: 0000000000000028
[1417839.586962] RDX: 0000000000000002 RSI: ffff8887f0296482 RDI: ffff888102d6def0
[1417839.603108] RBP: ffff88885664a000 R08: 0000000000000046 R09: 0000000000000238
[1417839.619255] R10: 0000000000000028 R11: ffff88885664af68 R12: 0000000000000000
[1417839.635402] R13: 0000000000000000 R14: ffff88875f573ad0 R15: ffff888797aafd90
[1417839.651549] FS: 00007f5a844fa700(0000) GS:ffff88885f680000(0000) knlGS:0000000000000000
[1417839.669810] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1417839.682887] CR2: 00007f7884541fe0 CR3: 000000049f609002 CR4: 00000000003606e0
[1417839.699037] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[1417839.715187] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[1417839.731320] Call Trace:
[1417839.737103] release_extent_buffer+0x39/0x90
[1417839.746913] read_block_for_search.isra.38+0x2a3/0x370
[1417839.758645] btrfs_search_slot+0x260/0x9b0
[1417839.768054] btrfs_lookup_file_extent+0x4a/0x70
[1417839.778427] btrfs_get_extent+0x15f/0x830
[1417839.787665] ? submit_extent_page+0xc4/0x1c0
[1417839.797474] ? __do_readpage+0x299/0x7a0
[1417839.806515] __do_readpage+0x33b/0x7a0
[1417839.815171] ? btrfs_releasepage+0x70/0x70
[1417839.824597] extent_readpages+0x28f/0x400
[1417839.833836] read_pages+0x6a/0x1c0
[1417839.841729] ? startup_64+0x2/0x30
[1417839.849624] __do_page_cache_readahead+0x13c/0x1a0
[1417839.860590] filemap_fault+0x6c7/0x990
[1417839.869252] ? xas_load+0x8/0x80
[1417839.876756] ? xas_find+0x150/0x190
[1417839.884839] ? filemap_map_pages+0x295/0x3b0
[1417839.894652] __do_fault+0x32/0x110
[1417839.902540] __handle_mm_fault+0xacd/0x1000
[1417839.912156] handle_mm_fault+0xaa/0x1c0
[1417839.921004] __do_page_fault+0x242/0x4b0
[1417839.930044] ? page_fault+0x8/0x30
[1417839.937933] page_fault+0x1e/0x30
[1417839.945631] RIP: 0033:0x33c4bae
[1417839.952927] Code: Bad RIP value.
[1417839.960411] RSP: 002b:00007f5a844f7350 EFLAGS: 00010206
[1417839.972331] RAX: 000000000000006e RBX: 1614b3ff6a50398a RCX: 0000000000000000
[1417839.988477] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000002
[1417840.004626] RBP: 00007f5a844f7420 R08: 000000000000006e R09: 00007f5a94aeccb8
[1417840.020784] R10: 00007f5a844f7350 R11: 0000000000000000 R12: 00007f5a94aecc79
[1417840.036932] R13: 00007f5a94aecc78 R14: 00007f5a94aecc90 R15: 00007f5a94aecc40
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-06-18 02:35:19 +08:00
|
|
|
* It is only cleared in two cases: freeing the last non-tree
|
|
|
|
* reference to the extent_buffer when its STALE bit is set or
|
2022-05-01 11:15:16 +08:00
|
|
|
* calling release_folio when the tree reference is the only reference.
|
2012-03-13 21:38:00 +08:00
|
|
|
*
|
btrfs: fix fatal extent_buffer readahead vs releasepage race
Under somewhat convoluted conditions, it is possible to attempt to
release an extent_buffer that is under io, which triggers a BUG_ON in
btrfs_release_extent_buffer_pages.
This relies on a few different factors. First, extent_buffer reads done
as readahead for searching use WAIT_NONE, so they free the local extent
buffer reference while the io is outstanding. However, they should still
be protected by TREE_REF. However, if the system is doing signficant
reclaim, and simultaneously heavily accessing the extent_buffers, it is
possible for releasepage to race with two concurrent readahead attempts
in a way that leaves TREE_REF unset when the readahead extent buffer is
released.
Essentially, if two tasks race to allocate a new extent_buffer, but the
winner who attempts the first io is rebuffed by a page being locked
(likely by the reclaim itself) then the loser will still go ahead with
issuing the readahead. The loser's call to find_extent_buffer must also
race with the reclaim task reading the extent_buffer's refcount as 1 in
a way that allows the reclaim to re-clear the TREE_REF checked by
find_extent_buffer.
The following represents an example execution demonstrating the race:
CPU0 CPU1 CPU2
reada_for_search reada_for_search
readahead_tree_block readahead_tree_block
find_create_tree_block find_create_tree_block
alloc_extent_buffer alloc_extent_buffer
find_extent_buffer // not found
allocates eb
lock pages
associate pages to eb
insert eb into radix tree
set TREE_REF, refs == 2
unlock pages
read_extent_buffer_pages // WAIT_NONE
not uptodate (brand new eb)
lock_page
if !trylock_page
goto unlock_exit // not an error
free_extent_buffer
release_extent_buffer
atomic_dec_and_test refs to 1
find_extent_buffer // found
try_release_extent_buffer
take refs_lock
reads refs == 1; no io
atomic_inc_not_zero refs to 2
mark_buffer_accessed
check_buffer_tree_ref
// not STALE, won't take refs_lock
refs == 2; TREE_REF set // no action
read_extent_buffer_pages // WAIT_NONE
clear TREE_REF
release_extent_buffer
atomic_dec_and_test refs to 1
unlock_page
still not uptodate (CPU1 read failed on trylock_page)
locks pages
set io_pages > 0
submit io
return
free_extent_buffer
release_extent_buffer
dec refs to 0
delete from radix tree
btrfs_release_extent_buffer_pages
BUG_ON(io_pages > 0)!!!
We observe this at a very low rate in production and were also able to
reproduce it in a test environment by introducing some spurious delays
and by introducing probabilistic trylock_page failures.
To fix it, we apply check_tree_ref at a point where it could not
possibly be unset by a competing task: after io_pages has been
incremented. All the codepaths that clear TREE_REF check for io, so they
would not be able to clear it after this point until the io is done.
Stack trace, for reference:
[1417839.424739] ------------[ cut here ]------------
[1417839.435328] kernel BUG at fs/btrfs/extent_io.c:4841!
[1417839.447024] invalid opcode: 0000 [#1] SMP
[1417839.502972] RIP: 0010:btrfs_release_extent_buffer_pages+0x20/0x1f0
[1417839.517008] Code: ed e9 ...
[1417839.558895] RSP: 0018:ffffc90020bcf798 EFLAGS: 00010202
[1417839.570816] RAX: 0000000000000002 RBX: ffff888102d6def0 RCX: 0000000000000028
[1417839.586962] RDX: 0000000000000002 RSI: ffff8887f0296482 RDI: ffff888102d6def0
[1417839.603108] RBP: ffff88885664a000 R08: 0000000000000046 R09: 0000000000000238
[1417839.619255] R10: 0000000000000028 R11: ffff88885664af68 R12: 0000000000000000
[1417839.635402] R13: 0000000000000000 R14: ffff88875f573ad0 R15: ffff888797aafd90
[1417839.651549] FS: 00007f5a844fa700(0000) GS:ffff88885f680000(0000) knlGS:0000000000000000
[1417839.669810] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1417839.682887] CR2: 00007f7884541fe0 CR3: 000000049f609002 CR4: 00000000003606e0
[1417839.699037] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[1417839.715187] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[1417839.731320] Call Trace:
[1417839.737103] release_extent_buffer+0x39/0x90
[1417839.746913] read_block_for_search.isra.38+0x2a3/0x370
[1417839.758645] btrfs_search_slot+0x260/0x9b0
[1417839.768054] btrfs_lookup_file_extent+0x4a/0x70
[1417839.778427] btrfs_get_extent+0x15f/0x830
[1417839.787665] ? submit_extent_page+0xc4/0x1c0
[1417839.797474] ? __do_readpage+0x299/0x7a0
[1417839.806515] __do_readpage+0x33b/0x7a0
[1417839.815171] ? btrfs_releasepage+0x70/0x70
[1417839.824597] extent_readpages+0x28f/0x400
[1417839.833836] read_pages+0x6a/0x1c0
[1417839.841729] ? startup_64+0x2/0x30
[1417839.849624] __do_page_cache_readahead+0x13c/0x1a0
[1417839.860590] filemap_fault+0x6c7/0x990
[1417839.869252] ? xas_load+0x8/0x80
[1417839.876756] ? xas_find+0x150/0x190
[1417839.884839] ? filemap_map_pages+0x295/0x3b0
[1417839.894652] __do_fault+0x32/0x110
[1417839.902540] __handle_mm_fault+0xacd/0x1000
[1417839.912156] handle_mm_fault+0xaa/0x1c0
[1417839.921004] __do_page_fault+0x242/0x4b0
[1417839.930044] ? page_fault+0x8/0x30
[1417839.937933] page_fault+0x1e/0x30
[1417839.945631] RIP: 0033:0x33c4bae
[1417839.952927] Code: Bad RIP value.
[1417839.960411] RSP: 002b:00007f5a844f7350 EFLAGS: 00010206
[1417839.972331] RAX: 000000000000006e RBX: 1614b3ff6a50398a RCX: 0000000000000000
[1417839.988477] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000002
[1417840.004626] RBP: 00007f5a844f7420 R08: 000000000000006e R09: 00007f5a94aeccb8
[1417840.020784] R10: 00007f5a844f7350 R11: 0000000000000000 R12: 00007f5a94aecc79
[1417840.036932] R13: 00007f5a94aecc78 R14: 00007f5a94aecc90 R15: 00007f5a94aecc40
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-06-18 02:35:19 +08:00
|
|
|
* In both cases, care is taken to ensure that the extent_buffer's
|
2022-05-01 11:15:16 +08:00
|
|
|
* pages are not under io. However, release_folio can be concurrently
|
btrfs: fix fatal extent_buffer readahead vs releasepage race
Under somewhat convoluted conditions, it is possible to attempt to
release an extent_buffer that is under io, which triggers a BUG_ON in
btrfs_release_extent_buffer_pages.
This relies on a few different factors. First, extent_buffer reads done
as readahead for searching use WAIT_NONE, so they free the local extent
buffer reference while the io is outstanding. However, they should still
be protected by TREE_REF. However, if the system is doing signficant
reclaim, and simultaneously heavily accessing the extent_buffers, it is
possible for releasepage to race with two concurrent readahead attempts
in a way that leaves TREE_REF unset when the readahead extent buffer is
released.
Essentially, if two tasks race to allocate a new extent_buffer, but the
winner who attempts the first io is rebuffed by a page being locked
(likely by the reclaim itself) then the loser will still go ahead with
issuing the readahead. The loser's call to find_extent_buffer must also
race with the reclaim task reading the extent_buffer's refcount as 1 in
a way that allows the reclaim to re-clear the TREE_REF checked by
find_extent_buffer.
The following represents an example execution demonstrating the race:
CPU0 CPU1 CPU2
reada_for_search reada_for_search
readahead_tree_block readahead_tree_block
find_create_tree_block find_create_tree_block
alloc_extent_buffer alloc_extent_buffer
find_extent_buffer // not found
allocates eb
lock pages
associate pages to eb
insert eb into radix tree
set TREE_REF, refs == 2
unlock pages
read_extent_buffer_pages // WAIT_NONE
not uptodate (brand new eb)
lock_page
if !trylock_page
goto unlock_exit // not an error
free_extent_buffer
release_extent_buffer
atomic_dec_and_test refs to 1
find_extent_buffer // found
try_release_extent_buffer
take refs_lock
reads refs == 1; no io
atomic_inc_not_zero refs to 2
mark_buffer_accessed
check_buffer_tree_ref
// not STALE, won't take refs_lock
refs == 2; TREE_REF set // no action
read_extent_buffer_pages // WAIT_NONE
clear TREE_REF
release_extent_buffer
atomic_dec_and_test refs to 1
unlock_page
still not uptodate (CPU1 read failed on trylock_page)
locks pages
set io_pages > 0
submit io
return
free_extent_buffer
release_extent_buffer
dec refs to 0
delete from radix tree
btrfs_release_extent_buffer_pages
BUG_ON(io_pages > 0)!!!
We observe this at a very low rate in production and were also able to
reproduce it in a test environment by introducing some spurious delays
and by introducing probabilistic trylock_page failures.
To fix it, we apply check_tree_ref at a point where it could not
possibly be unset by a competing task: after io_pages has been
incremented. All the codepaths that clear TREE_REF check for io, so they
would not be able to clear it after this point until the io is done.
Stack trace, for reference:
[1417839.424739] ------------[ cut here ]------------
[1417839.435328] kernel BUG at fs/btrfs/extent_io.c:4841!
[1417839.447024] invalid opcode: 0000 [#1] SMP
[1417839.502972] RIP: 0010:btrfs_release_extent_buffer_pages+0x20/0x1f0
[1417839.517008] Code: ed e9 ...
[1417839.558895] RSP: 0018:ffffc90020bcf798 EFLAGS: 00010202
[1417839.570816] RAX: 0000000000000002 RBX: ffff888102d6def0 RCX: 0000000000000028
[1417839.586962] RDX: 0000000000000002 RSI: ffff8887f0296482 RDI: ffff888102d6def0
[1417839.603108] RBP: ffff88885664a000 R08: 0000000000000046 R09: 0000000000000238
[1417839.619255] R10: 0000000000000028 R11: ffff88885664af68 R12: 0000000000000000
[1417839.635402] R13: 0000000000000000 R14: ffff88875f573ad0 R15: ffff888797aafd90
[1417839.651549] FS: 00007f5a844fa700(0000) GS:ffff88885f680000(0000) knlGS:0000000000000000
[1417839.669810] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1417839.682887] CR2: 00007f7884541fe0 CR3: 000000049f609002 CR4: 00000000003606e0
[1417839.699037] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[1417839.715187] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[1417839.731320] Call Trace:
[1417839.737103] release_extent_buffer+0x39/0x90
[1417839.746913] read_block_for_search.isra.38+0x2a3/0x370
[1417839.758645] btrfs_search_slot+0x260/0x9b0
[1417839.768054] btrfs_lookup_file_extent+0x4a/0x70
[1417839.778427] btrfs_get_extent+0x15f/0x830
[1417839.787665] ? submit_extent_page+0xc4/0x1c0
[1417839.797474] ? __do_readpage+0x299/0x7a0
[1417839.806515] __do_readpage+0x33b/0x7a0
[1417839.815171] ? btrfs_releasepage+0x70/0x70
[1417839.824597] extent_readpages+0x28f/0x400
[1417839.833836] read_pages+0x6a/0x1c0
[1417839.841729] ? startup_64+0x2/0x30
[1417839.849624] __do_page_cache_readahead+0x13c/0x1a0
[1417839.860590] filemap_fault+0x6c7/0x990
[1417839.869252] ? xas_load+0x8/0x80
[1417839.876756] ? xas_find+0x150/0x190
[1417839.884839] ? filemap_map_pages+0x295/0x3b0
[1417839.894652] __do_fault+0x32/0x110
[1417839.902540] __handle_mm_fault+0xacd/0x1000
[1417839.912156] handle_mm_fault+0xaa/0x1c0
[1417839.921004] __do_page_fault+0x242/0x4b0
[1417839.930044] ? page_fault+0x8/0x30
[1417839.937933] page_fault+0x1e/0x30
[1417839.945631] RIP: 0033:0x33c4bae
[1417839.952927] Code: Bad RIP value.
[1417839.960411] RSP: 002b:00007f5a844f7350 EFLAGS: 00010206
[1417839.972331] RAX: 000000000000006e RBX: 1614b3ff6a50398a RCX: 0000000000000000
[1417839.988477] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000002
[1417840.004626] RBP: 00007f5a844f7420 R08: 000000000000006e R09: 00007f5a94aeccb8
[1417840.020784] R10: 00007f5a844f7350 R11: 0000000000000000 R12: 00007f5a94aecc79
[1417840.036932] R13: 00007f5a94aecc78 R14: 00007f5a94aecc90 R15: 00007f5a94aecc40
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-06-18 02:35:19 +08:00
|
|
|
* called with creating new references, which is prone to race
|
|
|
|
* conditions between the calls to check_buffer_tree_ref in those
|
|
|
|
* codepaths and clearing TREE_REF in try_release_extent_buffer.
|
2012-03-13 21:38:00 +08:00
|
|
|
*
|
btrfs: fix fatal extent_buffer readahead vs releasepage race
Under somewhat convoluted conditions, it is possible to attempt to
release an extent_buffer that is under io, which triggers a BUG_ON in
btrfs_release_extent_buffer_pages.
This relies on a few different factors. First, extent_buffer reads done
as readahead for searching use WAIT_NONE, so they free the local extent
buffer reference while the io is outstanding. However, they should still
be protected by TREE_REF. However, if the system is doing signficant
reclaim, and simultaneously heavily accessing the extent_buffers, it is
possible for releasepage to race with two concurrent readahead attempts
in a way that leaves TREE_REF unset when the readahead extent buffer is
released.
Essentially, if two tasks race to allocate a new extent_buffer, but the
winner who attempts the first io is rebuffed by a page being locked
(likely by the reclaim itself) then the loser will still go ahead with
issuing the readahead. The loser's call to find_extent_buffer must also
race with the reclaim task reading the extent_buffer's refcount as 1 in
a way that allows the reclaim to re-clear the TREE_REF checked by
find_extent_buffer.
The following represents an example execution demonstrating the race:
CPU0 CPU1 CPU2
reada_for_search reada_for_search
readahead_tree_block readahead_tree_block
find_create_tree_block find_create_tree_block
alloc_extent_buffer alloc_extent_buffer
find_extent_buffer // not found
allocates eb
lock pages
associate pages to eb
insert eb into radix tree
set TREE_REF, refs == 2
unlock pages
read_extent_buffer_pages // WAIT_NONE
not uptodate (brand new eb)
lock_page
if !trylock_page
goto unlock_exit // not an error
free_extent_buffer
release_extent_buffer
atomic_dec_and_test refs to 1
find_extent_buffer // found
try_release_extent_buffer
take refs_lock
reads refs == 1; no io
atomic_inc_not_zero refs to 2
mark_buffer_accessed
check_buffer_tree_ref
// not STALE, won't take refs_lock
refs == 2; TREE_REF set // no action
read_extent_buffer_pages // WAIT_NONE
clear TREE_REF
release_extent_buffer
atomic_dec_and_test refs to 1
unlock_page
still not uptodate (CPU1 read failed on trylock_page)
locks pages
set io_pages > 0
submit io
return
free_extent_buffer
release_extent_buffer
dec refs to 0
delete from radix tree
btrfs_release_extent_buffer_pages
BUG_ON(io_pages > 0)!!!
We observe this at a very low rate in production and were also able to
reproduce it in a test environment by introducing some spurious delays
and by introducing probabilistic trylock_page failures.
To fix it, we apply check_tree_ref at a point where it could not
possibly be unset by a competing task: after io_pages has been
incremented. All the codepaths that clear TREE_REF check for io, so they
would not be able to clear it after this point until the io is done.
Stack trace, for reference:
[1417839.424739] ------------[ cut here ]------------
[1417839.435328] kernel BUG at fs/btrfs/extent_io.c:4841!
[1417839.447024] invalid opcode: 0000 [#1] SMP
[1417839.502972] RIP: 0010:btrfs_release_extent_buffer_pages+0x20/0x1f0
[1417839.517008] Code: ed e9 ...
[1417839.558895] RSP: 0018:ffffc90020bcf798 EFLAGS: 00010202
[1417839.570816] RAX: 0000000000000002 RBX: ffff888102d6def0 RCX: 0000000000000028
[1417839.586962] RDX: 0000000000000002 RSI: ffff8887f0296482 RDI: ffff888102d6def0
[1417839.603108] RBP: ffff88885664a000 R08: 0000000000000046 R09: 0000000000000238
[1417839.619255] R10: 0000000000000028 R11: ffff88885664af68 R12: 0000000000000000
[1417839.635402] R13: 0000000000000000 R14: ffff88875f573ad0 R15: ffff888797aafd90
[1417839.651549] FS: 00007f5a844fa700(0000) GS:ffff88885f680000(0000) knlGS:0000000000000000
[1417839.669810] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1417839.682887] CR2: 00007f7884541fe0 CR3: 000000049f609002 CR4: 00000000003606e0
[1417839.699037] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[1417839.715187] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[1417839.731320] Call Trace:
[1417839.737103] release_extent_buffer+0x39/0x90
[1417839.746913] read_block_for_search.isra.38+0x2a3/0x370
[1417839.758645] btrfs_search_slot+0x260/0x9b0
[1417839.768054] btrfs_lookup_file_extent+0x4a/0x70
[1417839.778427] btrfs_get_extent+0x15f/0x830
[1417839.787665] ? submit_extent_page+0xc4/0x1c0
[1417839.797474] ? __do_readpage+0x299/0x7a0
[1417839.806515] __do_readpage+0x33b/0x7a0
[1417839.815171] ? btrfs_releasepage+0x70/0x70
[1417839.824597] extent_readpages+0x28f/0x400
[1417839.833836] read_pages+0x6a/0x1c0
[1417839.841729] ? startup_64+0x2/0x30
[1417839.849624] __do_page_cache_readahead+0x13c/0x1a0
[1417839.860590] filemap_fault+0x6c7/0x990
[1417839.869252] ? xas_load+0x8/0x80
[1417839.876756] ? xas_find+0x150/0x190
[1417839.884839] ? filemap_map_pages+0x295/0x3b0
[1417839.894652] __do_fault+0x32/0x110
[1417839.902540] __handle_mm_fault+0xacd/0x1000
[1417839.912156] handle_mm_fault+0xaa/0x1c0
[1417839.921004] __do_page_fault+0x242/0x4b0
[1417839.930044] ? page_fault+0x8/0x30
[1417839.937933] page_fault+0x1e/0x30
[1417839.945631] RIP: 0033:0x33c4bae
[1417839.952927] Code: Bad RIP value.
