2018-04-04 01:23:33 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2009 Oracle. All rights reserved.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/sched.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2009-03-13 22:10:06 +08:00
|
|
|
#include <linux/sort.h>
|
2022-10-19 22:50:49 +08:00
|
|
|
#include "messages.h"
|
2009-03-13 22:10:06 +08:00
|
|
|
#include "ctree.h"
|
|
|
|
#include "delayed-ref.h"
|
|
|
|
#include "transaction.h"
|
2015-04-16 14:34:17 +08:00
|
|
|
#include "qgroup.h"
|
2019-06-20 03:11:58 +08:00
|
|
|
#include "space-info.h"
|
2021-03-11 22:31:07 +08:00
|
|
|
#include "tree-mod-log.h"
|
2022-10-19 22:50:53 +08:00
|
|
|
#include "fs.h"
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2012-11-21 10:21:28 +08:00
|
|
|
struct kmem_cache *btrfs_delayed_ref_head_cachep;
|
2024-04-13 05:16:40 +08:00
|
|
|
struct kmem_cache *btrfs_delayed_ref_node_cachep;
|
2012-11-21 10:21:28 +08:00
|
|
|
struct kmem_cache *btrfs_delayed_extent_op_cachep;
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
|
|
|
* delayed back reference update tracking. For subvolume trees
|
|
|
|
* we queue up extent allocations and backref maintenance for
|
|
|
|
* delayed processing. This avoids deep call chains where we
|
|
|
|
* add extents in the middle of btrfs_search_slot, and it allows
|
|
|
|
* us to buffer up frequently modified backrefs in an rb tree instead
|
|
|
|
* of hammering updates on the extent allocation tree.
|
|
|
|
*/
|
|
|
|
|
2019-06-20 03:11:58 +08:00
|
|
|
bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
|
|
|
|
struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
|
|
|
|
bool ret = false;
|
|
|
|
u64 reserved;
|
|
|
|
|
|
|
|
spin_lock(&global_rsv->lock);
|
|
|
|
reserved = global_rsv->reserved;
|
|
|
|
spin_unlock(&global_rsv->lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Since the global reserve is just kind of magic we don't really want
|
|
|
|
* to rely on it to save our bacon, so if our size is more than the
|
|
|
|
* delayed_refs_rsv and the global rsv then it's time to think about
|
|
|
|
* bailing.
|
|
|
|
*/
|
|
|
|
spin_lock(&delayed_refs_rsv->lock);
|
|
|
|
reserved += delayed_refs_rsv->reserved;
|
|
|
|
if (delayed_refs_rsv->size >= reserved)
|
|
|
|
ret = true;
|
|
|
|
spin_unlock(&delayed_refs_rsv->lock);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
|
|
|
* Release a ref head's reservation.
|
2021-01-22 17:57:55 +08:00
|
|
|
*
|
|
|
|
* @fs_info: the filesystem
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
* @nr_refs: number of delayed refs to drop
|
|
|
|
* @nr_csums: number of csum items to drop
|
2019-06-20 03:11:58 +08:00
|
|
|
*
|
2022-10-27 20:21:42 +08:00
|
|
|
* Drops the delayed ref head's count from the delayed refs rsv and free any
|
|
|
|
* excess reservation we had.
|
2019-06-20 03:11:58 +08:00
|
|
|
*/
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr_refs, int nr_csums)
|
2019-06-20 03:11:58 +08:00
|
|
|
{
|
|
|
|
struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
u64 num_bytes;
|
2023-09-09 01:20:36 +08:00
|
|
|
u64 released;
|
2019-06-20 03:11:58 +08:00
|
|
|
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, nr_refs);
|
|
|
|
num_bytes += btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
|
|
|
|
|
2020-03-10 16:59:31 +08:00
|
|
|
released = btrfs_block_rsv_release(fs_info, block_rsv, num_bytes, NULL);
|
2019-06-20 03:11:58 +08:00
|
|
|
if (released)
|
|
|
|
trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
|
|
|
|
0, released, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2022-10-27 20:21:42 +08:00
|
|
|
* Adjust the size of the delayed refs rsv.
|
2019-06-20 03:11:58 +08:00
|
|
|
*
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
* This is to be called anytime we may have adjusted trans->delayed_ref_updates
|
|
|
|
* or trans->delayed_ref_csum_deletions, it'll calculate the additional size and
|
|
|
|
* add it to the delayed_refs_rsv.