[1417839.960411] RSP: 002b:00007f5a844f7350 EFLAGS: 00010206
[1417839.972331] RAX: 000000000000006e RBX: 1614b3ff6a50398a RCX: 0000000000000000
[1417839.988477] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000002
[1417840.004626] RBP: 00007f5a844f7420 R08: 000000000000006e R09: 00007f5a94aeccb8
[1417840.020784] R10: 00007f5a844f7350 R11: 0000000000000000 R12: 00007f5a94aecc79
[1417840.036932] R13: 00007f5a94aecc78 R14: 00007f5a94aecc90 R15: 00007f5a94aecc40
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-06-18 02:35:19 +08:00
|
|
|
* The actual lifetime of the extent_buffer in the radix tree is
|
|
|
|
* adequately protected by the refcount, but the TREE_REF bit and
|
|
|
|
* its corresponding reference are not. To protect against this
|
|
|
|
* class of races, we call check_buffer_tree_ref from the codepaths
|
|
|
|
* which trigger io after they set eb->io_pages. Note that once io is
|
|
|
|
* initiated, TREE_REF can no longer be cleared, so that is the
|
|
|
|
* moment at which any such race is best fixed.
|
2012-03-13 21:38:00 +08:00
|
|
|
*/
|
2013-01-30 06:49:37 +08:00
|
|
|
refs = atomic_read(&eb->refs);
|
|
|
|
if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
|
|
|
|
return;
|
|
|
|
|
2012-07-21 04:11:08 +08:00
|
|
|
spin_lock(&eb->refs_lock);
|
|
|
|
if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
|
2012-03-13 21:38:00 +08:00
|
|
|
atomic_inc(&eb->refs);
|
2012-07-21 04:11:08 +08:00
|
|
|
spin_unlock(&eb->refs_lock);
|
2012-03-13 21:38:00 +08:00
|
|
|
}
|
|
|
|
|
2014-06-05 07:10:31 +08:00
|
|
|
static void mark_extent_buffer_accessed(struct extent_buffer *eb,
|
|
|
|
struct page *accessed)
|
2012-03-16 06:24:42 +08:00
|
|
|
{
|
2018-03-02 01:20:27 +08:00
|
|
|
int num_pages, i;
|
2012-03-16 06:24:42 +08:00
|
|
|
|
2012-03-13 21:38:00 +08:00
|
|
|
check_buffer_tree_ref(eb);
|
|
|
|
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2012-03-16 06:24:42 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
struct page *p = eb->pages[i];
|
|
|
|
|
2014-06-05 07:10:31 +08:00
|
|
|
if (p != accessed)
|
|
|
|
mark_page_accessed(p);
|
2012-03-16 06:24:42 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-12-17 02:24:27 +08:00
|
|
|
struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
|
|
|
|
u64 start)
|
2013-10-07 23:45:25 +08:00
|
|
|
{
|
|
|
|
struct extent_buffer *eb;
|
|
|
|
|
2021-04-06 08:36:00 +08:00
|
|
|
eb = find_extent_buffer_nolock(fs_info, start);
|
|
|
|
if (!eb)
|
|
|
|
return NULL;
|
|
|
|
/*
|
|
|
|
* Lock our eb's refs_lock to avoid races with free_extent_buffer().
|
|
|
|
* When we get our eb it might be flagged with EXTENT_BUFFER_STALE and
|
|
|
|
* another task running free_extent_buffer() might have seen that flag
|
|
|
|
* set, eb->refs == 2, that the buffer isn't under IO (dirty and
|
|
|
|
* writeback flags not set) and it's still in the tree (flag
|
|
|
|
* EXTENT_BUFFER_TREE_REF set), therefore being in the process of
|
|
|
|
* decrementing the extent buffer's reference count twice. So here we
|
|
|
|
* could race and increment the eb's reference count, clear its stale
|
|
|
|
* flag, mark it as dirty and drop our reference before the other task
|
|
|
|
* finishes executing free_extent_buffer, which would later result in
|
|
|
|
* an attempt to free an extent buffer that is dirty.
|
|
|
|
*/
|
|
|
|
if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) {
|
|
|
|
spin_lock(&eb->refs_lock);
|
|
|
|
spin_unlock(&eb->refs_lock);
|
2013-10-07 23:45:25 +08:00
|
|
|
}
|
2021-04-06 08:36:00 +08:00
|
|
|
mark_extent_buffer_accessed(eb, NULL);
|
|
|
|
return eb;
|
2013-10-07 23:45:25 +08:00
|
|
|
}
|
|
|
|
|
2014-05-08 05:06:09 +08:00
|
|
|
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
|
|
|
|
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
|
2016-06-15 21:22:56 +08:00
|
|
|
u64 start)
|
2014-05-08 05:06:09 +08:00
|
|
|
{
|
|
|
|
struct extent_buffer *eb, *exists = NULL;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
eb = find_extent_buffer(fs_info, start);
|
|
|
|
if (eb)
|
|
|
|
return eb;
|
2016-06-15 21:22:56 +08:00
|
|
|
eb = alloc_dummy_extent_buffer(fs_info, start);
|
2014-05-08 05:06:09 +08:00
|
|
|
if (!eb)
|
2019-12-03 19:24:58 +08:00
|
|
|
return ERR_PTR(-ENOMEM);
|
2014-05-08 05:06:09 +08:00
|
|
|
eb->fs_info = fs_info;
|
2022-07-15 19:59:31 +08:00
|
|
|
again:
|
|
|
|
ret = radix_tree_preload(GFP_NOFS);
|
|
|
|
if (ret) {
|
|
|
|
exists = ERR_PTR(ret);
|
|
|
|
goto free_eb;
|
|
|
|
}
|
|
|
|
spin_lock(&fs_info->buffer_lock);
|
|
|
|
ret = radix_tree_insert(&fs_info->buffer_radix,
|
|
|
|
start >> fs_info->sectorsize_bits, eb);
|
|
|
|
spin_unlock(&fs_info->buffer_lock);
|
|
|
|
radix_tree_preload_end();
|
|
|
|
if (ret == -EEXIST) {
|
|
|
|
exists = find_extent_buffer(fs_info, start);
|
|
|
|
if (exists)
|
2014-05-08 05:06:09 +08:00
|
|
|
goto free_eb;
|
2022-07-15 19:59:31 +08:00
|
|
|
else
|
|
|
|
goto again;
|
|
|
|
}
|
2014-05-08 05:06:09 +08:00
|
|
|
check_buffer_tree_ref(eb);
|
|
|
|
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
|
|
|
|
|
|
|
|
return eb;
|
|
|
|
free_eb:
|
|
|
|
btrfs_release_extent_buffer(eb);
|
|
|
|
return exists;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2021-01-26 16:33:49 +08:00
|
|
|
static struct extent_buffer *grab_extent_buffer(
|
|
|
|
struct btrfs_fs_info *fs_info, struct page *page)
|
2021-01-06 09:01:45 +08:00
|
|
|
{
|
|
|
|
struct extent_buffer *exists;
|
|
|
|
|
2021-01-26 16:33:49 +08:00
|
|
|
/*
|
|
|
|
* For subpage case, we completely rely on radix tree to ensure we
|
|
|
|
* don't try to insert two ebs for the same bytenr. So here we always
|
|
|
|
* return NULL and just continue.
|
|
|
|
*/
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (fs_info->nodesize < PAGE_SIZE)
|
2021-01-26 16:33:49 +08:00
|
|
|
return NULL;
|
|
|
|
|
2021-01-06 09:01:45 +08:00
|
|
|
/* Page not yet attached to an extent buffer */
|
|
|
|
if (!PagePrivate(page))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We could have already allocated an eb for this page and attached one
|
|
|
|
* so lets see if we can get a ref on the existing eb, and if we can we
|
|
|
|
* know it's good and we can just return that one, else we know we can
|
|
|
|
* just overwrite page->private.
|
|
|
|
*/
|
|
|
|
exists = (struct extent_buffer *)page->private;
|
|
|
|
if (atomic_inc_not_zero(&exists->refs))
|
|
|
|
return exists;
|
|
|
|
|
|
|
|
WARN_ON(PageDirty(page));
|
|
|
|
detach_page_private(page);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start)
|
|
|
|
{
|
|
|
|
if (!IS_ALIGNED(start, fs_info->sectorsize)) {
|
|
|
|
btrfs_err(fs_info, "bad tree block start %llu", start);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (fs_info->nodesize < PAGE_SIZE &&
|
|
|
|
offset_in_page(start) + fs_info->nodesize > PAGE_SIZE) {
|
|
|
|
btrfs_err(fs_info,
|
|
|
|
"tree block crosses page boundary, start %llu nodesize %u",
|
|
|
|
start, fs_info->nodesize);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
if (fs_info->nodesize >= PAGE_SIZE &&
|
2022-05-26 22:35:40 +08:00
|
|
|
!PAGE_ALIGNED(start)) {
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
btrfs_err(fs_info,
|
|
|
|
"tree block is not page aligned, start %llu nodesize %u",
|
|
|
|
start, fs_info->nodesize);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-12-17 02:24:27 +08:00
|
|
|
struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
|
2020-11-05 23:45:20 +08:00
|
|
|
u64 start, u64 owner_root, int level)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2016-06-15 21:22:56 +08:00
|
|
|
unsigned long len = fs_info->nodesize;
|
2018-03-02 01:20:27 +08:00
|
|
|
int num_pages;
|
|
|
|
int i;
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
unsigned long index = start >> PAGE_SHIFT;
|
2008-01-25 05:13:08 +08:00
|
|
|
struct extent_buffer *eb;
|
2008-07-22 23:18:07 +08:00
|
|
|
struct extent_buffer *exists = NULL;
|
2008-01-25 05:13:08 +08:00
|
|
|
struct page *p;
|
2013-12-17 02:24:27 +08:00
|
|
|
struct address_space *mapping = fs_info->btree_inode->i_mapping;
|
btrfs: fix lockdep splat with reloc root extent buffers
We have been hitting the following lockdep splat with btrfs/187 recently
WARNING: possible circular locking dependency detected
5.19.0-rc8+ #775 Not tainted
------------------------------------------------------
btrfs/752500 is trying to acquire lock:
ffff97e1875a97b8 (btrfs-treloc-02#2){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
but task is already holding lock:
ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (btrfs-tree-01/1){+.+.}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_init_new_buffer+0x7d/0x2c0
btrfs_alloc_tree_block+0x120/0x3b0
__btrfs_cow_block+0x136/0x600
btrfs_cow_block+0x10b/0x230
btrfs_search_slot+0x53b/0xb70
btrfs_lookup_inode+0x2a/0xa0
__btrfs_update_delayed_inode+0x5f/0x280
btrfs_async_run_delayed_root+0x24c/0x290
btrfs_work_helper+0xf2/0x3e0
process_one_work+0x271/0x590
worker_thread+0x52/0x3b0
kthread+0xf0/0x120
ret_from_fork+0x1f/0x30
-> #1 (btrfs-tree-01){++++}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_search_slot+0x3c3/0xb70
do_relocation+0x10c/0x6b0
relocate_tree_blocks+0x317/0x6d0
relocate_block_group+0x1f1/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
-> #0 (btrfs-treloc-02#2){+.+.}-{3:3}:
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
other info that might help us debug this:
Chain exists of:
btrfs-treloc-02#2 --> btrfs-tree-01 --> btrfs-tree-01/1
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(btrfs-tree-01/1);
lock(btrfs-tree-01);
lock(btrfs-tree-01/1);
lock(btrfs-treloc-02#2);
*** DEADLOCK ***
7 locks held by btrfs/752500:
#0: ffff97e292fdf460 (sb_writers#12){.+.+}-{0:0}, at: btrfs_ioctl+0x208/0x2c90
#1: ffff97e284c02050 (&fs_info->reclaim_bgs_lock){+.+.}-{3:3}, at: btrfs_balance+0x55f/0xe40
#2: ffff97e284c00878 (&fs_info->cleaner_mutex){+.+.}-{3:3}, at: btrfs_relocate_block_group+0x236/0x400
#3: ffff97e292fdf650 (sb_internal#2){.+.+}-{0:0}, at: merge_reloc_root+0xef/0x610
#4: ffff97e284c02378 (btrfs_trans_num_writers){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#5: ffff97e284c023a0 (btrfs_trans_num_extwriters){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#6: ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
stack backtrace:
CPU: 1 PID: 752500 Comm: btrfs Not tainted 5.19.0-rc8+ #775
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
dump_stack_lvl+0x56/0x73
check_noncircular+0xd6/0x100
? lock_is_held_type+0xe2/0x140
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
? __btrfs_tree_lock+0x24/0x110
down_write_nested+0x41/0x80
? __btrfs_tree_lock+0x24/0x110
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
? lock_release+0x137/0x2d0
? _raw_spin_unlock+0x29/0x50
? release_extent_buffer+0x128/0x180
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
? lock_is_held_type+0xe2/0x140
? lock_is_held_type+0xe2/0x140
? __x64_sys_ioctl+0x88/0xc0
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
This isn't necessarily new, it's just tricky to hit in practice. There
are two competing things going on here. With relocation we create a
snapshot of every fs tree with a reloc tree. Any extent buffers that
get initialized here are initialized with the reloc root lockdep key.
However since it is a snapshot, any blocks that are currently in cache
that originally belonged to the fs tree will have the normal tree
lockdep key set. This creates the lock dependency of
reloc tree -> normal tree
for the extent buffer locking during the first phase of the relocation
as we walk down the reloc root to relocate blocks.
However this is problematic because the final phase of the relocation is
merging the reloc root into the original fs root. This involves
searching down to any keys that exist in the original fs root and then
swapping the relocated block and the original fs root block. We have to
search down to the fs root first, and then go search the reloc root for
the block we need to replace. This creates the dependency of
normal tree -> reloc tree
which is why lockdep complains.
Additionally even if we were to fix this particular mismatch with a
different nesting for the merge case, we're still slotting in a block
that has a owner of the reloc root objectid into a normal tree, so that
block will have its lockdep key set to the tree reloc root, and create a
lockdep splat later on when we wander into that block from the fs root.
Unfortunately the only solution here is to make sure we do not set the
lockdep key to the reloc tree lockdep key normally, and then reset any
blocks we wander into from the reloc root when we're doing the merged.
This solves the problem of having mixed tree reloc keys intermixed with
normal tree keys, and then allows us to make sure in the merge case we
maintain the lock order of
normal tree -> reloc tree
We handle this by setting a bit on the reloc root when we do the search
for the block we want to relocate, and any block we search into or COW
at that point gets set to the reloc tree key. This works correctly
because we only ever COW down to the parent node, so we aren't resetting
the key for the block we're linking into the fs root.
With this patch we no longer have the lockdep splat in btrfs/187.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-07-27 04:24:04 +08:00
|
|
|
u64 lockdep_owner = owner_root;
|
2008-01-25 05:13:08 +08:00
|
|
|
int uptodate = 1;
|
2010-10-27 08:57:29 +08:00
|
|
|
int ret;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (check_eb_alignment(fs_info, start))
|
2016-06-07 03:01:23 +08:00
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
2021-02-25 09:18:14 +08:00
|
|
|
#if BITS_PER_LONG == 32
|
|
|
|
if (start >= MAX_LFS_FILESIZE) {
|
|
|
|
btrfs_err_rl(fs_info,
|
|
|
|
"extent buffer %llu is beyond 32bit page cache limit", start);
|
|
|
|
btrfs_err_32bit_limit(fs_info);
|
|
|
|
return ERR_PTR(-EOVERFLOW);
|
|
|
|
}
|
|
|
|
if (start >= BTRFS_32BIT_EARLY_WARN_THRESHOLD)
|
|
|
|
btrfs_warn_32bit_limit(fs_info);
|
|
|
|
#endif
|
|
|
|
|
2013-12-17 02:24:27 +08:00
|
|
|
eb = find_extent_buffer(fs_info, start);
|
2013-10-07 23:45:25 +08:00
|
|
|
if (eb)
|
2008-07-22 23:18:07 +08:00
|
|
|
return eb;
|
|
|
|
|
2014-06-15 08:55:29 +08:00
|
|
|
eb = __alloc_extent_buffer(fs_info, start, len);
|
2008-04-01 23:21:40 +08:00
|
|
|
if (!eb)
|
2016-06-07 03:01:23 +08:00
|
|
|
return ERR_PTR(-ENOMEM);
|
btrfs: fix lockdep splat with reloc root extent buffers
We have been hitting the following lockdep splat with btrfs/187 recently
WARNING: possible circular locking dependency detected
5.19.0-rc8+ #775 Not tainted
------------------------------------------------------
btrfs/752500 is trying to acquire lock:
ffff97e1875a97b8 (btrfs-treloc-02#2){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
but task is already holding lock:
ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (btrfs-tree-01/1){+.+.}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_init_new_buffer+0x7d/0x2c0
btrfs_alloc_tree_block+0x120/0x3b0
__btrfs_cow_block+0x136/0x600
btrfs_cow_block+0x10b/0x230
btrfs_search_slot+0x53b/0xb70
btrfs_lookup_inode+0x2a/0xa0
__btrfs_update_delayed_inode+0x5f/0x280
btrfs_async_run_delayed_root+0x24c/0x290
btrfs_work_helper+0xf2/0x3e0
process_one_work+0x271/0x590
worker_thread+0x52/0x3b0
kthread+0xf0/0x120
ret_from_fork+0x1f/0x30
-> #1 (btrfs-tree-01){++++}-{3:3}:
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_search_slot+0x3c3/0xb70
do_relocation+0x10c/0x6b0
relocate_tree_blocks+0x317/0x6d0
relocate_block_group+0x1f1/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
-> #0 (btrfs-treloc-02#2){+.+.}-{3:3}:
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
down_write_nested+0x41/0x80
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
other info that might help us debug this:
Chain exists of:
btrfs-treloc-02#2 --> btrfs-tree-01 --> btrfs-tree-01/1
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(btrfs-tree-01/1);
lock(btrfs-tree-01);
lock(btrfs-tree-01/1);
lock(btrfs-treloc-02#2);
*** DEADLOCK ***
7 locks held by btrfs/752500:
#0: ffff97e292fdf460 (sb_writers#12){.+.+}-{0:0}, at: btrfs_ioctl+0x208/0x2c90
#1: ffff97e284c02050 (&fs_info->reclaim_bgs_lock){+.+.}-{3:3}, at: btrfs_balance+0x55f/0xe40
#2: ffff97e284c00878 (&fs_info->cleaner_mutex){+.+.}-{3:3}, at: btrfs_relocate_block_group+0x236/0x400
#3: ffff97e292fdf650 (sb_internal#2){.+.+}-{0:0}, at: merge_reloc_root+0xef/0x610
#4: ffff97e284c02378 (btrfs_trans_num_writers){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#5: ffff97e284c023a0 (btrfs_trans_num_extwriters){++++}-{0:0}, at: join_transaction+0x1a8/0x5a0
#6: ffff97e1875a9278 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x24/0x110
stack backtrace:
CPU: 1 PID: 752500 Comm: btrfs Not tainted 5.19.0-rc8+ #775
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
dump_stack_lvl+0x56/0x73
check_noncircular+0xd6/0x100
? lock_is_held_type+0xe2/0x140
__lock_acquire+0x1122/0x1e10
lock_acquire+0xc2/0x2d0
? __btrfs_tree_lock+0x24/0x110
down_write_nested+0x41/0x80
? __btrfs_tree_lock+0x24/0x110
__btrfs_tree_lock+0x24/0x110
btrfs_lock_root_node+0x31/0x50
btrfs_search_slot+0x1cb/0xb70
? lock_release+0x137/0x2d0
? _raw_spin_unlock+0x29/0x50
? release_extent_buffer+0x128/0x180
replace_path+0x541/0x9f0
merge_reloc_root+0x1d6/0x610
merge_reloc_roots+0xe2/0x260
relocate_block_group+0x2c8/0x560
btrfs_relocate_block_group+0x23e/0x400
btrfs_relocate_chunk+0x4c/0x140
btrfs_balance+0x755/0xe40
btrfs_ioctl+0x1ea2/0x2c90
? lock_is_held_type+0xe2/0x140
? lock_is_held_type+0xe2/0x140
? __x64_sys_ioctl+0x88/0xc0
__x64_sys_ioctl+0x88/0xc0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
This isn't necessarily new, it's just tricky to hit in practice. There
are two competing things going on here. With relocation we create a
snapshot of every fs tree with a reloc tree. Any extent buffers that
get initialized here are initialized with the reloc root lockdep key.
However since it is a snapshot, any blocks that are currently in cache
that originally belonged to the fs tree will have the normal tree
lockdep key set. This creates the lock dependency of
reloc tree -> normal tree
for the extent buffer locking during the first phase of the relocation
as we walk down the reloc root to relocate blocks.
However this is problematic because the final phase of the relocation is
merging the reloc root into the original fs root. This involves
searching down to any keys that exist in the original fs root and then
swapping the relocated block and the original fs root block. We have to
search down to the fs root first, and then go search the reloc root for
the block we need to replace. This creates the dependency of
normal tree -> reloc tree
which is why lockdep complains.
Additionally even if we were to fix this particular mismatch with a
different nesting for the merge case, we're still slotting in a block
that has a owner of the reloc root objectid into a normal tree, so that
block will have its lockdep key set to the tree reloc root, and create a
lockdep splat later on when we wander into that block from the fs root.
Unfortunately the only solution here is to make sure we do not set the
lockdep key to the reloc tree lockdep key normally, and then reset any
blocks we wander into from the reloc root when we're doing the merged.
This solves the problem of having mixed tree reloc keys intermixed with
normal tree keys, and then allows us to make sure in the merge case we
maintain the lock order of
normal tree -> reloc tree
We handle this by setting a bit on the reloc root when we do the search
for the block we want to relocate, and any block we search into or COW
at that point gets set to the reloc tree key. This works correctly
because we only ever COW down to the parent node, so we aren't resetting
the key for the block we're linking into the fs root.
With this patch we no longer have the lockdep splat in btrfs/187.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-07-27 04:24:04 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* The reloc trees are just snapshots, so we need them to appear to be
|
|
|
|
* just like any other fs tree WRT lockdep.
|
|
|
|
*/
|
|
|
|
if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID)
|
|
|
|
lockdep_owner = BTRFS_FS_TREE_OBJECTID;
|
|
|
|
|
|
|
|
btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2010-08-07 01:21:20 +08:00
|
|
|
for (i = 0; i < num_pages; i++, index++) {
|
2021-01-26 16:33:48 +08:00
|
|
|
struct btrfs_subpage *prealloc = NULL;
|
|
|
|
|
2015-08-19 20:17:40 +08:00
|
|
|
p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
|
2016-06-07 03:01:23 +08:00
|
|
|
if (!p) {
|
|
|
|
exists = ERR_PTR(-ENOMEM);
|
2008-07-22 23:18:07 +08:00
|
|
|
goto free_eb;
|
2016-06-07 03:01:23 +08:00
|
|
|
}
|
2012-03-08 05:20:05 +08:00
|
|
|
|
2021-01-26 16:33:48 +08:00
|
|
|
/*
|
|
|
|
* Preallocate page->private for subpage case, so that we won't
|
|
|
|
* allocate memory with private_lock hold. The memory will be
|
|
|
|
* freed by attach_extent_buffer_page() or freed manually if
|
|
|
|
* we exit earlier.
|
|
|
|
*
|
|
|
|
* Although we have ensured one subpage eb can only have one
|
|
|
|
* page, but it may change in the future for 16K page size
|
|
|
|
* support, so we still preallocate the memory in the loop.
|
|
|
|
*/
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (fs_info->nodesize < PAGE_SIZE) {
|
2021-08-17 17:38:50 +08:00
|
|
|
prealloc = btrfs_alloc_subpage(fs_info, BTRFS_SUBPAGE_METADATA);
|
|
|
|
if (IS_ERR(prealloc)) {
|
|
|
|
ret = PTR_ERR(prealloc);
|
2021-08-17 17:38:49 +08:00
|
|
|
unlock_page(p);
|
|
|
|
put_page(p);
|
|
|
|
exists = ERR_PTR(ret);
|
|
|
|
goto free_eb;
|
|
|
|
}
|
2021-01-26 16:33:48 +08:00
|
|
|
}
|
|
|
|
|
2012-03-08 05:20:05 +08:00
|
|
|
spin_lock(&mapping->private_lock);
|
2021-01-26 16:33:49 +08:00
|
|
|
exists = grab_extent_buffer(fs_info, p);
|
2021-01-06 09:01:45 +08:00
|
|
|
if (exists) {
|
|
|
|
spin_unlock(&mapping->private_lock);
|
|
|
|
unlock_page(p);
|
|
|
|
put_page(p);
|
|
|
|
mark_extent_buffer_accessed(exists, p);
|
2021-01-26 16:33:48 +08:00
|
|
|
btrfs_free_subpage(prealloc);
|
2021-01-06 09:01:45 +08:00
|
|
|
goto free_eb;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
2021-01-26 16:33:48 +08:00
|
|
|
/* Should not fail, as we have preallocated the memory */
|
|
|
|
ret = attach_extent_buffer_page(eb, p, prealloc);
|
|
|
|
ASSERT(!ret);
|
btrfs: support subpage for extent buffer page release
In btrfs_release_extent_buffer_pages(), we need to add extra handling
for subpage.
Introduce a helper, detach_extent_buffer_page(), to do different
handling for regular and subpage cases.
For subpage case, handle detaching page private.
For unmapped (dummy or cloned) ebs, we can detach the page private
immediately as the page can only be attached to one unmapped eb.
For mapped ebs, we have to ensure there are no eb in the page range
before we delete it, as page->private is shared between all ebs in the
same page.
But there is a subpage specific race, where we can race with extent
buffer allocation, and clear the page private while new eb is still
being utilized, like this:
Extent buffer A is the new extent buffer which will be allocated,
while extent buffer B is the last existing extent buffer of the page.
T1 (eb A) | T2 (eb B)
-------------------------------+------------------------------
alloc_extent_buffer() | btrfs_release_extent_buffer_pages()
|- p = find_or_create_page() | |
|- attach_extent_buffer_page() | |
| | |- detach_extent_buffer_page()
| | |- if (!page_range_has_eb())
| | | No new eb in the page range yet
| | | As new eb A hasn't yet been
| | | inserted into radix tree.
| | |- btrfs_detach_subpage()
| | |- detach_page_private();
|- radix_tree_insert() |
Then we have a metadata eb whose page has no private bit.
To avoid such race, we introduce a subpage metadata-specific member,
btrfs_subpage::eb_refs.
In alloc_extent_buffer() we increase eb_refs in the critical section of
private_lock. Then page_range_has_eb() will return true for
detach_extent_buffer_page(), and will not detach page private.
The section is marked by:
- btrfs_page_inc_eb_refs()
- btrfs_page_dec_eb_refs()
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-26 16:33:50 +08:00
|
|
|
/*
|
|
|
|
* To inform we have extra eb under allocation, so that
|
|
|
|
* detach_extent_buffer_page() won't release the page private
|
|
|
|
* when the eb hasn't yet been inserted into radix tree.
|
|
|
|
*
|
|
|
|
* The ref will be decreased when the eb released the page, in
|
|
|
|
* detach_extent_buffer_page().
|
|
|
|
* Thus needs no special handling in error path.
|
|
|
|
*/
|
|
|
|
btrfs_page_inc_eb_refs(fs_info, p);
|
2012-03-08 05:20:05 +08:00
|
|
|
spin_unlock(&mapping->private_lock);
|
2021-01-26 16:33:48 +08:00
|
|
|
|
2021-03-25 15:14:41 +08:00
|
|
|
WARN_ON(btrfs_page_test_dirty(fs_info, p, eb->start, eb->len));
|
2010-08-07 01:21:20 +08:00
|
|
|
eb->pages[i] = p;
|
2008-01-25 05:13:08 +08:00
|
|
|
if (!PageUptodate(p))
|
|
|
|
uptodate = 0;
|
2011-02-11 01:35:00 +08:00
|
|
|
|
|
|
|
/*
|
2018-07-04 15:24:52 +08:00
|
|
|
* We can't unlock the pages just yet since the extent buffer
|
|
|
|
* hasn't been properly inserted in the radix tree, this
|
2022-05-01 11:15:16 +08:00
|
|
|
* opens a race with btree_release_folio which can free a page
|
2018-07-04 15:24:52 +08:00
|
|
|
* while we are still filling in all pages for the buffer and
|
|
|
|
* we could crash.
|
2011-02-11 01:35:00 +08:00
|
|
|
*/
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
if (uptodate)
|
Btrfs: Change btree locking to use explicit blocking points
Most of the btrfs metadata operations can be protected by a spinlock,
but some operations still need to schedule.
So far, btrfs has been using a mutex along with a trylock loop,
most of the time it is able to avoid going for the full mutex, so
the trylock loop is a big performance gain.
This commit is step one for getting rid of the blocking locks entirely.
btrfs_tree_lock takes a spinlock, and the code explicitly switches
to a blocking lock when it starts an operation that can schedule.
We'll be able get rid of the blocking locks in smaller pieces over time.
Tracing allows us to find the most common cause of blocking, so we
can start with the hot spots first.
The basic idea is:
btrfs_tree_lock() returns with the spin lock held
btrfs_set_lock_blocking() sets the EXTENT_BUFFER_BLOCKING bit in
the extent buffer flags, and then drops the spin lock. The buffer is
still considered locked by all of the btrfs code.
If btrfs_tree_lock gets the spinlock but finds the blocking bit set, it drops
the spin lock and waits on a wait queue for the blocking bit to go away.
Much of the code that needs to set the blocking bit finishes without actually
blocking a good percentage of the time. So, an adaptive spin is still
used against the blocking bit to avoid very high context switch rates.
btrfs_clear_lock_blocking() clears the blocking bit and returns
with the spinlock held again.
btrfs_tree_unlock() can be called on either blocking or spinning locks,
it does the right thing based on the blocking bit.
ctree.c has a helper function to set/clear all the locked buffers in a
path as blocking.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-02-04 22:25:08 +08:00
|
|
|
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
|
2022-07-15 19:59:31 +08:00
|
|
|
again:
|
|
|
|
ret = radix_tree_preload(GFP_NOFS);
|
|
|
|
if (ret) {
|
|
|
|
exists = ERR_PTR(ret);
|
|
|
|
goto free_eb;
|
|
|
|
}
|
|
|
|
|
|
|
|
spin_lock(&fs_info->buffer_lock);
|
|
|
|
ret = radix_tree_insert(&fs_info->buffer_radix,
|
|
|
|
start >> fs_info->sectorsize_bits, eb);
|
|
|
|
spin_unlock(&fs_info->buffer_lock);
|
|
|
|
radix_tree_preload_end();
|
|
|
|
if (ret == -EEXIST) {
|
|
|
|
exists = find_extent_buffer(fs_info, start);
|
|
|
|
if (exists)
|
2013-10-07 23:45:25 +08:00
|
|
|
goto free_eb;
|
2022-07-15 19:59:31 +08:00
|
|
|
else
|
|
|
|
goto again;
|
|
|
|
}
|
2008-07-22 23:18:07 +08:00
|
|
|
/* add one reference for the tree */
|
2012-03-13 21:38:00 +08:00
|
|
|
check_buffer_tree_ref(eb);
|
2013-12-13 23:41:51 +08:00
|
|
|
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
|
2011-02-11 01:35:00 +08:00
|
|
|
|
|
|
|
/*
|
2018-07-04 15:24:52 +08:00
|
|
|
* Now it's safe to unlock the pages because any calls to
|
2022-05-01 11:15:16 +08:00
|
|
|
* btree_release_folio will correctly detect that a page belongs to a
|
2018-07-04 15:24:52 +08:00
|
|
|
* live buffer and won't free them prematurely.
|
2011-02-11 01:35:00 +08:00
|
|
|
*/
|
2018-07-04 15:24:51 +08:00
|
|
|
for (i = 0; i < num_pages; i++)
|
|
|
|
unlock_page(eb->pages[i]);
|
2008-01-25 05:13:08 +08:00
|
|
|
return eb;
|
|
|
|
|
2008-07-22 23:18:07 +08:00
|
|
|
free_eb:
|
2015-02-24 18:47:05 +08:00
|
|
|
WARN_ON(!atomic_dec_and_test(&eb->refs));
|
2010-08-07 01:21:20 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
|
|
|
if (eb->pages[i])
|
|
|
|
unlock_page(eb->pages[i]);
|
|
|
|
}
|
2011-02-11 01:35:00 +08:00
|
|
|
|
2010-10-27 08:57:29 +08:00
|
|
|
btrfs_release_extent_buffer(eb);
|
2008-07-22 23:18:07 +08:00
|
|
|
return exists;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2012-03-10 05:01:49 +08:00
|
|
|
static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
|
|
|
|
{
|
|
|
|
struct extent_buffer *eb =
|
|
|
|
container_of(head, struct extent_buffer, rcu_head);
|
|
|
|
|
|
|
|
__free_extent_buffer(eb);
|
|
|
|
}
|
|
|
|
|
2013-04-26 22:56:29 +08:00
|
|
|
static int release_extent_buffer(struct extent_buffer *eb)
|
2020-02-24 07:16:42 +08:00
|
|
|
__releases(&eb->refs_lock)
|
2012-03-10 05:01:49 +08:00
|
|
|
{
|
2018-06-27 21:38:23 +08:00
|
|
|
lockdep_assert_held(&eb->refs_lock);
|
|
|
|
|
2012-03-10 05:01:49 +08:00
|
|
|
WARN_ON(atomic_read(&eb->refs) == 0);
|
|
|
|
if (atomic_dec_and_test(&eb->refs)) {
|
2013-12-13 23:41:51 +08:00
|
|
|
if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
|
2013-12-17 02:24:27 +08:00
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
2012-03-10 05:01:49 +08:00
|
|
|
|
2012-05-16 23:00:02 +08:00
|
|
|
spin_unlock(&eb->refs_lock);
|
2012-03-10 05:01:49 +08:00
|
|
|
|
2022-07-15 19:59:31 +08:00
|
|
|
spin_lock(&fs_info->buffer_lock);
|
|
|
|
radix_tree_delete(&fs_info->buffer_radix,
|
|
|
|
eb->start >> fs_info->sectorsize_bits);
|
|
|
|
spin_unlock(&fs_info->buffer_lock);
|
2013-12-13 23:41:51 +08:00
|
|
|
} else {
|
|
|
|
spin_unlock(&eb->refs_lock);
|
2012-05-16 23:00:02 +08:00
|
|
|
}
|
2012-03-10 05:01:49 +08:00
|
|
|
|
2022-09-10 05:53:19 +08:00
|
|
|
btrfs_leak_debug_del_eb(eb);
|
2012-03-10 05:01:49 +08:00
|
|
|
/* Should be safe to release our pages at this point */
|
2018-07-19 23:24:32 +08:00
|
|
|
btrfs_release_extent_buffer_pages(eb);
|
2015-03-17 05:38:02 +08:00
|
|
|
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
|
2018-06-27 21:38:24 +08:00
|
|
|
if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))) {
|
2015-03-17 05:38:02 +08:00
|
|
|
__free_extent_buffer(eb);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
#endif
|
2012-03-10 05:01:49 +08:00
|
|
|
call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
|
2012-07-21 04:05:36 +08:00
|
|
|
return 1;
|
2012-03-10 05:01:49 +08:00
|
|
|
}
|
|
|
|
spin_unlock(&eb->refs_lock);
|
2012-07-21 04:05:36 +08:00
|
|
|
|
|
|
|
return 0;
|
2012-03-10 05:01:49 +08:00
|
|
|
}
|
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
void free_extent_buffer(struct extent_buffer *eb)
|
|
|
|
{
|
2013-01-30 06:49:37 +08:00
|
|
|
int refs;
|
2008-01-25 05:13:08 +08:00
|
|
|
if (!eb)
|
|
|
|
return;
|
|
|
|
|
2022-08-10 00:36:33 +08:00
|
|
|
refs = atomic_read(&eb->refs);
|
2013-01-30 06:49:37 +08:00
|
|
|
while (1) {
|
2018-10-15 22:04:01 +08:00
|
|
|
if ((!test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags) && refs <= 3)
|
|
|
|
|| (test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags) &&
|
|
|
|
refs == 1))
|
2013-01-30 06:49:37 +08:00
|
|
|
break;
|
2022-08-10 00:36:33 +08:00
|
|
|
if (atomic_try_cmpxchg(&eb->refs, &refs, refs - 1))
|
2013-01-30 06:49:37 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2012-03-10 05:01:49 +08:00
|
|
|
spin_lock(&eb->refs_lock);
|
|
|
|
if (atomic_read(&eb->refs) == 2 &&
|
|
|
|
test_bit(EXTENT_BUFFER_STALE, &eb->bflags) &&
|
2012-03-13 21:38:00 +08:00
|
|
|
!extent_buffer_under_io(eb) &&
|
2012-03-10 05:01:49 +08:00
|
|
|
test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
|
|
|
|
atomic_dec(&eb->refs);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* I know this is terrible, but it's temporary until we stop tracking
|
|
|
|
* the uptodate bits and such for the extent buffers.
|
|
|
|
*/
|
2013-04-26 22:56:29 +08:00
|
|
|
release_extent_buffer(eb);
|
2012-03-10 05:01:49 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void free_extent_buffer_stale(struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
if (!eb)
|
2008-01-25 05:13:08 +08:00
|
|
|
return;
|
|
|
|
|
2012-03-10 05:01:49 +08:00
|
|
|
spin_lock(&eb->refs_lock);
|
|
|
|
set_bit(EXTENT_BUFFER_STALE, &eb->bflags);
|
|
|
|
|
2012-03-13 21:38:00 +08:00
|
|
|
if (atomic_read(&eb->refs) == 2 && !extent_buffer_under_io(eb) &&
|
2012-03-10 05:01:49 +08:00
|
|
|
test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
|
|
|
|
atomic_dec(&eb->refs);
|
2013-04-26 22:56:29 +08:00
|
|
|
release_extent_buffer(eb);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
btrfs: make set/clear_extent_buffer_dirty() subpage compatible
For set_extent_buffer_dirty() to support subpage sized metadata, just
call btrfs_page_set_dirty() to handle both cases.
For clear_extent_buffer_dirty(), it needs to clear the page dirty if and
only if all extent buffers in the page range are no longer dirty.
Also do the same for page error.
This is pretty different from the existing clear_extent_buffer_dirty()
routine, so add a new helper function,
clear_subpage_extent_buffer_dirty() to do this for subpage metadata.
Also since the main part of clearing page dirty code is still the same,
extract that into btree_clear_page_dirty() so that it can be utilized
for both cases.
But there is a special race between set_extent_buffer_dirty() and
clear_extent_buffer_dirty(), where we can clear the page dirty.
[POSSIBLE RACE WINDOW]
For the race window between clear_subpage_extent_buffer_dirty() and
set_extent_buffer_dirty(), due to the fact that we can't call
clear_page_dirty_for_io() under subpage spin lock, we can race like
below:
T1 (eb1 in the same page) | T2 (eb2 in the same page)
-------------------------------+------------------------------
set_extent_buffer_dirty() | clear_extent_buffer_dirty()
|- was_dirty = false; | |- clear_subpagE_extent_buffer_dirty()
| | |- btrfs_clear_and_test_dirty()
| | | Since eb2 is the last dirty page
| | | we got:
| | | last == true;
| | |
|- btrfs_page_set_dirty() | |
| We set the page dirty and | |
| subpage dirty bitmap | |
| | |- if (last)
| | | Since we don't have subpage lock
| | | held, now @last is no longer
| | | correct
| | |- btree_clear_page_dirty()
| | Now PageDirty == false, even if
| | we have dirty_bitmap not zero.
|- ASSERT(PageDirty()); |
^^^^ CRASH
The solution here is to also lock the eb->pages[0] for subpage case of
set_extent_buffer_dirty(), to prevent racing with
clear_extent_buffer_dirty().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-25 15:14:43 +08:00
|
|
|
static void btree_clear_page_dirty(struct page *page)
|
|
|
|
{
|
|
|
|
ASSERT(PageDirty(page));
|
|
|
|
ASSERT(PageLocked(page));
|
|
|
|
clear_page_dirty_for_io(page);
|
|
|
|
xa_lock_irq(&page->mapping->i_pages);
|
|
|
|
if (!PageDirty(page))
|
|
|
|
__xa_clear_mark(&page->mapping->i_pages,
|
|
|
|
page_index(page), PAGECACHE_TAG_DIRTY);
|
|
|
|
xa_unlock_irq(&page->mapping->i_pages);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void clear_subpage_extent_buffer_dirty(const struct extent_buffer *eb)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
|
|
|
struct page *page = eb->pages[0];
|
|
|
|
bool last;
|
|
|
|
|
|
|
|
/* btree_clear_page_dirty() needs page locked */
|
|
|
|
lock_page(page);
|
|
|
|
last = btrfs_subpage_clear_and_test_dirty(fs_info, page, eb->start,
|
|
|
|
eb->len);
|
|
|
|
if (last)
|
|
|
|
btree_clear_page_dirty(page);
|
|
|
|
unlock_page(page);
|
|
|
|
WARN_ON(atomic_read(&eb->refs) == 0);
|
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void clear_extent_buffer_dirty(const struct extent_buffer *eb)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2018-03-02 01:20:27 +08:00
|
|
|
int i;
|
|
|
|
int num_pages;
|
2008-01-25 05:13:08 +08:00
|
|
|
struct page *page;
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (eb->fs_info->nodesize < PAGE_SIZE)
|
btrfs: make set/clear_extent_buffer_dirty() subpage compatible
For set_extent_buffer_dirty() to support subpage sized metadata, just
call btrfs_page_set_dirty() to handle both cases.
For clear_extent_buffer_dirty(), it needs to clear the page dirty if and
only if all extent buffers in the page range are no longer dirty.
Also do the same for page error.