|
2019-06-20 03:11:58 +08:00
|
|
|
*/
|
|
|
|
void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
|
|
|
|
{
|
|
|
|
struct btrfs_fs_info *fs_info = trans->fs_info;
|
|
|
|
struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
|
btrfs: always reserve space for delayed refs when starting transaction
When starting a transaction (or joining an existing one with
btrfs_start_transaction()), we reserve space for the number of items we
want to insert in a btree, but we don't do it for the delayed refs we
will generate while using the transaction to modify (COW) extent buffers
in a btree or allocate new extent buffers. Basically how it works:
1) When we start a transaction we reserve space for the number of items
the caller wants to be inserted/modified/deleted in a btree. This space
goes to the transaction block reserve;
2) If the delayed refs block reserve is not full, its size is greater
than the amount of its reserved space, and the flush method is
BTRFS_RESERVE_FLUSH_ALL, then we attempt to reserve more space for
it corresponding to the number of items the caller wants to
insert/modify/delete in a btree;
3) The size of the delayed refs block reserve is increased when a task
creates delayed refs after COWing an extent buffer, allocating a new
one or deleting (freeing) an extent buffer. This happens after the
the task started or joined a transaction, whenever it calls
btrfs_update_delayed_refs_rsv();
4) The delayed refs block reserve is then refilled by anyone calling
btrfs_delayed_refs_rsv_refill(), either during unlink/truncate
operations or when someone else calls btrfs_start_transaction() with
a 0 number of items and flush method BTRFS_RESERVE_FLUSH_ALL;
5) As a task COWs or allocates extent buffers, it consumes space from the
transaction block reserve. When the task releases its transaction
handle (btrfs_end_transaction()) or it attempts to commit the
transaction, it releases any remaining space in the transaction block
reserve that it did not use, as not all space may have been used (due
to pessimistic space calculation) by calling btrfs_block_rsv_release()
which will try to add that unused space to the delayed refs block
reserve (if its current size is greater than its reserved space).
That transferred space may not be enough to completely fulfill the
delayed refs block reserve.
Plus we have some tasks that will attempt do modify as many leaves
as they can before getting -ENOSPC (and then reserving more space and
retrying), such as hole punching and extent cloning which call
btrfs_replace_file_extents(). Such tasks can generate therefore a
high number of delayed refs, for both metadata and data (we can't
know in advance how many file extent items we will find in a range
and therefore how many delayed refs for dropping references on data
extents we will generate);
6) If a transaction starts its commit before the delayed refs block
reserve is refilled, for example by the transaction kthread or by
someone who called btrfs_join_transaction() before starting the
commit, then when running delayed references if we don't have enough
reserved space in the delayed refs block reserve, we will consume
space from the global block reserve.
Now this doesn't make a lot of sense because:
1) We should reserve space for delayed references when starting the
transaction, since we have no guarantees the delayed refs block
reserve will be refilled;
2) If no refill happens then we will consume from the global block reserve
when running delayed refs during the transaction commit;
3) If we have a bunch of tasks calling btrfs_start_transaction() with a
number of items greater than zero and at the time the delayed refs
reserve is full, then we don't reserve any space at
btrfs_start_transaction() for the delayed refs that will be generated
by a task, and we can therefore end up using a lot of space from the
global reserve when running the delayed refs during a transaction
commit;
4) There are also other operations that result in bumping the size of the
delayed refs reserve, such as creating and deleting block groups, as
well as the need to update a block group item because we allocated or
freed an extent from the respective block group;
5) If we have a significant gap between the delayed refs reserve's size
and its reserved space, two very bad things may happen:
1) The reserved space of the global reserve may not be enough and we
fail the transaction commit with -ENOSPC when running delayed refs;
2) If the available space in the global reserve is enough it may result
in nearly exhausting it. If the fs has no more unallocated device
space for allocating a new block group and all the available space
in existing metadata block groups is not far from the global
reserve's size before we started the transaction commit, we may end
up in a situation where after the transaction commit we have too
little available metadata space, and any future transaction commit
will fail with -ENOSPC, because although we were able to reserve
space to start the transaction, we were not able to commit it, as
running delayed refs generates some more delayed refs (to update the
extent tree for example) - this includes not even being able to
commit a transaction that was started with the goal of unlinking a
file, removing an empty data block group or doing reclaim/balance,
so there's no way to release metadata space.