This is pretty different from the existing clear_extent_buffer_dirty()
routine, so add a new helper function,
clear_subpage_extent_buffer_dirty() to do this for subpage metadata.
Also since the main part of clearing page dirty code is still the same,
extract that into btree_clear_page_dirty() so that it can be utilized
for both cases.
But there is a special race between set_extent_buffer_dirty() and
clear_extent_buffer_dirty(), where we can clear the page dirty.
[POSSIBLE RACE WINDOW]
For the race window between clear_subpage_extent_buffer_dirty() and
set_extent_buffer_dirty(), due to the fact that we can't call
clear_page_dirty_for_io() under subpage spin lock, we can race like
below:
T1 (eb1 in the same page) | T2 (eb2 in the same page)
-------------------------------+------------------------------
set_extent_buffer_dirty() | clear_extent_buffer_dirty()
|- was_dirty = false; | |- clear_subpagE_extent_buffer_dirty()
| | |- btrfs_clear_and_test_dirty()
| | | Since eb2 is the last dirty page
| | | we got:
| | | last == true;
| | |
|- btrfs_page_set_dirty() | |
| We set the page dirty and | |
| subpage dirty bitmap | |
| | |- if (last)
| | | Since we don't have subpage lock
| | | held, now @last is no longer
| | | correct
| | |- btree_clear_page_dirty()
| | Now PageDirty == false, even if
| | we have dirty_bitmap not zero.
|- ASSERT(PageDirty()); |
^^^^ CRASH
The solution here is to also lock the eb->pages[0] for subpage case of
set_extent_buffer_dirty(), to prevent racing with
clear_extent_buffer_dirty().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-25 15:14:43 +08:00
|
|
|
return clear_subpage_extent_buffer_dirty(eb);
|
|
|
|
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2009-03-13 23:00:37 +08:00
|
|
|
if (!PageDirty(page))
|
2008-11-20 01:44:22 +08:00
|
|
|
continue;
|
2008-07-22 23:18:08 +08:00
|
|
|
lock_page(page);
|
btrfs: make set/clear_extent_buffer_dirty() subpage compatible
For set_extent_buffer_dirty() to support subpage sized metadata, just
call btrfs_page_set_dirty() to handle both cases.
For clear_extent_buffer_dirty(), it needs to clear the page dirty if and
only if all extent buffers in the page range are no longer dirty.
Also do the same for page error.
This is pretty different from the existing clear_extent_buffer_dirty()
routine, so add a new helper function,
clear_subpage_extent_buffer_dirty() to do this for subpage metadata.
Also since the main part of clearing page dirty code is still the same,
extract that into btree_clear_page_dirty() so that it can be utilized
for both cases.
But there is a special race between set_extent_buffer_dirty() and
clear_extent_buffer_dirty(), where we can clear the page dirty.
[POSSIBLE RACE WINDOW]
For the race window between clear_subpage_extent_buffer_dirty() and
set_extent_buffer_dirty(), due to the fact that we can't call
clear_page_dirty_for_io() under subpage spin lock, we can race like
below:
T1 (eb1 in the same page) | T2 (eb2 in the same page)
-------------------------------+------------------------------
set_extent_buffer_dirty() | clear_extent_buffer_dirty()
|- was_dirty = false; | |- clear_subpagE_extent_buffer_dirty()
| | |- btrfs_clear_and_test_dirty()
| | | Since eb2 is the last dirty page
| | | we got:
| | | last == true;
| | |
|- btrfs_page_set_dirty() | |
| We set the page dirty and | |
| subpage dirty bitmap | |
| | |- if (last)
| | | Since we don't have subpage lock
| | | held, now @last is no longer
| | | correct
| | |- btree_clear_page_dirty()
| | Now PageDirty == false, even if
| | we have dirty_bitmap not zero.
|- ASSERT(PageDirty()); |
^^^^ CRASH
The solution here is to also lock the eb->pages[0] for subpage case of
set_extent_buffer_dirty(), to prevent racing with
clear_extent_buffer_dirty().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-25 15:14:43 +08:00
|
|
|
btree_clear_page_dirty(page);
|
2011-11-05 00:29:37 +08:00
|
|
|
ClearPageError(page);
|
2008-07-22 23:18:08 +08:00
|
|
|
unlock_page(page);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
2012-03-13 21:38:00 +08:00
|
|
|
WARN_ON(atomic_read(&eb->refs) == 0);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2018-09-14 01:44:42 +08:00
|
|
|
bool set_extent_buffer_dirty(struct extent_buffer *eb)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2018-03-02 01:20:27 +08:00
|
|
|
int i;
|
|
|
|
int num_pages;
|
2018-09-14 01:44:42 +08:00
|
|
|
bool was_dirty;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2012-03-13 21:38:00 +08:00
|
|
|
check_buffer_tree_ref(eb);
|
|
|
|
|
2009-03-13 23:00:37 +08:00
|
|
|
was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
|
2012-03-13 21:38:00 +08:00
|
|
|
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2012-03-10 05:01:49 +08:00
|
|
|
WARN_ON(atomic_read(&eb->refs) == 0);
|
2012-03-13 21:38:00 +08:00
|
|
|
WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
|
|
|
|
|
btrfs: make set/clear_extent_buffer_dirty() subpage compatible
For set_extent_buffer_dirty() to support subpage sized metadata, just
call btrfs_page_set_dirty() to handle both cases.
For clear_extent_buffer_dirty(), it needs to clear the page dirty if and
only if all extent buffers in the page range are no longer dirty.
Also do the same for page error.
This is pretty different from the existing clear_extent_buffer_dirty()
routine, so add a new helper function,
clear_subpage_extent_buffer_dirty() to do this for subpage metadata.
Also since the main part of clearing page dirty code is still the same,
extract that into btree_clear_page_dirty() so that it can be utilized
for both cases.
But there is a special race between set_extent_buffer_dirty() and
clear_extent_buffer_dirty(), where we can clear the page dirty.
[POSSIBLE RACE WINDOW]
For the race window between clear_subpage_extent_buffer_dirty() and
set_extent_buffer_dirty(), due to the fact that we can't call
clear_page_dirty_for_io() under subpage spin lock, we can race like
below:
T1 (eb1 in the same page) | T2 (eb2 in the same page)
-------------------------------+------------------------------
set_extent_buffer_dirty() | clear_extent_buffer_dirty()
|- was_dirty = false; | |- clear_subpagE_extent_buffer_dirty()
| | |- btrfs_clear_and_test_dirty()
| | | Since eb2 is the last dirty page
| | | we got:
| | | last == true;
| | |
|- btrfs_page_set_dirty() | |
| We set the page dirty and | |
| subpage dirty bitmap | |
| | |- if (last)
| | | Since we don't have subpage lock
| | | held, now @last is no longer
| | | correct
| | |- btree_clear_page_dirty()
| | Now PageDirty == false, even if
| | we have dirty_bitmap not zero.
|- ASSERT(PageDirty()); |
^^^^ CRASH
The solution here is to also lock the eb->pages[0] for subpage case of
set_extent_buffer_dirty(), to prevent racing with
clear_extent_buffer_dirty().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-25 15:14:43 +08:00
|
|
|
if (!was_dirty) {
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
bool subpage = eb->fs_info->nodesize < PAGE_SIZE;
|
2018-09-14 01:46:08 +08:00
|
|
|
|
btrfs: make set/clear_extent_buffer_dirty() subpage compatible
For set_extent_buffer_dirty() to support subpage sized metadata, just
call btrfs_page_set_dirty() to handle both cases.
For clear_extent_buffer_dirty(), it needs to clear the page dirty if and
only if all extent buffers in the page range are no longer dirty.
Also do the same for page error.
This is pretty different from the existing clear_extent_buffer_dirty()
routine, so add a new helper function,
clear_subpage_extent_buffer_dirty() to do this for subpage metadata.
Also since the main part of clearing page dirty code is still the same,
extract that into btree_clear_page_dirty() so that it can be utilized
for both cases.
But there is a special race between set_extent_buffer_dirty() and
clear_extent_buffer_dirty(), where we can clear the page dirty.
[POSSIBLE RACE WINDOW]
For the race window between clear_subpage_extent_buffer_dirty() and
set_extent_buffer_dirty(), due to the fact that we can't call
clear_page_dirty_for_io() under subpage spin lock, we can race like
below:
T1 (eb1 in the same page) | T2 (eb2 in the same page)
-------------------------------+------------------------------
set_extent_buffer_dirty() | clear_extent_buffer_dirty()
|- was_dirty = false; | |- clear_subpagE_extent_buffer_dirty()
| | |- btrfs_clear_and_test_dirty()
| | | Since eb2 is the last dirty page
| | | we got:
| | | last == true;
| | |
|- btrfs_page_set_dirty() | |
| We set the page dirty and | |
| subpage dirty bitmap | |
| | |- if (last)
| | | Since we don't have subpage lock
| | | held, now @last is no longer
| | | correct
| | |- btree_clear_page_dirty()
| | Now PageDirty == false, even if
| | we have dirty_bitmap not zero.
|- ASSERT(PageDirty()); |
^^^^ CRASH
The solution here is to also lock the eb->pages[0] for subpage case of
set_extent_buffer_dirty(), to prevent racing with
clear_extent_buffer_dirty().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-03-25 15:14:43 +08:00
|
|
|
/*
|
|
|
|
* For subpage case, we can have other extent buffers in the
|
|
|
|
* same page, and in clear_subpage_extent_buffer_dirty() we
|
|
|
|
* have to clear page dirty without subpage lock held.
|
|
|
|
* This can cause race where our page gets dirty cleared after
|
|
|
|
* we just set it.
|
|
|
|
*
|
|
|
|
* Thankfully, clear_subpage_extent_buffer_dirty() has locked
|
|
|
|
* its page for other reasons, we can use page lock to prevent
|
|
|
|
* the above race.
|
|
|
|
*/
|
|
|
|
if (subpage)
|
|
|
|
lock_page(eb->pages[0]);
|
|
|
|
for (i = 0; i < num_pages; i++)
|
|
|
|
btrfs_page_set_dirty(eb->fs_info, eb->pages[i],
|
|
|
|
eb->start, eb->len);
|
|
|
|
if (subpage)
|
|
|
|
unlock_page(eb->pages[0]);
|
|
|
|
}
|
2018-09-14 01:46:08 +08:00
|
|
|
#ifdef CONFIG_BTRFS_DEBUG
|
|
|
|
for (i = 0; i < num_pages; i++)
|
|
|
|
ASSERT(PageDirty(eb->pages[i]));
|
|
|
|
#endif
|
|
|
|
|
2009-03-13 23:00:37 +08:00
|
|
|
return was_dirty;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2015-12-03 20:08:59 +08:00
|
|
|
void clear_extent_buffer_uptodate(struct extent_buffer *eb)
|
2008-05-13 01:39:03 +08:00
|
|
|
{
|
2021-01-26 16:33:54 +08:00
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
2008-05-13 01:39:03 +08:00
|
|
|
struct page *page;
|
2018-03-02 01:20:27 +08:00
|
|
|
int num_pages;
|
2021-01-26 16:33:54 +08:00
|
|
|
int i;
|
2008-05-13 01:39:03 +08:00
|
|
|
|
Btrfs: Change btree locking to use explicit blocking points
Most of the btrfs metadata operations can be protected by a spinlock,
but some operations still need to schedule.
So far, btrfs has been using a mutex along with a trylock loop,
most of the time it is able to avoid going for the full mutex, so
the trylock loop is a big performance gain.
This commit is step one for getting rid of the blocking locks entirely.
btrfs_tree_lock takes a spinlock, and the code explicitly switches
to a blocking lock when it starts an operation that can schedule.
We'll be able get rid of the blocking locks in smaller pieces over time.
Tracing allows us to find the most common cause of blocking, so we
can start with the hot spots first.
The basic idea is:
btrfs_tree_lock() returns with the spin lock held
btrfs_set_lock_blocking() sets the EXTENT_BUFFER_BLOCKING bit in
the extent buffer flags, and then drops the spin lock. The buffer is
still considered locked by all of the btrfs code.
If btrfs_tree_lock gets the spinlock but finds the blocking bit set, it drops
the spin lock and waits on a wait queue for the blocking bit to go away.
Much of the code that needs to set the blocking bit finishes without actually
blocking a good percentage of the time. So, an adaptive spin is still
used against the blocking bit to avoid very high context switch rates.
btrfs_clear_lock_blocking() clears the blocking bit and returns
with the spinlock held again.
btrfs_tree_unlock() can be called on either blocking or spinning locks,
it does the right thing based on the blocking bit.
ctree.c has a helper function to set/clear all the locked buffers in a
path as blocking.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-02-04 22:25:08 +08:00
|
|
|
clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2008-05-13 01:39:03 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (!page)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is special handling for metadata subpage, as regular
|
|
|
|
* btrfs_is_subpage() can not handle cloned/dummy metadata.
|
|
|
|
*/
|
|
|
|
if (fs_info->nodesize >= PAGE_SIZE)
|
|
|
|
ClearPageUptodate(page);
|
|
|
|
else
|
|
|
|
btrfs_subpage_clear_uptodate(fs_info, page, eb->start,
|
|
|
|
eb->len);
|
2008-05-13 01:39:03 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-12-03 20:08:59 +08:00
|
|
|
void set_extent_buffer_uptodate(struct extent_buffer *eb)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2021-01-26 16:33:54 +08:00
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
2008-01-25 05:13:08 +08:00
|
|
|
struct page *page;
|
2018-03-02 01:20:27 +08:00
|
|
|
int num_pages;
|
2021-01-26 16:33:54 +08:00
|
|
|
int i;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2012-03-13 21:38:00 +08:00
|
|
|
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2008-01-25 05:13:08 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* This is special handling for metadata subpage, as regular
|
|
|
|
* btrfs_is_subpage() can not handle cloned/dummy metadata.
|
|
|
|
*/
|
|
|
|
if (fs_info->nodesize >= PAGE_SIZE)
|
|
|
|
SetPageUptodate(page);
|
|
|
|
else
|
|
|
|
btrfs_subpage_set_uptodate(fs_info, page, eb->start,
|
|
|
|
eb->len);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-01-26 16:33:57 +08:00
|
|
|
static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait,
|
btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-14 13:32:51 +08:00
|
|
|
int mirror_num,
|
|
|
|
struct btrfs_tree_parent_check *check)
|
2021-01-26 16:33:57 +08:00
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
|
|
|
struct extent_io_tree *io_tree;
|
|
|
|
struct page *page = eb->pages[0];
|
2022-10-01 04:45:13 +08:00
|
|
|
struct extent_state *cached_state = NULL;
|
2022-06-03 15:11:03 +08:00
|
|
|
struct btrfs_bio_ctrl bio_ctrl = {
|
|
|
|
.mirror_num = mirror_num,
|
|
|
|
};
|
2021-01-26 16:33:57 +08:00
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
ASSERT(!test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags));
|
|
|
|
ASSERT(PagePrivate(page));
|
btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-14 13:32:51 +08:00
|
|
|
ASSERT(check);
|
2021-01-26 16:33:57 +08:00
|
|
|
io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
|
|
|
|
|
|
|
|
if (wait == WAIT_NONE) {
|
2022-10-01 04:45:09 +08:00
|
|
|
if (!try_lock_extent(io_tree, eb->start, eb->start + eb->len - 1,
|
2022-10-01 04:45:13 +08:00
|
|
|
&cached_state))
|
2021-04-08 20:40:25 +08:00
|
|
|
return -EAGAIN;
|
2021-01-26 16:33:57 +08:00
|
|
|
} else {
|
2022-10-01 04:45:13 +08:00
|
|
|
ret = lock_extent(io_tree, eb->start, eb->start + eb->len - 1,
|
|
|
|
&cached_state);
|
2021-01-26 16:33:57 +08:00
|
|
|
if (ret < 0)
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = 0;
|
|
|
|
if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags) ||
|
|
|
|
PageUptodate(page) ||
|
|
|
|
btrfs_subpage_test_uptodate(fs_info, page, eb->start, eb->len)) {
|
|
|
|
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
|
2022-10-01 04:45:13 +08:00
|
|
|
unlock_extent(io_tree, eb->start, eb->start + eb->len - 1,
|
|
|
|
&cached_state);
|
2021-01-26 16:33:57 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
|
|
|
|
eb->read_mirror = 0;
|
|
|
|
atomic_set(&eb->io_pages, 1);
|
|
|
|
check_buffer_tree_ref(eb);
|
2022-09-13 13:31:14 +08:00
|
|
|
bio_ctrl.end_io_func = end_bio_extent_readpage;
|
|
|
|
|
2021-01-26 16:33:57 +08:00
|
|
|
btrfs_subpage_clear_error(fs_info, page, eb->start, eb->len);
|
|
|
|
|
btrfs: subpage: fix a rare race between metadata endio and eb freeing
[BUG]
There is a very rare ASSERT() triggering during full fstests run for
subpage rw support.
No other reproducer so far.
The ASSERT() gets triggered for metadata read in
btrfs_page_set_uptodate() inside end_page_read().
[CAUSE]
There is still a small race window for metadata only, the race could
happen like this:
T1 | T2
------------------------------------+-----------------------------
end_bio_extent_readpage() |
|- btrfs_validate_metadata_buffer() |
| |- free_extent_buffer() |
| Still have 2 refs |
|- end_page_read() |
|- if (unlikely(PagePrivate()) |
| The page still has Private |
| | free_extent_buffer()
| | | Only one ref 1, will be
| | | released
| | |- detach_extent_buffer_page()
| | |- btrfs_detach_subpage()
|- btrfs_set_page_uptodate() |
The page no longer has Private|
>>> ASSERT() triggered <<< |
This race window is super small, thus pretty hard to hit, even with so
many runs of fstests.
But the race window is still there, we have to go another way to solve
it other than relying on random PagePrivate() check.
Data path is not affected, as it will lock the page before reading,
while unlocking the page after the last read has finished, thus no race
window.
[FIX]
This patch will fix the bug by repurposing btrfs_subpage::readers.
Now btrfs_subpage::readers will be a member shared by both metadata and
data.
For metadata path, we don't do the page unlock as metadata only relies
on extent locking.
At the same time, teach page_range_has_eb() to take
btrfs_subpage::readers into consideration.
So that even if the last eb of a page gets freed, page::private won't be
detached as long as there still are pending end_page_read() calls.
By this we eliminate the race window, this will slight increase the
metadata memory usage, as the page may not be released as frequently as
usual. But it should not be a big deal.
The code got introduced in ("btrfs: submit read time repair only for
each corrupted sector"), but the fix is in a separate patch to keep the
problem description and the crash is rare so it should not hurt
bisectability.
Signed-off-by: Qu Wegruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-06-07 17:02:58 +08:00
|
|
|
btrfs_subpage_start_reader(fs_info, page, eb->start, eb->len);
|
2022-05-26 15:36:39 +08:00
|
|
|
ret = submit_extent_page(REQ_OP_READ, NULL, &bio_ctrl,
|
btrfs: switch page and disk_bytenr argument position for submit_extent_page()
Normally we put (page, pg_len, pg_offset) arguments together, just like
what __bio_add_page() does.
But in submit_extent_page(), what we got is, (page, disk_bytenr, pg_len,
pg_offset), which sometimes can be confusing.
Change the order to (disk_bytenr, page, pg_len, pg_offset) to make it
to follow the common schema.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-13 13:31:13 +08:00
|
|
|
eb->start, page, eb->len,
|
2022-09-13 13:31:14 +08:00
|
|
|
eb->start - page_offset(page), 0, true);
|
2021-01-26 16:33:57 +08:00
|
|
|
if (ret) {
|
|
|
|
/*
|
|
|
|
* In the endio function, if we hit something wrong we will
|
|
|
|
* increase the io_pages, so here we need to decrease it for
|
|
|
|
* error path.
|
|
|
|
*/
|
|
|
|
atomic_dec(&eb->io_pages);
|
|
|
|
}
|
btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-14 13:32:51 +08:00
|
|
|
memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
|
2022-06-03 15:11:03 +08:00
|
|
|
submit_one_bio(&bio_ctrl);
|
2022-10-01 04:45:13 +08:00
|
|
|
if (ret || wait != WAIT_COMPLETE) {
|
|
|
|
free_extent_state(cached_state);
|
2021-01-26 16:33:57 +08:00
|
|
|
return ret;
|
2022-10-01 04:45:13 +08:00
|
|
|
}
|
2021-01-26 16:33:57 +08:00
|
|
|
|
2022-10-01 04:45:12 +08:00
|
|
|
wait_extent_bit(io_tree, eb->start, eb->start + eb->len - 1,
|
2022-10-01 04:45:13 +08:00
|
|
|
EXTENT_LOCKED, &cached_state);
|
2021-01-26 16:33:57 +08:00
|
|
|
if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
|
|
|
|
ret = -EIO;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-14 13:32:51 +08:00
|
|
|
int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
|
|
|
|
struct btrfs_tree_parent_check *check)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
2018-03-02 01:20:27 +08:00
|
|
|
int i;
|
2008-01-25 05:13:08 +08:00
|
|
|
struct page *page;
|
|
|
|
int err;
|
|
|
|
int ret = 0;
|
2008-04-10 04:28:12 +08:00
|
|
|
int locked_pages = 0;
|
|
|
|
int all_uptodate = 1;
|
2018-03-02 01:20:27 +08:00
|
|
|
int num_pages;
|
2010-08-07 01:21:20 +08:00
|
|
|
unsigned long num_reads = 0;
|
2022-06-03 15:11:03 +08:00
|
|
|
struct btrfs_bio_ctrl bio_ctrl = {
|
|
|
|
.mirror_num = mirror_num,
|
|
|
|
};
|
2008-02-07 23:50:54 +08:00
|
|
|
|
Btrfs: Change btree locking to use explicit blocking points
Most of the btrfs metadata operations can be protected by a spinlock,
but some operations still need to schedule.