In the worst case the next time we mount the filesystem we may
also fail with -ENOSPC due to failure to commit a transaction to
cleanup orphan inodes. This later case was reported and hit by
someone running a SLE (SUSE Linux Enterprise) distribution for
example - where the fs had no more unallocated space that could be
used to allocate a new metadata block group, and the available
metadata space was about 1.5M, not enough to commit a transaction
to cleanup an orphan inode (or do relocation of data block groups
that were far from being full).
So improve on this situation by always reserving space for delayed refs
when calling start_transaction(), and if the flush method is
BTRFS_RESERVE_FLUSH_ALL, also try to refill the delayed refs block
reserve if it's not full. The space reserved for the delayed refs is added
to a local block reserve that is part of the transaction handle, and when
a task updates the delayed refs block reserve size, after creating a
delayed ref, the space is transferred from that local reserve to the
global delayed refs reserve (fs_info->delayed_refs_rsv). In case the
local reserve does not have enough space, which may happen for tasks
that generate a variable and potentially large number of delayed refs
(such as the hole punching and extent cloning cases mentioned before),
we transfer any available space and then rely on the current behaviour
of hoping some other task refills the delayed refs reserve or fallback
to the global block reserve.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:38 +08:00
|
|
|
struct btrfs_block_rsv *local_rsv = &trans->delayed_rsv;
|
2019-06-20 03:11:58 +08:00
|
|
|
u64 num_bytes;
|
btrfs: always reserve space for delayed refs when starting transaction
When starting a transaction (or joining an existing one with
btrfs_start_transaction()), we reserve space for the number of items we
want to insert in a btree, but we don't do it for the delayed refs we
will generate while using the transaction to modify (COW) extent buffers
in a btree or allocate new extent buffers. Basically how it works:
1) When we start a transaction we reserve space for the number of items
the caller wants to be inserted/modified/deleted in a btree. This space
goes to the transaction block reserve;
2) If the delayed refs block reserve is not full, its size is greater
than the amount of its reserved space, and the flush method is
BTRFS_RESERVE_FLUSH_ALL, then we attempt to reserve more space for
it corresponding to the number of items the caller wants to
insert/modify/delete in a btree;
3) The size of the delayed refs block reserve is increased when a task
creates delayed refs after COWing an extent buffer, allocating a new
one or deleting (freeing) an extent buffer. This happens after the
the task started or joined a transaction, whenever it calls
btrfs_update_delayed_refs_rsv();
4) The delayed refs block reserve is then refilled by anyone calling
btrfs_delayed_refs_rsv_refill(), either during unlink/truncate
operations or when someone else calls btrfs_start_transaction() with
a 0 number of items and flush method BTRFS_RESERVE_FLUSH_ALL;
5) As a task COWs or allocates extent buffers, it consumes space from the
transaction block reserve. When the task releases its transaction
handle (btrfs_end_transaction()) or it attempts to commit the
transaction, it releases any remaining space in the transaction block
reserve that it did not use, as not all space may have been used (due
to pessimistic space calculation) by calling btrfs_block_rsv_release()
which will try to add that unused space to the delayed refs block
reserve (if its current size is greater than its reserved space).
That transferred space may not be enough to completely fulfill the
delayed refs block reserve.
Plus we have some tasks that will attempt do modify as many leaves
as they can before getting -ENOSPC (and then reserving more space and
retrying), such as hole punching and extent cloning which call
btrfs_replace_file_extents(). Such tasks can generate therefore a
high number of delayed refs, for both metadata and data (we can't
know in advance how many file extent items we will find in a range
and therefore how many delayed refs for dropping references on data
extents we will generate);
6) If a transaction starts its commit before the delayed refs block
reserve is refilled, for example by the transaction kthread or by
someone who called btrfs_join_transaction() before starting the
commit, then when running delayed references if we don't have enough
reserved space in the delayed refs block reserve, we will consume
space from the global block reserve.