So far, btrfs has been using a mutex along with a trylock loop,
most of the time it is able to avoid going for the full mutex, so
the trylock loop is a big performance gain.
This commit is step one for getting rid of the blocking locks entirely.
btrfs_tree_lock takes a spinlock, and the code explicitly switches
to a blocking lock when it starts an operation that can schedule.
We'll be able get rid of the blocking locks in smaller pieces over time.
Tracing allows us to find the most common cause of blocking, so we
can start with the hot spots first.
The basic idea is:
btrfs_tree_lock() returns with the spin lock held
btrfs_set_lock_blocking() sets the EXTENT_BUFFER_BLOCKING bit in
the extent buffer flags, and then drops the spin lock. The buffer is
still considered locked by all of the btrfs code.
If btrfs_tree_lock gets the spinlock but finds the blocking bit set, it drops
the spin lock and waits on a wait queue for the blocking bit to go away.
Much of the code that needs to set the blocking bit finishes without actually
blocking a good percentage of the time. So, an adaptive spin is still
used against the blocking bit to avoid very high context switch rates.
btrfs_clear_lock_blocking() clears the blocking bit and returns
with the spinlock held again.
btrfs_tree_unlock() can be called on either blocking or spinning locks,
it does the right thing based on the blocking bit.
ctree.c has a helper function to set/clear all the locked buffers in a
path as blocking.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-02-04 22:25:08 +08:00
|
|
|
if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
|
2008-01-25 05:13:08 +08:00
|
|
|
return 0;
|
|
|
|
|
btrfs: check WRITE_ERR when trying to read an extent buffer
Filipe reported a hang when we have errors on btrfs. This turned out to
be a side-effect of my fix c2e39305299f01 ("btrfs: clear extent buffer
uptodate when we fail to write it") which made it so we clear
EXTENT_BUFFER_UPTODATE on an eb when we fail to write it out.
Below is a paste of Filipe's analysis he got from using drgn to debug
the hang
"""
btree readahead code calls read_extent_buffer_pages(), sets ->io_pages to
a value while writeback of all pages has not yet completed:
--> writeback for the first 3 pages finishes, we clear
EXTENT_BUFFER_UPTODATE from eb on the first page when we get an
error.
--> at this point eb->io_pages is 1 and we cleared Uptodate bit from the
first 3 pages
--> read_extent_buffer_pages() does not see EXTENT_BUFFER_UPTODATE() so
it continues, it's able to lock the pages since we obviously don't
hold the pages locked during writeback
--> read_extent_buffer_pages() then computes 'num_reads' as 3, and sets
eb->io_pages to 3, since only the first page does not have Uptodate
bit set at this point
--> writeback for the remaining page completes, we ended decrementing
eb->io_pages by 1, resulting in eb->io_pages == 2, and therefore
never calling end_extent_buffer_writeback(), so
EXTENT_BUFFER_WRITEBACK remains in the eb's flags
--> of course, when the read bio completes, it doesn't and shouldn't
call end_extent_buffer_writeback()
--> we should clear EXTENT_BUFFER_UPTODATE only after all pages of
the eb finished writeback? or maybe make the read pages code
wait for writeback of all pages of the eb to complete before
checking which pages need to be read, touch ->io_pages, submit
read bio, etc
writeback bit never cleared means we can hang when aborting a
transaction, at:
btrfs_cleanup_one_transaction()
btrfs_destroy_marked_extents()
wait_on_extent_buffer_writeback()
"""
This is a problem because our writes are not synchronized with reads in
any way. We clear the UPTODATE flag and then we can easily come in and
try to read the EB while we're still waiting on other bio's to
complete.
We have two options here, we could lock all the pages, and then check to
see if eb->io_pages != 0 to know if we've already got an outstanding
write on the eb.
Or we can simply check to see if we have WRITE_ERR set on this extent
buffer. We set this bit _before_ we clear UPTODATE, so if the read gets
triggered because we aren't UPTODATE because of a write error we're
guaranteed to have WRITE_ERR set, and in this case we can simply return
-EIO. This will fix the reported hang.
Reported-by: Filipe Manana <fdmanana@suse.com>
Fixes: c2e39305299f01 ("btrfs: clear extent buffer uptodate when we fail to write it")
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-12-14 03:22:33 +08:00
|
|
|
/*
|
|
|
|
* We could have had EXTENT_BUFFER_UPTODATE cleared by the write
|
|
|
|
* operation, which could potentially still be in flight. In this case
|
|
|
|
* we simply want to return an error.
|
|
|
|
*/
|
|
|
|
if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)))
|
|
|
|
return -EIO;
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (eb->fs_info->nodesize < PAGE_SIZE)
|
btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-14 13:32:51 +08:00
|
|
|
return read_extent_buffer_subpage(eb, wait, mirror_num, check);
|
2021-01-26 16:33:57 +08:00
|
|
|
|
2018-06-29 16:56:49 +08:00
|
|
|
num_pages = num_extent_pages(eb);
|
2016-09-03 03:40:03 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2011-06-10 20:06:53 +08:00
|
|
|
if (wait == WAIT_NONE) {
|
2021-01-28 19:25:08 +08:00
|
|
|
/*
|
|
|
|
* WAIT_NONE is only utilized by readahead. If we can't
|
|
|
|
* acquire the lock atomically it means either the eb
|
|
|
|
* is being read out or under modification.
|
|
|
|
* Either way the eb will be or has been cached,
|
|
|
|
* readahead can exit safely.
|
|
|
|
*/
|
2008-08-07 23:19:43 +08:00
|
|
|
if (!trylock_page(page))
|
2008-04-10 04:28:12 +08:00
|
|
|
goto unlock_exit;
|
2008-01-25 05:13:08 +08:00
|
|
|
} else {
|
|
|
|
lock_page(page);
|
|
|
|
}
|
2008-04-10 04:28:12 +08:00
|
|
|
locked_pages++;
|
Btrfs: fix memory leak in reading btree blocks
So we can read a btree block via readahead or intentional read,
and we can end up with a memory leak when something happens as
follows,
1) readahead starts to read block A but does not wait for read
completion,
2) btree_readpage_end_io_hook finds that block A is corrupted,
and it needs to clear all block A's pages' uptodate bit.
3) meanwhile an intentional read kicks in and checks block A's
pages' uptodate to decide which page needs to be read.
4) when some pages have the uptodate bit during 3)'s check so
3) doesn't count them for eb->io_pages, but they are later
cleared by 2) so we has to readpage on the page, we get
the wrong eb->io_pages which results in a memory leak of
this block.
This fixes the problem by firstly getting all pages's locking and
then checking pages' uptodate bit.
t1(readahead) t2(readahead endio) t3(the following read)
read_extent_buffer_pages end_bio_extent_readpage
for pg in eb: for page 0,1,2 in eb:
if pg is uptodate: btree_readpage_end_io_hook(pg)
num_reads++ if uptodate:
eb->io_pages = num_reads SetPageUptodate(pg) _______________
for pg in eb: for page 3 in eb: read_extent_buffer_pages
if pg is NOT uptodate: btree_readpage_end_io_hook(pg) for pg in eb:
__extent_read_full_page(pg) sanity check reports something wrong if pg is uptodate:
clear_extent_buffer_uptodate(eb) num_reads++
for pg in eb: eb->io_pages = num_reads
ClearPageUptodate(page) _______________
for pg in eb:
if pg is NOT uptodate:
__extent_read_full_page(pg)
So t3's eb->io_pages is not consistent with the number of pages it's reading,
and during endio(), atomic_dec_and_test(&eb->io_pages) will get a negative
number so that we're not able to free the eb.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2016-08-04 03:33:01 +08:00
|
|
|
}
|
|
|
|
/*
|
|
|
|
* We need to firstly lock all pages to make sure that
|
|
|
|
* the uptodate bit of our pages won't be affected by
|
|
|
|
* clear_extent_buffer_uptodate().
|
|
|
|
*/
|
2016-09-03 03:40:03 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
Btrfs: fix memory leak in reading btree blocks
So we can read a btree block via readahead or intentional read,
and we can end up with a memory leak when something happens as
follows,
1) readahead starts to read block A but does not wait for read
completion,
2) btree_readpage_end_io_hook finds that block A is corrupted,
and it needs to clear all block A's pages' uptodate bit.
3) meanwhile an intentional read kicks in and checks block A's
pages' uptodate to decide which page needs to be read.
4) when some pages have the uptodate bit during 3)'s check so
3) doesn't count them for eb->io_pages, but they are later
cleared by 2) so we has to readpage on the page, we get
the wrong eb->io_pages which results in a memory leak of
this block.
This fixes the problem by firstly getting all pages's locking and
then checking pages' uptodate bit.
t1(readahead) t2(readahead endio) t3(the following read)
read_extent_buffer_pages end_bio_extent_readpage
for pg in eb: for page 0,1,2 in eb:
if pg is uptodate: btree_readpage_end_io_hook(pg)
num_reads++ if uptodate:
eb->io_pages = num_reads SetPageUptodate(pg) _______________
for pg in eb: for page 3 in eb: read_extent_buffer_pages
if pg is NOT uptodate: btree_readpage_end_io_hook(pg) for pg in eb:
__extent_read_full_page(pg) sanity check reports something wrong if pg is uptodate:
clear_extent_buffer_uptodate(eb) num_reads++
for pg in eb: eb->io_pages = num_reads
ClearPageUptodate(page) _______________
for pg in eb:
if pg is NOT uptodate:
__extent_read_full_page(pg)
So t3's eb->io_pages is not consistent with the number of pages it's reading,
and during endio(), atomic_dec_and_test(&eb->io_pages) will get a negative
number so that we're not able to free the eb.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2016-08-04 03:33:01 +08:00
|
|
|
page = eb->pages[i];
|
2010-08-07 01:21:20 +08:00
|
|
|
if (!PageUptodate(page)) {
|
|
|
|
num_reads++;
|
2008-04-10 04:28:12 +08:00
|
|
|
all_uptodate = 0;
|
2010-08-07 01:21:20 +08:00
|
|
|
}
|
2008-04-10 04:28:12 +08:00
|
|
|
}
|
Btrfs: fix memory leak in reading btree blocks
So we can read a btree block via readahead or intentional read,
and we can end up with a memory leak when something happens as
follows,
1) readahead starts to read block A but does not wait for read
completion,
2) btree_readpage_end_io_hook finds that block A is corrupted,
and it needs to clear all block A's pages' uptodate bit.
3) meanwhile an intentional read kicks in and checks block A's
pages' uptodate to decide which page needs to be read.
4) when some pages have the uptodate bit during 3)'s check so
3) doesn't count them for eb->io_pages, but they are later
cleared by 2) so we has to readpage on the page, we get
the wrong eb->io_pages which results in a memory leak of
this block.
This fixes the problem by firstly getting all pages's locking and
then checking pages' uptodate bit.
t1(readahead) t2(readahead endio) t3(the following read)
read_extent_buffer_pages end_bio_extent_readpage
for pg in eb: for page 0,1,2 in eb:
if pg is uptodate: btree_readpage_end_io_hook(pg)
num_reads++ if uptodate:
eb->io_pages = num_reads SetPageUptodate(pg) _______________
for pg in eb: for page 3 in eb: read_extent_buffer_pages
if pg is NOT uptodate: btree_readpage_end_io_hook(pg) for pg in eb:
__extent_read_full_page(pg) sanity check reports something wrong if pg is uptodate:
clear_extent_buffer_uptodate(eb) num_reads++
for pg in eb: eb->io_pages = num_reads
ClearPageUptodate(page) _______________
for pg in eb:
if pg is NOT uptodate:
__extent_read_full_page(pg)
So t3's eb->io_pages is not consistent with the number of pages it's reading,
and during endio(), atomic_dec_and_test(&eb->io_pages) will get a negative
number so that we're not able to free the eb.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2016-08-04 03:33:01 +08:00
|
|
|
|
2008-04-10 04:28:12 +08:00
|
|
|
if (all_uptodate) {
|
2016-09-03 03:40:03 +08:00
|
|
|
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
|
2008-04-10 04:28:12 +08:00
|
|
|
goto unlock_exit;
|
|
|
|
}
|
|
|
|
|
Btrfs: be aware of btree inode write errors to avoid fs corruption
While we have a transaction ongoing, the VM might decide at any time
to call btree_inode->i_mapping->a_ops->writepages(), which will start
writeback of dirty pages belonging to btree nodes/leafs. This call
might return an error or the writeback might finish with an error
before we attempt to commit the running transaction. If this happens,
we might have no way of knowing that such error happened when we are
committing the transaction - because the pages might no longer be
marked dirty nor tagged for writeback (if a subsequent modification
to the extent buffer didn't happen before the transaction commit) which
makes filemap_fdata[write|wait]_range unable to find such pages (even
if they're marked with SetPageError).
So if this happens we must abort the transaction, otherwise we commit
a super block with btree roots that point to btree nodes/leafs whose
content on disk is invalid - either garbage or the content of some
node/leaf from a past generation that got cowed or deleted and is no
longer valid (for this later case we end up getting error messages like
"parent transid verify failed on 10826481664 wanted 25748 found 29562"
when reading btree nodes/leafs from disk).
Note that setting and checking AS_EIO/AS_ENOSPC in the btree inode's
i_mapping would not be enough because we need to distinguish between
log tree extents (not fatal) vs non-log tree extents (fatal) and
because the next call to filemap_fdatawait_range() will catch and clear
such errors in the mapping - and that call might be from a log sync and
not from a transaction commit, which means we would not know about the
error at transaction commit time. Also, checking for the eb flag
EXTENT_BUFFER_IOERR at transaction commit time isn't done and would
not be completely reliable, as the eb might be removed from memory and
read back when trying to get it, which clears that flag right before
reading the eb's pages from disk, making us not know about the previous
write error.
Using the new 3 flags for the btree inode also makes us achieve the
goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
writeback for all dirty pages and before filemap_fdatawait_range() is
called, the writeback for all dirty pages had already finished with
errors - because we were not using AS_EIO/AS_ENOSPC,
filemap_fdatawait_range() would return success, as it could not know
that writeback errors happened (the pages were no longer tagged for
writeback).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2014-09-26 19:25:56 +08:00
|
|
|
clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
|
2012-04-16 21:42:26 +08:00
|
|
|
eb->read_mirror = 0;
|
2012-03-13 21:38:00 +08:00
|
|
|
atomic_set(&eb->io_pages, num_reads);
|
btrfs: fix fatal extent_buffer readahead vs releasepage race
Under somewhat convoluted conditions, it is possible to attempt to
release an extent_buffer that is under io, which triggers a BUG_ON in
btrfs_release_extent_buffer_pages.
This relies on a few different factors. First, extent_buffer reads done
as readahead for searching use WAIT_NONE, so they free the local extent
buffer reference while the io is outstanding. However, they should still
be protected by TREE_REF. However, if the system is doing signficant
reclaim, and simultaneously heavily accessing the extent_buffers, it is
possible for releasepage to race with two concurrent readahead attempts
in a way that leaves TREE_REF unset when the readahead extent buffer is
released.
Essentially, if two tasks race to allocate a new extent_buffer, but the
winner who attempts the first io is rebuffed by a page being locked
(likely by the reclaim itself) then the loser will still go ahead with
issuing the readahead. The loser's call to find_extent_buffer must also
race with the reclaim task reading the extent_buffer's refcount as 1 in
a way that allows the reclaim to re-clear the TREE_REF checked by
find_extent_buffer.
The following represents an example execution demonstrating the race:
CPU0 CPU1 CPU2
reada_for_search reada_for_search
readahead_tree_block readahead_tree_block
find_create_tree_block find_create_tree_block
alloc_extent_buffer alloc_extent_buffer
find_extent_buffer // not found
allocates eb
lock pages
associate pages to eb
insert eb into radix tree
set TREE_REF, refs == 2
unlock pages
read_extent_buffer_pages // WAIT_NONE
not uptodate (brand new eb)
lock_page
if !trylock_page
goto unlock_exit // not an error
free_extent_buffer
release_extent_buffer
atomic_dec_and_test refs to 1
find_extent_buffer // found
try_release_extent_buffer
take refs_lock
reads refs == 1; no io
atomic_inc_not_zero refs to 2
mark_buffer_accessed
check_buffer_tree_ref
// not STALE, won't take refs_lock
refs == 2; TREE_REF set // no action
read_extent_buffer_pages // WAIT_NONE
clear TREE_REF
release_extent_buffer
atomic_dec_and_test refs to 1
unlock_page
still not uptodate (CPU1 read failed on trylock_page)
locks pages
set io_pages > 0
submit io
return
free_extent_buffer
release_extent_buffer
dec refs to 0
delete from radix tree
btrfs_release_extent_buffer_pages
BUG_ON(io_pages > 0)!!!
We observe this at a very low rate in production and were also able to
reproduce it in a test environment by introducing some spurious delays
and by introducing probabilistic trylock_page failures.
To fix it, we apply check_tree_ref at a point where it could not
possibly be unset by a competing task: after io_pages has been
incremented. All the codepaths that clear TREE_REF check for io, so they
would not be able to clear it after this point until the io is done.
Stack trace, for reference:
[1417839.424739] ------------[ cut here ]------------
[1417839.435328] kernel BUG at fs/btrfs/extent_io.c:4841!
[1417839.447024] invalid opcode: 0000 [#1] SMP
[1417839.502972] RIP: 0010:btrfs_release_extent_buffer_pages+0x20/0x1f0
[1417839.517008] Code: ed e9 ...
[1417839.558895] RSP: 0018:ffffc90020bcf798 EFLAGS: 00010202
[1417839.570816] RAX: 0000000000000002 RBX: ffff888102d6def0 RCX: 0000000000000028
[1417839.586962] RDX: 0000000000000002 RSI: ffff8887f0296482 RDI: ffff888102d6def0
[1417839.603108] RBP: ffff88885664a000 R08: 0000000000000046 R09: 0000000000000238
[1417839.619255] R10: 0000000000000028 R11: ffff88885664af68 R12: 0000000000000000
[1417839.635402] R13: 0000000000000000 R14: ffff88875f573ad0 R15: ffff888797aafd90
[1417839.651549] FS: 00007f5a844fa700(0000) GS:ffff88885f680000(0000) knlGS:0000000000000000
[1417839.669810] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1417839.682887] CR2: 00007f7884541fe0 CR3: 000000049f609002 CR4: 00000000003606e0
[1417839.699037] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[1417839.715187] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[1417839.731320] Call Trace:
[1417839.737103] release_extent_buffer+0x39/0x90
[1417839.746913] read_block_for_search.isra.38+0x2a3/0x370
[1417839.758645] btrfs_search_slot+0x260/0x9b0
[1417839.768054] btrfs_lookup_file_extent+0x4a/0x70
[1417839.778427] btrfs_get_extent+0x15f/0x830
[1417839.787665] ? submit_extent_page+0xc4/0x1c0
[1417839.797474] ? __do_readpage+0x299/0x7a0
[1417839.806515] __do_readpage+0x33b/0x7a0
[1417839.815171] ? btrfs_releasepage+0x70/0x70
[1417839.824597] extent_readpages+0x28f/0x400
[1417839.833836] read_pages+0x6a/0x1c0
[1417839.841729] ? startup_64+0x2/0x30
[1417839.849624] __do_page_cache_readahead+0x13c/0x1a0
[1417839.860590] filemap_fault+0x6c7/0x990
[1417839.869252] ? xas_load+0x8/0x80
[1417839.876756] ? xas_find+0x150/0x190
[1417839.884839] ? filemap_map_pages+0x295/0x3b0
[1417839.894652] __do_fault+0x32/0x110
[1417839.902540] __handle_mm_fault+0xacd/0x1000
[1417839.912156] handle_mm_fault+0xaa/0x1c0
[1417839.921004] __do_page_fault+0x242/0x4b0
[1417839.930044] ? page_fault+0x8/0x30
[1417839.937933] page_fault+0x1e/0x30
[1417839.945631] RIP: 0033:0x33c4bae
[1417839.952927] Code: Bad RIP value.
[1417839.960411] RSP: 002b:00007f5a844f7350 EFLAGS: 00010206
[1417839.972331] RAX: 000000000000006e RBX: 1614b3ff6a50398a RCX: 0000000000000000
[1417839.988477] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000002
[1417840.004626] RBP: 00007f5a844f7420 R08: 000000000000006e R09: 00007f5a94aeccb8
[1417840.020784] R10: 00007f5a844f7350 R11: 0000000000000000 R12: 00007f5a94aecc79
[1417840.036932] R13: 00007f5a94aecc78 R14: 00007f5a94aecc90 R15: 00007f5a94aecc40
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-06-18 02:35:19 +08:00
|
|
|
/*
|
2022-05-01 11:15:16 +08:00
|
|
|
* It is possible for release_folio to clear the TREE_REF bit before we
|
btrfs: fix fatal extent_buffer readahead vs releasepage race
Under somewhat convoluted conditions, it is possible to attempt to
release an extent_buffer that is under io, which triggers a BUG_ON in
btrfs_release_extent_buffer_pages.
This relies on a few different factors. First, extent_buffer reads done
as readahead for searching use WAIT_NONE, so they free the local extent
buffer reference while the io is outstanding. However, they should still
be protected by TREE_REF. However, if the system is doing signficant
reclaim, and simultaneously heavily accessing the extent_buffers, it is
possible for releasepage to race with two concurrent readahead attempts
in a way that leaves TREE_REF unset when the readahead extent buffer is
released.
Essentially, if two tasks race to allocate a new extent_buffer, but the
winner who attempts the first io is rebuffed by a page being locked
(likely by the reclaim itself) then the loser will still go ahead with
issuing the readahead. The loser's call to find_extent_buffer must also
race with the reclaim task reading the extent_buffer's refcount as 1 in
a way that allows the reclaim to re-clear the TREE_REF checked by
find_extent_buffer.
The following represents an example execution demonstrating the race:
CPU0 CPU1 CPU2
reada_for_search reada_for_search
readahead_tree_block readahead_tree_block
find_create_tree_block find_create_tree_block
alloc_extent_buffer alloc_extent_buffer
find_extent_buffer // not found
allocates eb
lock pages
associate pages to eb
insert eb into radix tree
set TREE_REF, refs == 2
unlock pages
read_extent_buffer_pages // WAIT_NONE
not uptodate (brand new eb)
lock_page
if !trylock_page
goto unlock_exit // not an error
free_extent_buffer
release_extent_buffer
atomic_dec_and_test refs to 1
find_extent_buffer // found
try_release_extent_buffer
take refs_lock
reads refs == 1; no io
atomic_inc_not_zero refs to 2
mark_buffer_accessed
check_buffer_tree_ref
// not STALE, won't take refs_lock
refs == 2; TREE_REF set // no action
read_extent_buffer_pages // WAIT_NONE
clear TREE_REF
release_extent_buffer
atomic_dec_and_test refs to 1
unlock_page
still not uptodate (CPU1 read failed on trylock_page)
locks pages
set io_pages > 0
submit io
return
free_extent_buffer
release_extent_buffer
dec refs to 0
delete from radix tree
btrfs_release_extent_buffer_pages
BUG_ON(io_pages > 0)!!!
We observe this at a very low rate in production and were also able to
reproduce it in a test environment by introducing some spurious delays
and by introducing probabilistic trylock_page failures.
To fix it, we apply check_tree_ref at a point where it could not
possibly be unset by a competing task: after io_pages has been
incremented. All the codepaths that clear TREE_REF check for io, so they
would not be able to clear it after this point until the io is done.
Stack trace, for reference:
[1417839.424739] ------------[ cut here ]------------
[1417839.435328] kernel BUG at fs/btrfs/extent_io.c:4841!
[1417839.447024] invalid opcode: 0000 [#1] SMP
[1417839.502972] RIP: 0010:btrfs_release_extent_buffer_pages+0x20/0x1f0
[1417839.517008] Code: ed e9 ...
[1417839.558895] RSP: 0018:ffffc90020bcf798 EFLAGS: 00010202
[1417839.570816] RAX: 0000000000000002 RBX: ffff888102d6def0 RCX: 0000000000000028
[1417839.586962] RDX: 0000000000000002 RSI: ffff8887f0296482 RDI: ffff888102d6def0
[1417839.603108] RBP: ffff88885664a000 R08: 0000000000000046 R09: 0000000000000238
[1417839.619255] R10: 0000000000000028 R11: ffff88885664af68 R12: 0000000000000000
[1417839.635402] R13: 0000000000000000 R14: ffff88875f573ad0 R15: ffff888797aafd90
[1417839.651549] FS: 00007f5a844fa700(0000) GS:ffff88885f680000(0000) knlGS:0000000000000000
[1417839.669810] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1417839.682887] CR2: 00007f7884541fe0 CR3: 000000049f609002 CR4: 00000000003606e0
[1417839.699037] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[1417839.715187] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[1417839.731320] Call Trace:
[1417839.737103] release_extent_buffer+0x39/0x90
[1417839.746913] read_block_for_search.isra.38+0x2a3/0x370
[1417839.758645] btrfs_search_slot+0x260/0x9b0
[1417839.768054] btrfs_lookup_file_extent+0x4a/0x70
[1417839.778427] btrfs_get_extent+0x15f/0x830
[1417839.787665] ? submit_extent_page+0xc4/0x1c0
[1417839.797474] ? __do_readpage+0x299/0x7a0
[1417839.806515] __do_readpage+0x33b/0x7a0
[1417839.815171] ? btrfs_releasepage+0x70/0x70
[1417839.824597] extent_readpages+0x28f/0x400
[1417839.833836] read_pages+0x6a/0x1c0
[1417839.841729] ? startup_64+0x2/0x30
[1417839.849624] __do_page_cache_readahead+0x13c/0x1a0
[1417839.860590] filemap_fault+0x6c7/0x990
[1417839.869252] ? xas_load+0x8/0x80
[1417839.876756] ? xas_find+0x150/0x190
[1417839.884839] ? filemap_map_pages+0x295/0x3b0
[1417839.894652] __do_fault+0x32/0x110
[1417839.902540] __handle_mm_fault+0xacd/0x1000
[1417839.912156] handle_mm_fault+0xaa/0x1c0
[1417839.921004] __do_page_fault+0x242/0x4b0
[1417839.930044] ? page_fault+0x8/0x30
[1417839.937933] page_fault+0x1e/0x30
[1417839.945631] RIP: 0033:0x33c4bae
[1417839.952927] Code: Bad RIP value.
[1417839.960411] RSP: 002b:00007f5a844f7350 EFLAGS: 00010206
[1417839.972331] RAX: 000000000000006e RBX: 1614b3ff6a50398a RCX: 0000000000000000
[1417839.988477] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000002
[1417840.004626] RBP: 00007f5a844f7420 R08: 000000000000006e R09: 00007f5a94aeccb8
[1417840.020784] R10: 00007f5a844f7350 R11: 0000000000000000 R12: 00007f5a94aecc79
[1417840.036932] R13: 00007f5a94aecc78 R14: 00007f5a94aecc90 R15: 00007f5a94aecc40
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
2020-06-18 02:35:19 +08:00
|
|
|
* set io_pages. See check_buffer_tree_ref for a more detailed comment.
|
|
|
|
*/
|
|
|
|
check_buffer_tree_ref(eb);
|
2022-09-13 13:31:14 +08:00
|
|
|
bio_ctrl.end_io_func = end_bio_extent_readpage;
|
2016-09-03 03:40:03 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2016-07-12 01:39:07 +08:00
|
|
|
|
2008-04-10 04:28:12 +08:00
|
|
|
if (!PageUptodate(page)) {
|
2016-07-12 01:39:07 +08:00
|
|
|
if (ret) {
|
|
|
|
atomic_dec(&eb->io_pages);
|
|
|
|
unlock_page(page);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2008-04-10 04:28:12 +08:00
|
|
|
ClearPageError(page);
|
2022-05-26 15:36:39 +08:00
|
|
|
err = submit_extent_page(REQ_OP_READ, NULL,
|
btrfs: switch page and disk_bytenr argument position for submit_extent_page()
Normally we put (page, pg_len, pg_offset) arguments together, just like
what __bio_add_page() does.
But in submit_extent_page(), what we got is, (page, disk_bytenr, pg_len,
pg_offset), which sometimes can be confusing.
Change the order to (disk_bytenr, page, pg_len, pg_offset) to make it
to follow the common schema.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-13 13:31:13 +08:00
|
|
|
&bio_ctrl, page_offset(page), page,
|
2022-09-13 13:31:14 +08:00
|
|
|
PAGE_SIZE, 0, 0, false);
|
2016-07-12 01:39:07 +08:00
|
|
|
if (err) {
|
|
|
|
/*
|
2020-09-14 17:37:04 +08:00
|
|
|
* We failed to submit the bio so it's the
|
|
|
|
* caller's responsibility to perform cleanup
|
|
|
|
* i.e unlock page/set error bit.
|
2016-07-12 01:39:07 +08:00
|
|
|
*/
|
2020-09-14 17:37:04 +08:00
|
|
|
ret = err;
|
|
|
|
SetPageError(page);
|
|
|
|
unlock_page(page);
|
2016-07-12 01:39:07 +08:00
|
|
|
atomic_dec(&eb->io_pages);
|
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
} else {
|
|
|
|
unlock_page(page);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-14 13:32:51 +08:00
|
|
|
memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
|
2022-06-03 15:11:03 +08:00
|
|
|
submit_one_bio(&bio_ctrl);
|
2008-02-07 23:50:54 +08:00
|
|
|
|
2011-06-10 20:06:53 +08:00
|
|
|
if (ret || wait != WAIT_COMPLETE)
|
2008-01-25 05:13:08 +08:00
|
|
|
return ret;
|
2009-01-06 10:25:51 +08:00
|
|
|
|
2016-09-03 03:40:03 +08:00
|
|
|
for (i = 0; i < num_pages; i++) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2008-01-25 05:13:08 +08:00
|
|
|
wait_on_page_locked(page);
|
2009-01-06 10:25:51 +08:00
|
|
|
if (!PageUptodate(page))
|
2008-01-25 05:13:08 +08:00
|
|
|
ret = -EIO;
|
|
|
|
}
|
2009-01-06 10:25:51 +08:00
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
return ret;
|
2008-04-10 04:28:12 +08:00
|
|
|
|
|
|
|
unlock_exit:
|
2009-01-06 10:25:51 +08:00
|
|
|
while (locked_pages > 0) {
|
2008-04-10 04:28:12 +08:00
|
|
|
locked_pages--;
|
2016-09-03 03:40:03 +08:00
|
|
|
page = eb->pages[locked_pages];
|
|
|
|
unlock_page(page);
|
2008-04-10 04:28:12 +08:00
|
|
|
}
|
|
|
|
return ret;
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
btrfs: extent_io: do extra check for extent buffer read write functions
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19 14:35:47 +08:00
|
|
|
static bool report_eb_range(const struct extent_buffer *eb, unsigned long start,
|
|
|
|
unsigned long len)
|
|
|
|
{
|
|
|
|
btrfs_warn(eb->fs_info,
|
|
|
|
"access to eb bytenr %llu len %lu out of range start %lu len %lu",
|
|
|
|
eb->start, eb->len, start, len);
|
|
|
|
WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check if the [start, start + len) range is valid before reading/writing
|
|
|
|
* the eb.
|
|
|
|
* NOTE: @start and @len are offset inside the eb, not logical address.
|
|
|
|
*
|
|
|
|
* Caller should not touch the dst/src memory if this function returns error.
|
|
|
|
*/
|
|
|
|
static inline int check_eb_range(const struct extent_buffer *eb,
|
|
|
|
unsigned long start, unsigned long len)
|
|
|
|
{
|
|
|
|
unsigned long offset;
|
|
|
|
|
|
|
|
/* start, start + len should not go beyond eb->len nor overflow */
|
|
|
|
if (unlikely(check_add_overflow(start, len, &offset) || offset > eb->len))
|
|
|
|
return report_eb_range(eb, start, len);
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2017-06-29 11:56:53 +08:00
|
|
|
void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
|
|
|
|
unsigned long start, unsigned long len)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
size_t cur;
|
|
|
|
size_t offset;
|
|
|
|
struct page *page;
|
|
|
|
char *kaddr;
|
|
|
|
char *dst = (char *)dstv;
|
2020-12-02 14:48:04 +08:00
|
|
|
unsigned long i = get_eb_page_index(start);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
btrfs: extent_io: do extra check for extent buffer read write functions
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19 14:35:47 +08:00
|
|
|
if (check_eb_range(eb, start, len))
|
Btrfs: fix out of bounds array access while reading extent buffer
There is a corner case that slips through the checkers in functions
reading extent buffer, ie.
if (start < eb->len) and (start + len > eb->len),
then
a) map_private_extent_buffer() returns immediately because
it's thinking the range spans across two pages,
b) and the checkers in read_extent_buffer(), WARN_ON(start > eb->len)
and WARN_ON(start + len > eb->start + eb->len), both are OK in this
corner case, but it'd actually try to access the eb->pages out of
bounds because of (start + len > eb->len).
The case is found by switching extent inline ref type from shared data
ref to non-shared data ref, which is a kind of metadata corruption.
It'd use the wrong helper to access the eb,
eg. btrfs_extent_data_ref_root(eb, ref) is used but the %ref passing
here is "struct btrfs_shared_data_ref". And if the extent item
happens to be the first item in the eb, then offset/length will get
over eb->len which ends up an invalid memory access.
This is adding proper checks in order to avoid invalid memory access,
ie. 'general protection fault', before it's too late.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2017-08-10 01:10:16 +08:00
|
|
|
return;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-12-02 14:48:04 +08:00
|
|
|
offset = get_eb_offset_in_page(eb, start);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2009-01-06 10:25:51 +08:00
|
|
|
while (len > 0) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2008-01-25 05:13:08 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
cur = min(len, (PAGE_SIZE - offset));
|
2011-07-20 00:04:14 +08:00
|
|
|
kaddr = page_address(page);
|
2008-01-25 05:13:08 +08:00
|
|
|
memcpy(dst, kaddr + offset, cur);
|
|
|
|
|
|
|
|
dst += cur;
|
|
|
|
len -= cur;
|
|
|
|
offset = 0;
|
|
|
|
i++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-08-10 23:42:27 +08:00
|
|
|
int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
|
|
|
|
void __user *dstv,
|
|
|
|
unsigned long start, unsigned long len)
|
2014-01-30 23:24:01 +08:00
|
|
|
{
|
|
|
|
size_t cur;
|
|
|
|
size_t offset;
|
|
|
|
struct page *page;
|
|
|
|
char *kaddr;
|
|
|
|
char __user *dst = (char __user *)dstv;
|
2020-12-02 14:48:04 +08:00
|
|
|
unsigned long i = get_eb_page_index(start);
|
2014-01-30 23:24:01 +08:00
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
WARN_ON(start > eb->len);
|
|
|
|
WARN_ON(start + len > eb->start + eb->len);
|
|
|
|
|
2020-12-02 14:48:04 +08:00
|
|
|
offset = get_eb_offset_in_page(eb, start);
|
2014-01-30 23:24:01 +08:00
|
|
|
|
|
|
|
while (len > 0) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2014-01-30 23:24:01 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
cur = min(len, (PAGE_SIZE - offset));
|
2014-01-30 23:24:01 +08:00
|
|
|
kaddr = page_address(page);
|
2020-08-10 23:42:27 +08:00
|
|
|
if (copy_to_user_nofault(dst, kaddr + offset, cur)) {
|
2014-01-30 23:24:01 +08:00
|
|
|
ret = -EFAULT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
dst += cur;
|
|
|
|
len -= cur;
|
|
|
|
offset = 0;
|
|
|
|
i++;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2017-06-29 11:56:53 +08:00
|
|
|
int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
|
|
|
|
unsigned long start, unsigned long len)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
size_t cur;
|
|
|
|
size_t offset;
|
|
|
|
struct page *page;
|
|
|
|
char *kaddr;
|
|
|
|
char *ptr = (char *)ptrv;
|
2020-12-02 14:48:04 +08:00
|
|
|
unsigned long i = get_eb_page_index(start);
|
2008-01-25 05:13:08 +08:00
|
|
|
int ret = 0;
|
|
|
|
|
btrfs: extent_io: do extra check for extent buffer read write functions
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19 14:35:47 +08:00
|
|
|
if (check_eb_range(eb, start, len))
|
|
|
|
return -EINVAL;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-12-02 14:48:04 +08:00
|
|
|
offset = get_eb_offset_in_page(eb, start);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2009-01-06 10:25:51 +08:00
|
|
|
while (len > 0) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2008-01-25 05:13:08 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
cur = min(len, (PAGE_SIZE - offset));
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2011-07-20 00:04:14 +08:00
|
|
|
kaddr = page_address(page);
|
2008-01-25 05:13:08 +08:00
|
|
|
ret = memcmp(ptr, kaddr + offset, cur);
|
|
|
|
if (ret)
|
|
|
|
break;
|
|
|
|
|
|
|
|
ptr += cur;
|
|
|
|
len -= cur;
|
|
|
|
offset = 0;
|
|
|
|
i++;
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2021-03-25 15:14:42 +08:00
|
|
|
/*
|
|
|
|
* Check that the extent buffer is uptodate.
|
|
|
|
*
|
|
|
|
* For regular sector size == PAGE_SIZE case, check if @page is uptodate.
|
|
|
|
* For subpage case, check if the range covered by the eb has EXTENT_UPTODATE.
|
|
|
|
*/
|
|
|
|
static void assert_eb_page_uptodate(const struct extent_buffer *eb,
|
|
|
|
struct page *page)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = eb->fs_info;
|
|
|
|
|
btrfs: do not WARN_ON() if we have PageError set
Whenever we do any extent buffer operations we call
assert_eb_page_uptodate() to complain loudly if we're operating on an
non-uptodate page. Our overnight tests caught this warning earlier this
week
WARNING: CPU: 1 PID: 553508 at fs/btrfs/extent_io.c:6849 assert_eb_page_uptodate+0x3f/0x50
CPU: 1 PID: 553508 Comm: kworker/u4:13 Tainted: G W 5.17.0-rc3+ #564
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Workqueue: btrfs-cache btrfs_work_helper
RIP: 0010:assert_eb_page_uptodate+0x3f/0x50
RSP: 0018:ffffa961440a7c68 EFLAGS: 00010246
RAX: 0017ffffc0002112 RBX: ffffe6e74453f9c0 RCX: 0000000000001000
RDX: ffffe6e74467c887 RSI: ffffe6e74453f9c0 RDI: ffff8d4c5efc2fc0
RBP: 0000000000000d56 R08: ffff8d4d4a224000 R09: 0000000000000000
R10: 00015817fa9d1ef0 R11: 000000000000000c R12: 00000000000007b1
R13: ffff8d4c5efc2fc0 R14: 0000000001500000 R15: 0000000001cb1000
FS: 0000000000000000(0000) GS:ffff8d4dbbd00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ff31d3448d8 CR3: 0000000118be8004 CR4: 0000000000370ee0
Call Trace:
extent_buffer_test_bit+0x3f/0x70
free_space_test_bit+0xa6/0xc0
load_free_space_tree+0x1f6/0x470
caching_thread+0x454/0x630
? rcu_read_lock_sched_held+0x12/0x60
? rcu_read_lock_sched_held+0x12/0x60
? rcu_read_lock_sched_held+0x12/0x60
? lock_release+0x1f0/0x2d0
btrfs_work_helper+0xf2/0x3e0
? lock_release+0x1f0/0x2d0
? finish_task_switch.isra.0+0xf9/0x3a0
process_one_work+0x26d/0x580
? process_one_work+0x580/0x580
worker_thread+0x55/0x3b0
? process_one_work+0x580/0x580
kthread+0xf0/0x120
? kthread_complete_and_exit+0x20/0x20
ret_from_fork+0x1f/0x30
This was partially fixed by c2e39305299f01 ("btrfs: clear extent buffer
uptodate when we fail to write it"), however all that fix did was keep
us from finding extent buffers after a failed writeout. It didn't keep
us from continuing to use a buffer that we already had found.
In this case we're searching the commit root to cache the block group,
so we can start committing the transaction and switch the commit root
and then start writing. After the switch we can look up an extent
buffer that hasn't been written yet and start processing that block
group. Then we fail to write that block out and clear Uptodate on the
page, and then we start spewing these errors.
Normally we're protected by the tree lock to a certain degree here. If
we read a block we have that block read locked, and we block the writer
from locking the block before we submit it for the write. However this
isn't necessarily fool proof because the read could happen before we do
the submit_bio and after we locked and unlocked the extent buffer.
Also in this particular case we have path->skip_locking set, so that
won't save us here. We'll simply get a block that was valid when we
read it, but became invalid while we were using it.
What we really want is to catch the case where we've "read" a block but
it's not marked Uptodate. On read we ClearPageError(), so if we're
!Uptodate and !Error we know we didn't do the right thing for reading
the page.
Fix this by checking !Uptodate && !Error, this way we will not complain
if our buffer gets invalidated while we're using it, and we'll maintain
the spirit of the check which is to make sure we have a fully in-cache
block while we're messing with it.