Now this doesn't make a lot of sense because:
1) We should reserve space for delayed references when starting the
transaction, since we have no guarantees the delayed refs block
reserve will be refilled;
2) If no refill happens then we will consume from the global block reserve
when running delayed refs during the transaction commit;
3) If we have a bunch of tasks calling btrfs_start_transaction() with a
number of items greater than zero and at the time the delayed refs
reserve is full, then we don't reserve any space at
btrfs_start_transaction() for the delayed refs that will be generated
by a task, and we can therefore end up using a lot of space from the
global reserve when running the delayed refs during a transaction
commit;
4) There are also other operations that result in bumping the size of the
delayed refs reserve, such as creating and deleting block groups, as
well as the need to update a block group item because we allocated or
freed an extent from the respective block group;
5) If we have a significant gap between the delayed refs reserve's size
and its reserved space, two very bad things may happen:
1) The reserved space of the global reserve may not be enough and we
fail the transaction commit with -ENOSPC when running delayed refs;
2) If the available space in the global reserve is enough it may result
in nearly exhausting it. If the fs has no more unallocated device
space for allocating a new block group and all the available space
in existing metadata block groups is not far from the global
reserve's size before we started the transaction commit, we may end
up in a situation where after the transaction commit we have too
little available metadata space, and any future transaction commit
will fail with -ENOSPC, because although we were able to reserve
space to start the transaction, we were not able to commit it, as
running delayed refs generates some more delayed refs (to update the
extent tree for example) - this includes not even being able to
commit a transaction that was started with the goal of unlinking a
file, removing an empty data block group or doing reclaim/balance,
so there's no way to release metadata space.
In the worst case the next time we mount the filesystem we may
also fail with -ENOSPC due to failure to commit a transaction to
cleanup orphan inodes. This later case was reported and hit by
someone running a SLE (SUSE Linux Enterprise) distribution for
example - where the fs had no more unallocated space that could be
used to allocate a new metadata block group, and the available
metadata space was about 1.5M, not enough to commit a transaction
to cleanup an orphan inode (or do relocation of data block groups
that were far from being full).
So improve on this situation by always reserving space for delayed refs
when calling start_transaction(), and if the flush method is
BTRFS_RESERVE_FLUSH_ALL, also try to refill the delayed refs block
reserve if it's not full. The space reserved for the delayed refs is added
to a local block reserve that is part of the transaction handle, and when
a task updates the delayed refs block reserve size, after creating a
delayed ref, the space is transferred from that local reserve to the
global delayed refs reserve (fs_info->delayed_refs_rsv). In case the
local reserve does not have enough space, which may happen for tasks
that generate a variable and potentially large number of delayed refs
(such as the hole punching and extent cloning cases mentioned before),
we transfer any available space and then rely on the current behaviour
of hoping some other task refills the delayed refs reserve or fallback
to the global block reserve.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:38 +08:00
|
|
|
u64 reserved_bytes;
|
2019-06-20 03:11:58 +08:00
|
|
|
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, trans->delayed_ref_updates);
|
|
|
|
num_bytes += btrfs_calc_delayed_ref_csum_bytes(fs_info,
|
|
|
|
trans->delayed_ref_csum_deletions);
|
2019-06-20 03:11:58 +08:00
|
|
|
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
if (num_bytes == 0)
|
|
|
|
return;
|
2021-12-03 04:34:32 +08:00
|
|
|
|
btrfs: always reserve space for delayed refs when starting transaction
When starting a transaction (or joining an existing one with
btrfs_start_transaction()), we reserve space for the number of items we
want to insert in a btree, but we don't do it for the delayed refs we
will generate while using the transaction to modify (COW) extent buffers
in a btree or allocate new extent buffers. Basically how it works:
1) When we start a transaction we reserve space for the number of items
the caller wants to be inserted/modified/deleted in a btree. This space
goes to the transaction block reserve;
2) If the delayed refs block reserve is not full, its size is greater
than the amount of its reserved space, and the flush method is
BTRFS_RESERVE_FLUSH_ALL, then we attempt to reserve more space for
it corresponding to the number of items the caller wants to
insert/modify/delete in a btree;
3) The size of the delayed refs block reserve is increased when a task
creates delayed refs after COWing an extent buffer, allocating a new
one or deleting (freeing) an extent buffer. This happens after the
the task started or joined a transaction, whenever it calls
btrfs_update_delayed_refs_rsv();
4) The delayed refs block reserve is then refilled by anyone calling
btrfs_delayed_refs_rsv_refill(), either during unlink/truncate
operations or when someone else calls btrfs_start_transaction() with
a 0 number of items and flush method BTRFS_RESERVE_FLUSH_ALL;
5) As a task COWs or allocates extent buffers, it consumes space from the
transaction block reserve. When the task releases its transaction
handle (btrfs_end_transaction()) or it attempts to commit the
transaction, it releases any remaining space in the transaction block
reserve that it did not use, as not all space may have been used (due
to pessimistic space calculation) by calling btrfs_block_rsv_release()
which will try to add that unused space to the delayed refs block
reserve (if its current size is greater than its reserved space).