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-18 23:17:39 +08:00
|
|
|
/*
|
|
|
|
* If we are using the commit root we could potentially clear a page
|
|
|
|
* Uptodate while we're using the extent buffer that we've previously
|
|
|
|
* looked up. We don't want to complain in this case, as the page was
|
|
|
|
* valid before, we just didn't write it out. Instead we want to catch
|
|
|
|
* the case where we didn't actually read the block properly, which
|
|
|
|
* would have !PageUptodate && !PageError, as we clear PageError before
|
|
|
|
* reading.
|
|
|
|
*/
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (fs_info->nodesize < PAGE_SIZE) {
|
btrfs: do not WARN_ON() if we have PageError set
Whenever we do any extent buffer operations we call
assert_eb_page_uptodate() to complain loudly if we're operating on an
non-uptodate page. Our overnight tests caught this warning earlier this
week
WARNING: CPU: 1 PID: 553508 at fs/btrfs/extent_io.c:6849 assert_eb_page_uptodate+0x3f/0x50
CPU: 1 PID: 553508 Comm: kworker/u4:13 Tainted: G W 5.17.0-rc3+ #564
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Workqueue: btrfs-cache btrfs_work_helper
RIP: 0010:assert_eb_page_uptodate+0x3f/0x50
RSP: 0018:ffffa961440a7c68 EFLAGS: 00010246
RAX: 0017ffffc0002112 RBX: ffffe6e74453f9c0 RCX: 0000000000001000
RDX: ffffe6e74467c887 RSI: ffffe6e74453f9c0 RDI: ffff8d4c5efc2fc0
RBP: 0000000000000d56 R08: ffff8d4d4a224000 R09: 0000000000000000
R10: 00015817fa9d1ef0 R11: 000000000000000c R12: 00000000000007b1
R13: ffff8d4c5efc2fc0 R14: 0000000001500000 R15: 0000000001cb1000
FS: 0000000000000000(0000) GS:ffff8d4dbbd00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ff31d3448d8 CR3: 0000000118be8004 CR4: 0000000000370ee0
Call Trace:
extent_buffer_test_bit+0x3f/0x70
free_space_test_bit+0xa6/0xc0
load_free_space_tree+0x1f6/0x470
caching_thread+0x454/0x630
? rcu_read_lock_sched_held+0x12/0x60
? rcu_read_lock_sched_held+0x12/0x60
? rcu_read_lock_sched_held+0x12/0x60
? lock_release+0x1f0/0x2d0
btrfs_work_helper+0xf2/0x3e0
? lock_release+0x1f0/0x2d0
? finish_task_switch.isra.0+0xf9/0x3a0
process_one_work+0x26d/0x580
? process_one_work+0x580/0x580
worker_thread+0x55/0x3b0
? process_one_work+0x580/0x580
kthread+0xf0/0x120
? kthread_complete_and_exit+0x20/0x20
ret_from_fork+0x1f/0x30
This was partially fixed by c2e39305299f01 ("btrfs: clear extent buffer
uptodate when we fail to write it"), however all that fix did was keep
us from finding extent buffers after a failed writeout. It didn't keep
us from continuing to use a buffer that we already had found.
In this case we're searching the commit root to cache the block group,
so we can start committing the transaction and switch the commit root
and then start writing. After the switch we can look up an extent
buffer that hasn't been written yet and start processing that block
group. Then we fail to write that block out and clear Uptodate on the
page, and then we start spewing these errors.
Normally we're protected by the tree lock to a certain degree here. If
we read a block we have that block read locked, and we block the writer
from locking the block before we submit it for the write. However this
isn't necessarily fool proof because the read could happen before we do
the submit_bio and after we locked and unlocked the extent buffer.
Also in this particular case we have path->skip_locking set, so that
won't save us here. We'll simply get a block that was valid when we
read it, but became invalid while we were using it.
What we really want is to catch the case where we've "read" a block but
it's not marked Uptodate. On read we ClearPageError(), so if we're
!Uptodate and !Error we know we didn't do the right thing for reading
the page.
Fix this by checking !Uptodate && !Error, this way we will not complain
if our buffer gets invalidated while we're using it, and we'll maintain
the spirit of the check which is to make sure we have a fully in-cache
block while we're messing with it.
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-18 23:17:39 +08:00
|
|
|
bool uptodate, error;
|
2021-03-25 15:14:42 +08:00
|
|
|
|
|
|
|
uptodate = btrfs_subpage_test_uptodate(fs_info, page,
|
|
|
|
eb->start, eb->len);
|
btrfs: do not WARN_ON() if we have PageError set
Whenever we do any extent buffer operations we call
assert_eb_page_uptodate() to complain loudly if we're operating on an
non-uptodate page. Our overnight tests caught this warning earlier this
week
WARNING: CPU: 1 PID: 553508 at fs/btrfs/extent_io.c:6849 assert_eb_page_uptodate+0x3f/0x50
CPU: 1 PID: 553508 Comm: kworker/u4:13 Tainted: G W 5.17.0-rc3+ #564
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Workqueue: btrfs-cache btrfs_work_helper
RIP: 0010:assert_eb_page_uptodate+0x3f/0x50
RSP: 0018:ffffa961440a7c68 EFLAGS: 00010246
RAX: 0017ffffc0002112 RBX: ffffe6e74453f9c0 RCX: 0000000000001000
RDX: ffffe6e74467c887 RSI: ffffe6e74453f9c0 RDI: ffff8d4c5efc2fc0
RBP: 0000000000000d56 R08: ffff8d4d4a224000 R09: 0000000000000000
R10: 00015817fa9d1ef0 R11: 000000000000000c R12: 00000000000007b1
R13: ffff8d4c5efc2fc0 R14: 0000000001500000 R15: 0000000001cb1000
FS: 0000000000000000(0000) GS:ffff8d4dbbd00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ff31d3448d8 CR3: 0000000118be8004 CR4: 0000000000370ee0
Call Trace:
extent_buffer_test_bit+0x3f/0x70
free_space_test_bit+0xa6/0xc0
load_free_space_tree+0x1f6/0x470
caching_thread+0x454/0x630
? rcu_read_lock_sched_held+0x12/0x60
? rcu_read_lock_sched_held+0x12/0x60
? rcu_read_lock_sched_held+0x12/0x60
? lock_release+0x1f0/0x2d0
btrfs_work_helper+0xf2/0x3e0
? lock_release+0x1f0/0x2d0
? finish_task_switch.isra.0+0xf9/0x3a0
process_one_work+0x26d/0x580
? process_one_work+0x580/0x580
worker_thread+0x55/0x3b0
? process_one_work+0x580/0x580
kthread+0xf0/0x120
? kthread_complete_and_exit+0x20/0x20
ret_from_fork+0x1f/0x30
This was partially fixed by c2e39305299f01 ("btrfs: clear extent buffer
uptodate when we fail to write it"), however all that fix did was keep
us from finding extent buffers after a failed writeout. It didn't keep
us from continuing to use a buffer that we already had found.
In this case we're searching the commit root to cache the block group,
so we can start committing the transaction and switch the commit root
and then start writing. After the switch we can look up an extent
buffer that hasn't been written yet and start processing that block
group. Then we fail to write that block out and clear Uptodate on the
page, and then we start spewing these errors.
Normally we're protected by the tree lock to a certain degree here. If
we read a block we have that block read locked, and we block the writer
from locking the block before we submit it for the write. However this
isn't necessarily fool proof because the read could happen before we do
the submit_bio and after we locked and unlocked the extent buffer.
Also in this particular case we have path->skip_locking set, so that
won't save us here. We'll simply get a block that was valid when we
read it, but became invalid while we were using it.
What we really want is to catch the case where we've "read" a block but
it's not marked Uptodate. On read we ClearPageError(), so if we're
!Uptodate and !Error we know we didn't do the right thing for reading
the page.
Fix this by checking !Uptodate && !Error, this way we will not complain
if our buffer gets invalidated while we're using it, and we'll maintain
the spirit of the check which is to make sure we have a fully in-cache
block while we're messing with it.
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-18 23:17:39 +08:00
|
|
|
error = btrfs_subpage_test_error(fs_info, page, eb->start, eb->len);
|
|
|
|
WARN_ON(!uptodate && !error);
|
2021-03-25 15:14:42 +08:00
|
|
|
} else {
|
btrfs: do not WARN_ON() if we have PageError set
Whenever we do any extent buffer operations we call
assert_eb_page_uptodate() to complain loudly if we're operating on an
non-uptodate page. Our overnight tests caught this warning earlier this
week
WARNING: CPU: 1 PID: 553508 at fs/btrfs/extent_io.c:6849 assert_eb_page_uptodate+0x3f/0x50
CPU: 1 PID: 553508 Comm: kworker/u4:13 Tainted: G W 5.17.0-rc3+ #564
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014
Workqueue: btrfs-cache btrfs_work_helper
RIP: 0010:assert_eb_page_uptodate+0x3f/0x50
RSP: 0018:ffffa961440a7c68 EFLAGS: 00010246
RAX: 0017ffffc0002112 RBX: ffffe6e74453f9c0 RCX: 0000000000001000
RDX: ffffe6e74467c887 RSI: ffffe6e74453f9c0 RDI: ffff8d4c5efc2fc0
RBP: 0000000000000d56 R08: ffff8d4d4a224000 R09: 0000000000000000
R10: 00015817fa9d1ef0 R11: 000000000000000c R12: 00000000000007b1
R13: ffff8d4c5efc2fc0 R14: 0000000001500000 R15: 0000000001cb1000
FS: 0000000000000000(0000) GS:ffff8d4dbbd00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ff31d3448d8 CR3: 0000000118be8004 CR4: 0000000000370ee0
Call Trace:
extent_buffer_test_bit+0x3f/0x70
free_space_test_bit+0xa6/0xc0
load_free_space_tree+0x1f6/0x470
caching_thread+0x454/0x630
? rcu_read_lock_sched_held+0x12/0x60
? rcu_read_lock_sched_held+0x12/0x60
? rcu_read_lock_sched_held+0x12/0x60
? lock_release+0x1f0/0x2d0
btrfs_work_helper+0xf2/0x3e0
? lock_release+0x1f0/0x2d0
? finish_task_switch.isra.0+0xf9/0x3a0
process_one_work+0x26d/0x580
? process_one_work+0x580/0x580
worker_thread+0x55/0x3b0
? process_one_work+0x580/0x580
kthread+0xf0/0x120
? kthread_complete_and_exit+0x20/0x20
ret_from_fork+0x1f/0x30
This was partially fixed by c2e39305299f01 ("btrfs: clear extent buffer
uptodate when we fail to write it"), however all that fix did was keep
us from finding extent buffers after a failed writeout. It didn't keep
us from continuing to use a buffer that we already had found.
In this case we're searching the commit root to cache the block group,
so we can start committing the transaction and switch the commit root
and then start writing. After the switch we can look up an extent
buffer that hasn't been written yet and start processing that block
group. Then we fail to write that block out and clear Uptodate on the
page, and then we start spewing these errors.
Normally we're protected by the tree lock to a certain degree here. If
we read a block we have that block read locked, and we block the writer
from locking the block before we submit it for the write. However this
isn't necessarily fool proof because the read could happen before we do
the submit_bio and after we locked and unlocked the extent buffer.
Also in this particular case we have path->skip_locking set, so that
won't save us here. We'll simply get a block that was valid when we
read it, but became invalid while we were using it.
What we really want is to catch the case where we've "read" a block but
it's not marked Uptodate. On read we ClearPageError(), so if we're
!Uptodate and !Error we know we didn't do the right thing for reading
the page.
Fix this by checking !Uptodate && !Error, this way we will not complain
if our buffer gets invalidated while we're using it, and we'll maintain
the spirit of the check which is to make sure we have a fully in-cache
block while we're messing with it.
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-18 23:17:39 +08:00
|
|
|
WARN_ON(!PageUptodate(page) && !PageError(page));
|
2021-03-25 15:14:42 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb,
|
2016-11-10 00:43:38 +08:00
|
|
|
const void *srcv)
|
|
|
|
{
|
|
|
|
char *kaddr;
|
|
|
|
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, eb->pages[0]);
|
2020-09-22 04:07:14 +08:00
|
|
|
kaddr = page_address(eb->pages[0]) +
|
|
|
|
get_eb_offset_in_page(eb, offsetof(struct btrfs_header,
|
|
|
|
chunk_tree_uuid));
|
|
|
|
memcpy(kaddr, srcv, BTRFS_FSID_SIZE);
|
2016-11-10 00:43:38 +08:00
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *srcv)
|
2016-11-10 00:43:38 +08:00
|
|
|
{
|
|
|
|
char *kaddr;
|
|
|
|
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, eb->pages[0]);
|
2020-09-22 04:07:14 +08:00
|
|
|
kaddr = page_address(eb->pages[0]) +
|
|
|
|
get_eb_offset_in_page(eb, offsetof(struct btrfs_header, fsid));
|
|
|
|
memcpy(kaddr, srcv, BTRFS_FSID_SIZE);
|
2016-11-10 00:43:38 +08:00
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
|
2008-01-25 05:13:08 +08:00
|
|
|
unsigned long start, unsigned long len)
|
|
|
|
{
|
|
|
|
size_t cur;
|
|
|
|
size_t offset;
|
|
|
|
struct page *page;
|
|
|
|
char *kaddr;
|
|
|
|
char *src = (char *)srcv;
|
2020-12-02 14:48:04 +08:00
|
|
|
unsigned long i = get_eb_page_index(start);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2021-02-04 18:21:54 +08:00
|
|
|
WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags));
|
|
|
|
|
btrfs: extent_io: do extra check for extent buffer read write functions
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19 14:35:47 +08:00
|
|
|
if (check_eb_range(eb, start, len))
|
|
|
|
return;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-12-02 14:48:04 +08:00
|
|
|
offset = get_eb_offset_in_page(eb, start);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2009-01-06 10:25:51 +08:00
|
|
|
while (len > 0) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, page);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
cur = min(len, PAGE_SIZE - offset);
|
2011-07-20 00:04:14 +08:00
|
|
|
kaddr = page_address(page);
|
2008-01-25 05:13:08 +08:00
|
|
|
memcpy(kaddr + offset, src, cur);
|
|
|
|
|
|
|
|
src += cur;
|
|
|
|
len -= cur;
|
|
|
|
offset = 0;
|
|
|
|
i++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
|
2016-11-09 01:09:03 +08:00
|
|
|
unsigned long len)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
size_t cur;
|
|
|
|
size_t offset;
|
|
|
|
struct page *page;
|
|
|
|
char *kaddr;
|
2020-12-02 14:48:04 +08:00
|
|
|
unsigned long i = get_eb_page_index(start);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
btrfs: extent_io: do extra check for extent buffer read write functions
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19 14:35:47 +08:00
|
|
|
if (check_eb_range(eb, start, len))
|
|
|
|
return;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-12-02 14:48:04 +08:00
|
|
|
offset = get_eb_offset_in_page(eb, start);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2009-01-06 10:25:51 +08:00
|
|
|
while (len > 0) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = eb->pages[i];
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, page);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
cur = min(len, PAGE_SIZE - offset);
|
2011-07-20 00:04:14 +08:00
|
|
|
kaddr = page_address(page);
|
2016-11-09 01:09:03 +08:00
|
|
|
memset(kaddr + offset, 0, cur);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
|
|
|
len -= cur;
|
|
|
|
offset = 0;
|
|
|
|
i++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void copy_extent_buffer_full(const struct extent_buffer *dst,
|
|
|
|
const struct extent_buffer *src)
|
2016-11-09 01:30:31 +08:00
|
|
|
{
|
|
|
|
int i;
|
2018-03-02 01:20:27 +08:00
|
|
|
int num_pages;
|
2016-11-09 01:30:31 +08:00
|
|
|
|
|
|
|
ASSERT(dst->len == src->len);
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (dst->fs_info->nodesize >= PAGE_SIZE) {
|
2020-12-02 14:48:04 +08:00
|
|
|
num_pages = num_extent_pages(dst);
|
|
|
|
for (i = 0; i < num_pages; i++)
|
|
|
|
copy_page(page_address(dst->pages[i]),
|
|
|
|
page_address(src->pages[i]));
|
|
|
|
} else {
|
|
|
|
size_t src_offset = get_eb_offset_in_page(src, 0);
|
|
|
|
size_t dst_offset = get_eb_offset_in_page(dst, 0);
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
ASSERT(src->fs_info->nodesize < PAGE_SIZE);
|
2020-12-02 14:48:04 +08:00
|
|
|
memcpy(page_address(dst->pages[0]) + dst_offset,
|
|
|
|
page_address(src->pages[0]) + src_offset,
|
|
|
|
src->len);
|
|
|
|
}
|
2016-11-09 01:30:31 +08:00
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void copy_extent_buffer(const struct extent_buffer *dst,
|
|
|
|
const struct extent_buffer *src,
|
2008-01-25 05:13:08 +08:00
|
|
|
unsigned long dst_offset, unsigned long src_offset,
|
|
|
|
unsigned long len)
|
|
|
|
{
|
|
|
|
u64 dst_len = dst->len;
|
|
|
|
size_t cur;
|
|
|
|
size_t offset;
|
|
|
|
struct page *page;
|
|
|
|
char *kaddr;
|
2020-12-02 14:48:04 +08:00
|
|
|
unsigned long i = get_eb_page_index(dst_offset);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
btrfs: extent_io: do extra check for extent buffer read write functions
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19 14:35:47 +08:00
|
|
|
if (check_eb_range(dst, dst_offset, len) ||
|
|
|
|
check_eb_range(src, src_offset, len))
|
|
|
|
return;
|
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
WARN_ON(src->len != dst_len);
|
|
|
|
|
2020-12-02 14:48:04 +08:00
|
|
|
offset = get_eb_offset_in_page(dst, dst_offset);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2009-01-06 10:25:51 +08:00
|
|
|
while (len > 0) {
|
2014-07-31 07:03:53 +08:00
|
|
|
page = dst->pages[i];
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(dst, page);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
cur = min(len, (unsigned long)(PAGE_SIZE - offset));
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2011-07-20 00:04:14 +08:00
|
|
|
kaddr = page_address(page);
|
2008-01-25 05:13:08 +08:00
|
|
|
read_extent_buffer(src, kaddr + offset, src_offset, cur);
|
|
|
|
|
|
|
|
src_offset += cur;
|
|
|
|
len -= cur;
|
|
|
|
offset = 0;
|
|
|
|
i++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-09-30 11:50:30 +08:00
|
|
|
/*
|
|
|
|
* eb_bitmap_offset() - calculate the page and offset of the byte containing the
|
|
|
|
* given bit number
|
|
|
|
* @eb: the extent buffer
|
|
|
|
* @start: offset of the bitmap item in the extent buffer
|
|
|
|
* @nr: bit number
|
|
|
|
* @page_index: return index of the page in the extent buffer that contains the
|
|
|
|
* given bit number
|
|
|
|
* @page_offset: return offset into the page given by page_index
|
|
|
|
*
|
|
|
|
* This helper hides the ugliness of finding the byte in an extent buffer which
|
|
|
|
* contains a given bit.
|
|
|
|
*/
|
2020-04-29 09:04:10 +08:00
|
|
|
static inline void eb_bitmap_offset(const struct extent_buffer *eb,
|
2015-09-30 11:50:30 +08:00
|
|
|
unsigned long start, unsigned long nr,
|
|
|
|
unsigned long *page_index,
|
|
|
|
size_t *page_offset)
|
|
|
|
{
|
|
|
|
size_t byte_offset = BIT_BYTE(nr);
|
|
|
|
size_t offset;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The byte we want is the offset of the extent buffer + the offset of
|
|
|
|
* the bitmap item in the extent buffer + the offset of the byte in the
|
|
|
|
* bitmap item.
|
|
|
|
*/
|
2020-12-02 14:48:04 +08:00
|
|
|
offset = start + offset_in_page(eb->start) + byte_offset;
|
2015-09-30 11:50:30 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
*page_index = offset >> PAGE_SHIFT;
|
2018-12-05 22:23:03 +08:00
|
|
|
*page_offset = offset_in_page(offset);
|
2015-09-30 11:50:30 +08:00
|
|
|
}
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
|
|
|
* Determine whether a bit in a bitmap item is set.
|
|
|
|
*
|
|
|
|
* @eb: the extent buffer
|
|
|
|
* @start: offset of the bitmap item in the extent buffer
|
|
|
|
* @nr: bit number to test
|
2015-09-30 11:50:30 +08:00
|
|
|
*/
|
2020-04-29 09:04:10 +08:00
|
|
|
int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
|
2015-09-30 11:50:30 +08:00
|
|
|
unsigned long nr)
|
|
|
|
{
|
2016-09-23 08:24:20 +08:00
|
|
|
u8 *kaddr;
|
2015-09-30 11:50:30 +08:00
|
|
|
struct page *page;
|
|
|
|
unsigned long i;
|
|
|
|
size_t offset;
|
|
|
|
|
|
|
|
eb_bitmap_offset(eb, start, nr, &i, &offset);
|
|
|
|
page = eb->pages[i];
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, page);
|
2015-09-30 11:50:30 +08:00
|
|
|
kaddr = page_address(page);
|
|
|
|
return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
|
|
|
|
}
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
|
|
|
* Set an area of a bitmap to 1.
|
|
|
|
*
|
|
|
|
* @eb: the extent buffer
|
|
|
|
* @start: offset of the bitmap item in the extent buffer
|
|
|
|
* @pos: bit number of the first bit
|
|
|
|
* @len: number of bits to set
|
2015-09-30 11:50:30 +08:00
|
|
|
*/
|
2020-04-29 09:04:10 +08:00
|
|
|
void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long start,
|
2015-09-30 11:50:30 +08:00
|
|
|
unsigned long pos, unsigned long len)
|
|
|
|
{
|
2016-09-23 08:24:20 +08:00
|
|
|
u8 *kaddr;
|
2015-09-30 11:50:30 +08:00
|
|
|
struct page *page;
|
|
|
|
unsigned long i;
|
|
|
|
size_t offset;
|
|
|
|
const unsigned int size = pos + len;
|
|
|
|
int bits_to_set = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
|
2016-09-23 08:24:20 +08:00
|
|
|
u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
|
2015-09-30 11:50:30 +08:00
|
|
|
|
|
|
|
eb_bitmap_offset(eb, start, pos, &i, &offset);
|
|
|
|
page = eb->pages[i];
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, page);
|
2015-09-30 11:50:30 +08:00
|
|
|
kaddr = page_address(page);
|
|
|
|
|
|
|
|
while (len >= bits_to_set) {
|
|
|
|
kaddr[offset] |= mask_to_set;
|
|
|
|
len -= bits_to_set;
|
|
|
|
bits_to_set = BITS_PER_BYTE;
|
2016-10-12 16:33:21 +08:00
|
|
|
mask_to_set = ~0;
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
if (++offset >= PAGE_SIZE && len > 0) {
|
2015-09-30 11:50:30 +08:00
|
|
|
offset = 0;
|
|
|
|
page = eb->pages[++i];
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, page);
|
2015-09-30 11:50:30 +08:00
|
|
|
kaddr = page_address(page);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (len) {
|
|
|
|
mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
|
|
|
|
kaddr[offset] |= mask_to_set;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
|
|
|
* Clear an area of a bitmap.
|
|
|
|
*
|
|
|
|
* @eb: the extent buffer
|
|
|
|
* @start: offset of the bitmap item in the extent buffer
|
|
|
|
* @pos: bit number of the first bit
|
|
|
|
* @len: number of bits to clear
|
2015-09-30 11:50:30 +08:00
|
|
|
*/
|
2020-04-29 09:04:10 +08:00
|
|
|
void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
|
|
|
|
unsigned long start, unsigned long pos,
|
|
|
|
unsigned long len)
|
2015-09-30 11:50:30 +08:00
|
|
|
{
|
2016-09-23 08:24:20 +08:00
|
|
|
u8 *kaddr;
|
2015-09-30 11:50:30 +08:00
|
|
|
struct page *page;
|
|
|
|
unsigned long i;
|
|
|
|
size_t offset;
|
|
|
|
const unsigned int size = pos + len;
|
|
|
|
int bits_to_clear = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
|
2016-09-23 08:24:20 +08:00
|
|
|
u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
|
2015-09-30 11:50:30 +08:00
|
|
|
|
|
|
|
eb_bitmap_offset(eb, start, pos, &i, &offset);
|
|
|
|
page = eb->pages[i];
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, page);
|
2015-09-30 11:50:30 +08:00
|
|
|
kaddr = page_address(page);
|
|
|
|
|
|
|
|
while (len >= bits_to_clear) {
|
|
|
|
kaddr[offset] &= ~mask_to_clear;
|
|
|
|
len -= bits_to_clear;
|
|
|
|
bits_to_clear = BITS_PER_BYTE;
|
2016-10-12 16:33:21 +08:00
|
|
|
mask_to_clear = ~0;
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
if (++offset >= PAGE_SIZE && len > 0) {
|
2015-09-30 11:50:30 +08:00
|
|
|
offset = 0;
|
|
|
|
page = eb->pages[++i];
|
2021-03-25 15:14:42 +08:00
|
|
|
assert_eb_page_uptodate(eb, page);
|
2015-09-30 11:50:30 +08:00
|
|
|
kaddr = page_address(page);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (len) {
|
|
|
|
mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
|
|
|
|
kaddr[offset] &= ~mask_to_clear;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-04-12 05:52:52 +08:00
|
|
|
static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len)
|
|
|
|
{
|
|
|
|
unsigned long distance = (src > dst) ? src - dst : dst - src;
|
|
|
|
return distance < len;
|
|
|
|
}
|
|
|
|
|
2008-01-25 05:13:08 +08:00
|
|
|
static void copy_pages(struct page *dst_page, struct page *src_page,
|
|
|
|
unsigned long dst_off, unsigned long src_off,
|
|
|
|
unsigned long len)
|
|
|
|
{
|
2011-07-20 00:04:14 +08:00
|
|
|
char *dst_kaddr = page_address(dst_page);
|
2008-01-25 05:13:08 +08:00
|
|
|
char *src_kaddr;
|
2010-08-07 01:21:20 +08:00
|
|
|
int must_memmove = 0;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2011-04-12 05:52:52 +08:00
|
|
|
if (dst_page != src_page) {
|
2011-07-20 00:04:14 +08:00
|
|
|
src_kaddr = page_address(src_page);
|
2011-04-12 05:52:52 +08:00
|
|
|
} else {
|
2008-01-25 05:13:08 +08:00
|
|
|
src_kaddr = dst_kaddr;
|
2010-08-07 01:21:20 +08:00
|
|
|
if (areas_overlap(src_off, dst_off, len))
|
|
|
|
must_memmove = 1;
|
2011-04-12 05:52:52 +08:00
|
|
|
}
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2010-08-07 01:21:20 +08:00
|
|
|
if (must_memmove)
|
|
|
|
memmove(dst_kaddr + dst_off, src_kaddr + src_off, len);
|
|
|
|
else
|
|
|
|
memcpy(dst_kaddr + dst_off, src_kaddr + src_off, len);
|
2008-01-25 05:13:08 +08:00
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void memcpy_extent_buffer(const struct extent_buffer *dst,
|
|
|
|
unsigned long dst_offset, unsigned long src_offset,
|
|
|
|
unsigned long len)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
size_t cur;
|
|
|
|
size_t dst_off_in_page;
|
|
|
|
size_t src_off_in_page;
|
|
|
|
unsigned long dst_i;
|
|
|
|
unsigned long src_i;
|
|
|
|
|
btrfs: extent_io: do extra check for extent buffer read write functions
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19 14:35:47 +08:00
|
|
|
if (check_eb_range(dst, dst_offset, len) ||
|
|
|
|
check_eb_range(dst, src_offset, len))
|
|
|
|
return;
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2009-01-06 10:25:51 +08:00
|
|
|
while (len > 0) {
|
2020-12-02 14:48:04 +08:00
|
|
|
dst_off_in_page = get_eb_offset_in_page(dst, dst_offset);
|
|
|
|
src_off_in_page = get_eb_offset_in_page(dst, src_offset);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-12-02 14:48:04 +08:00
|
|
|
dst_i = get_eb_page_index(dst_offset);
|
|
|
|
src_i = get_eb_page_index(src_offset);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
cur = min(len, (unsigned long)(PAGE_SIZE -
|
2008-01-25 05:13:08 +08:00
|
|
|
src_off_in_page));
|
|
|
|
cur = min_t(unsigned long, cur,
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
(unsigned long)(PAGE_SIZE - dst_off_in_page));
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2014-07-31 07:03:53 +08:00
|
|
|
copy_pages(dst->pages[dst_i], dst->pages[src_i],
|
2008-01-25 05:13:08 +08:00
|
|
|
dst_off_in_page, src_off_in_page, cur);
|
|
|
|
|
|
|
|
src_offset += cur;
|
|
|
|
dst_offset += cur;
|
|
|
|
len -= cur;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-04-29 09:04:10 +08:00
|
|
|
void memmove_extent_buffer(const struct extent_buffer *dst,
|
|
|
|
unsigned long dst_offset, unsigned long src_offset,
|
|
|
|
unsigned long len)
|
2008-01-25 05:13:08 +08:00
|
|
|
{
|
|
|
|
size_t cur;
|
|
|
|
size_t dst_off_in_page;
|
|
|
|
size_t src_off_in_page;
|
|
|
|
unsigned long dst_end = dst_offset + len - 1;
|
|
|
|
unsigned long src_end = src_offset + len - 1;
|
|
|
|
unsigned long dst_i;
|
|
|
|
unsigned long src_i;
|
|
|
|
|
btrfs: extent_io: do extra check for extent buffer read write functions
Although we have start, len check for extent buffer reader/write (e.g.
read_extent_buffer()), these checks have limitations:
- No overflow check
Values like start = 1024 len = -1024 can still pass the basic
(start + len) > eb->len check.
- Checks are not consistent
For read_extent_buffer() we only check (start + len) against eb->len.
While for memcmp_extent_buffer() we also check start against eb->len.
- Different error reporting mechanism
We use WARN() in read_extent_buffer() but BUG() in
memcpy_extent_buffer().
- Still modify memory if the request is obviously wrong
In read_extent_buffer() even we find (start + len) > eb->len, we still
call memset(dst, 0, len), which can easily cause memory access error
if start + len overflows.
To address above problems, this patch creates a new common function to
check such access, check_eb_range().
- Add overflow check
This function checks start, start + len against eb->len and overflow
check.
- Unified checks
- Unified error reports
Will call WARN() if CONFIG_BTRFS_DEBUG is configured.
And also do btrfs_warn() message for non-debug build.
- Exit ASAP if check fails
No more possible memory corruption.
- Add extra comment for @start @len used in those functions as it's
sometimes confused with the logical addressing instead of a range
inside the eb space
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202817
[ Inspired by above report, the report itself is already addressed ]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ use check_add_overflow ]
Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-19 14:35:47 +08:00
|
|
|
if (check_eb_range(dst, dst_offset, len) ||
|
|
|
|
check_eb_range(dst, src_offset, len))
|
|
|
|
return;
|
2010-08-07 01:21:20 +08:00
|
|
|
if (dst_offset < src_offset) {
|
2008-01-25 05:13:08 +08:00
|
|
|
memcpy_extent_buffer(dst, dst_offset, src_offset, len);
|
|
|
|
return;
|
|
|
|
}
|
2009-01-06 10:25:51 +08:00
|
|
|
while (len > 0) {
|
2020-12-02 14:48:04 +08:00
|
|
|
dst_i = get_eb_page_index(dst_end);
|
|
|
|
src_i = get_eb_page_index(src_end);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
2020-12-02 14:48:04 +08:00
|
|
|
dst_off_in_page = get_eb_offset_in_page(dst, dst_end);
|
|
|
|
src_off_in_page = get_eb_offset_in_page(dst, src_end);
|
2008-01-25 05:13:08 +08:00
|
|
|
|
|
|
|
cur = min_t(unsigned long, len, src_off_in_page + 1);
|
|
|
|
cur = min(cur, dst_off_in_page + 1);
|
2014-07-31 07:03:53 +08:00
|
|
|
copy_pages(dst->pages[dst_i], dst->pages[src_i],
|
2008-01-25 05:13:08 +08:00
|
|
|
dst_off_in_page - cur + 1,
|
|
|
|
src_off_in_page - cur + 1, cur);
|
|
|
|
|
|
|
|
dst_end -= cur;
|
|
|
|
src_end -= cur;
|
|
|
|
len -= cur;
|
|
|
|
}
|
|
|
|
}
|
2008-07-22 23:18:07 +08:00
|
|
|
|
2022-07-15 19:59:31 +08:00
|
|
|
#define GANG_LOOKUP_SIZE 16
|
2021-01-26 16:33:56 +08:00
|
|
|
static struct extent_buffer *get_next_extent_buffer(
|
|
|
|
struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
|
|
|
|
{
|
2022-07-15 19:59:31 +08:00
|
|
|
struct extent_buffer *gang[GANG_LOOKUP_SIZE];
|
|
|
|
struct extent_buffer *found = NULL;
|
2021-01-26 16:33:56 +08:00
|
|
|
u64 page_start = page_offset(page);
|
2022-07-15 19:59:31 +08:00
|
|
|
u64 cur = page_start;
|
2021-01-26 16:33:56 +08:00
|
|
|
|
|
|
|
ASSERT(in_range(bytenr, page_start, PAGE_SIZE));
|
|
|
|
lockdep_assert_held(&fs_info->buffer_lock);
|
|
|
|
|
2022-07-15 19:59:31 +08:00
|
|
|
while (cur < page_start + PAGE_SIZE) {
|
|
|
|
int ret;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
ret = radix_tree_gang_lookup(&fs_info->buffer_radix,
|
|
|
|
(void **)gang, cur >> fs_info->sectorsize_bits,
|
|
|
|
min_t(unsigned int, GANG_LOOKUP_SIZE,
|
|
|
|
PAGE_SIZE / fs_info->nodesize));
|
|
|
|
if (ret == 0)
|
|
|
|
goto out;
|
|
|
|
for (i = 0; i < ret; i++) {
|
|
|
|
/* Already beyond page end */
|
|
|
|
if (gang[i]->start >= page_start + PAGE_SIZE)
|
|
|
|
goto out;
|
|
|
|
/* Found one */
|
|
|
|
if (gang[i]->start >= bytenr) {
|
|
|
|
found = gang[i];
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
cur = gang[ret - 1]->start + gang[ret - 1]->len;
|
2021-01-26 16:33:56 +08:00
|
|
|
}
|
2022-07-15 19:59:31 +08:00
|
|
|
out:
|
|
|
|
return found;
|
2021-01-26 16:33:56 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int try_release_subpage_extent_buffer(struct page *page)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
|
|
|
|
u64 cur = page_offset(page);
|
|
|
|
const u64 end = page_offset(page) + PAGE_SIZE;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
while (cur < end) {
|
|
|
|
struct extent_buffer *eb = NULL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Unlike try_release_extent_buffer() which uses page->private
|
|
|
|
* to grab buffer, for subpage case we rely on radix tree, thus
|
|
|
|
* we need to ensure radix tree consistency.
|
|
|
|
*
|
|
|
|
* We also want an atomic snapshot of the radix tree, thus go
|
|
|
|
* with spinlock rather than RCU.
|
|
|
|
*/
|
|
|
|
spin_lock(&fs_info->buffer_lock);
|
|
|
|
eb = get_next_extent_buffer(fs_info, page, cur);
|
|
|
|
if (!eb) {
|
|
|
|
/* No more eb in the page range after or at cur */
|
|
|
|
spin_unlock(&fs_info->buffer_lock);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
cur = eb->start + eb->len;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The same as try_release_extent_buffer(), to ensure the eb
|
|
|
|
* won't disappear out from under us.
|
|
|
|
*/
|
|
|
|
spin_lock(&eb->refs_lock);
|
|
|
|
if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
|
|
|
|
spin_unlock(&eb->refs_lock);
|
|
|
|
spin_unlock(&fs_info->buffer_lock);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
spin_unlock(&fs_info->buffer_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If tree ref isn't set then we know the ref on this eb is a
|
|
|
|
* real ref, so just return, this eb will likely be freed soon
|
|
|
|
* anyway.
|
|
|
|
*/
|
|
|
|
if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
|
|
|
|
spin_unlock(&eb->refs_lock);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Here we don't care about the return value, we will always
|
|
|
|
* check the page private at the end. And
|
|
|
|
* release_extent_buffer() will release the refs_lock.
|
|
|
|
*/
|
|
|
|
release_extent_buffer(eb);
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Finally to check if we have cleared page private, as if we have
|
|
|
|
* released all ebs in the page, the page private should be cleared now.
|
|
|
|
*/
|
|
|
|
spin_lock(&page->mapping->private_lock);
|
|
|
|
if (!PagePrivate(page))
|
|
|
|
ret = 1;
|
|
|
|
else
|
|
|
|
ret = 0;
|
|
|
|
spin_unlock(&page->mapping->private_lock);
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2013-04-26 22:56:29 +08:00
|
|
|
int try_release_extent_buffer(struct page *page)
|
2010-10-27 08:57:29 +08:00
|
|
|
{
|
2008-07-22 23:18:07 +08:00
|
|
|
struct extent_buffer *eb;
|
|
|
|
|
btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine
The reason why we only support 64K page size for subpage is, for 64K
page size we can ensure no matter what the nodesize is, we can fit it
into one page.
When other page size come, especially like 16K, the limitation is a bit
limiting.
To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the
non-subpage routine. By this, we can allow 4K sectorsize on 16K page
size.
Although this introduces another smaller limitation, the metadata can
not cross page boundary, which is already met by most recent mkfs.
Another small improvement is, we can avoid the overhead for metadata if
nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and
16K page size/node size, we don't need to allocate extra memory for the
metadata pages.
Please note that, this patch will not yet enable other page size support
yet.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-13 13:22:09 +08:00
|
|
|
if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
|
2021-01-26 16:33:56 +08:00
|
|
|
return try_release_subpage_extent_buffer(page);
|
|
|
|
|
2012-03-10 05:01:49 +08:00
|
|
|
/*
|
2021-01-26 16:33:56 +08:00
|
|
|
* We need to make sure nobody is changing page->private, as we rely on
|
|
|
|
* page->private as the pointer to extent buffer.
|
2012-03-10 05:01:49 +08:00
|
|
|
*/
|
|
|
|
spin_lock(&page->mapping->private_lock);
|
|
|
|
if (!PagePrivate(page)) {
|
|
|
|
spin_unlock(&page->mapping->private_lock);
|
2012-03-08 05:20:05 +08:00
|
|
|
return 1;
|
2010-11-22 11:27:44 +08:00
|
|
|
}
|
2008-07-22 23:18:07 +08:00
|
|
|
|
2012-03-10 05:01:49 +08:00
|
|
|
eb = (struct extent_buffer *)page->private;
|
|
|
|
BUG_ON(!eb);
|
2010-10-27 08:57:29 +08:00
|
|
|
|
|
|
|
/*
|
2012-03-10 05:01:49 +08:00
|
|
|
* This is a little awful but should be ok, we need to make sure that
|
|
|
|
* the eb doesn't disappear out from under us while we're looking at
|
|
|
|
* this page.
|
2010-10-27 08:57:29 +08:00
|
|
|
*/
|
2012-03-10 05:01:49 +08:00
|
|
|
spin_lock(&eb->refs_lock);
|
2012-03-13 21:38:00 +08:00
|
|
|
if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
|
2012-03-10 05:01:49 +08:00
|
|
|
spin_unlock(&eb->refs_lock);
|
|
|
|
spin_unlock(&page->mapping->private_lock);
|
|
|
|
return 0;
|
2009-03-13 23:00:37 +08:00
|
|
|
}
|
2012-03-10 05:01:49 +08:00
|
|
|
spin_unlock(&page->mapping->private_lock);
|
2010-10-27 08:57:29 +08:00
|
|
|
|
2010-10-27 08:57:29 +08:00
|
|
|
/*
|
2012-03-10 05:01:49 +08:00
|
|
|
* If tree ref isn't set then we know the ref on this eb is a real ref,
|
|
|
|
* so just return, this page will likely be freed soon anyway.
|
2010-10-27 08:57:29 +08:00
|
|
|
*/
|
2012-03-10 05:01:49 +08:00
|
|
|
if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
|
|
|
|
spin_unlock(&eb->refs_lock);
|
|
|
|
return 0;
|
2009-03-13 23:00:37 +08:00
|
|
|
}
|
2010-10-27 08:57:29 +08:00
|
|
|
|
2013-04-26 22:56:29 +08:00
|
|
|
return release_extent_buffer(eb);
|
2008-07-22 23:18:07 +08:00
|
|
|
}
|
2020-11-05 23:45:09 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* btrfs_readahead_tree_block - attempt to readahead a child block
|
|
|
|
* @fs_info: the fs_info
|
|
|
|
* @bytenr: bytenr to read
|
2020-11-05 23:45:20 +08:00
|
|
|
* @owner_root: objectid of the root that owns this eb
|
2020-11-05 23:45:09 +08:00
|
|
|
* @gen: generation for the uptodate check, can be 0
|
2020-11-05 23:45:20 +08:00
|
|
|
* @level: level for the eb
|
2020-11-05 23:45:09 +08:00
|
|
|
*
|
|
|
|
* Attempt to readahead a tree block at @bytenr. If @gen is 0 then we do a
|
|
|
|
* normal uptodate check of the eb, without checking the generation. If we have
|
|
|
|
* to read the block we will not block on anything.
|
|
|
|
*/
|
|
|
|
void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
|
2020-11-05 23:45:20 +08:00
|
|
|
u64 bytenr, u64 owner_root, u64 gen, int level)
|
2020-11-05 23:45:09 +08:00
|
|
|
{
|
btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-14 13:32:51 +08:00
|
|
|
struct btrfs_tree_parent_check check = {
|
|
|
|
.has_first_key = 0,
|
|
|
|
.level = level,
|
|
|
|
.transid = gen
|
|
|
|
};
|
2020-11-05 23:45:09 +08:00
|
|
|
struct extent_buffer *eb;
|
|
|
|
int ret;
|
|
|
|
|
2020-11-05 23:45:20 +08:00
|
|
|
eb = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level);
|
2020-11-05 23:45:09 +08:00
|
|
|
if (IS_ERR(eb))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (btrfs_buffer_uptodate(eb, gen, 1)) {
|
|
|
|
free_extent_buffer(eb);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-14 13:32:51 +08:00
|
|
|
ret = read_extent_buffer_pages(eb, WAIT_NONE, 0, &check);
|
2020-11-05 23:45:09 +08:00
|
|
|
if (ret < 0)
|
|
|
|
free_extent_buffer_stale(eb);
|
|
|
|
else
|
|
|
|
free_extent_buffer(eb);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* btrfs_readahead_node_child - readahead a node's child block
|
|
|
|
* @node: parent node we're reading from
|
|
|
|
* @slot: slot in the parent node for the child we want to read
|
|
|
|
*
|
|
|
|
* A helper for btrfs_readahead_tree_block, we simply read the bytenr pointed at
|
|
|
|
* the slot in the node provided.
|
|
|
|
*/
|
|
|
|
void btrfs_readahead_node_child(struct extent_buffer *node, int slot)
|
|
|
|
{
|
|
|
|
btrfs_readahead_tree_block(node->fs_info,
|
|
|
|
btrfs_node_blockptr(node, slot),
|
2020-11-05 23:45:20 +08:00
|
|
|
btrfs_header_owner(node),
|
|
|
|
btrfs_node_ptr_generation(node, slot),
|
|
|
|
btrfs_header_level(node) - 1);
|
2020-11-05 23:45:09 +08:00
|
|
|
}
|