That transferred space may not be enough to completely fulfill the
delayed refs block reserve.
Plus we have some tasks that will attempt do modify as many leaves
as they can before getting -ENOSPC (and then reserving more space and
retrying), such as hole punching and extent cloning which call
btrfs_replace_file_extents(). Such tasks can generate therefore a
high number of delayed refs, for both metadata and data (we can't
know in advance how many file extent items we will find in a range
and therefore how many delayed refs for dropping references on data
extents we will generate);
6) If a transaction starts its commit before the delayed refs block
reserve is refilled, for example by the transaction kthread or by
someone who called btrfs_join_transaction() before starting the
commit, then when running delayed references if we don't have enough
reserved space in the delayed refs block reserve, we will consume
space from the global block reserve.
Now this doesn't make a lot of sense because:
1) We should reserve space for delayed references when starting the
transaction, since we have no guarantees the delayed refs block
reserve will be refilled;
2) If no refill happens then we will consume from the global block reserve
when running delayed refs during the transaction commit;
3) If we have a bunch of tasks calling btrfs_start_transaction() with a
number of items greater than zero and at the time the delayed refs
reserve is full, then we don't reserve any space at
btrfs_start_transaction() for the delayed refs that will be generated
by a task, and we can therefore end up using a lot of space from the
global reserve when running the delayed refs during a transaction
commit;
4) There are also other operations that result in bumping the size of the
delayed refs reserve, such as creating and deleting block groups, as
well as the need to update a block group item because we allocated or
freed an extent from the respective block group;
5) If we have a significant gap between the delayed refs reserve's size
and its reserved space, two very bad things may happen:
1) The reserved space of the global reserve may not be enough and we
fail the transaction commit with -ENOSPC when running delayed refs;
2) If the available space in the global reserve is enough it may result
in nearly exhausting it. If the fs has no more unallocated device
space for allocating a new block group and all the available space
in existing metadata block groups is not far from the global
reserve's size before we started the transaction commit, we may end
up in a situation where after the transaction commit we have too
little available metadata space, and any future transaction commit
will fail with -ENOSPC, because although we were able to reserve
space to start the transaction, we were not able to commit it, as
running delayed refs generates some more delayed refs (to update the
extent tree for example) - this includes not even being able to
commit a transaction that was started with the goal of unlinking a
file, removing an empty data block group or doing reclaim/balance,
so there's no way to release metadata space.
In the worst case the next time we mount the filesystem we may
also fail with -ENOSPC due to failure to commit a transaction to
cleanup orphan inodes. This later case was reported and hit by
someone running a SLE (SUSE Linux Enterprise) distribution for
example - where the fs had no more unallocated space that could be
used to allocate a new metadata block group, and the available
metadata space was about 1.5M, not enough to commit a transaction
to cleanup an orphan inode (or do relocation of data block groups
that were far from being full).
So improve on this situation by always reserving space for delayed refs
when calling start_transaction(), and if the flush method is
BTRFS_RESERVE_FLUSH_ALL, also try to refill the delayed refs block
reserve if it's not full. The space reserved for the delayed refs is added
to a local block reserve that is part of the transaction handle, and when
a task updates the delayed refs block reserve size, after creating a
delayed ref, the space is transferred from that local reserve to the
global delayed refs reserve (fs_info->delayed_refs_rsv). In case the
local reserve does not have enough space, which may happen for tasks
that generate a variable and potentially large number of delayed refs
(such as the hole punching and extent cloning cases mentioned before),
we transfer any available space and then rely on the current behaviour
of hoping some other task refills the delayed refs reserve or fallback
to the global block reserve.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:38 +08:00
|
|
|
/*
|
|
|
|
* Try to take num_bytes from the transaction's local delayed reserve.
|
|
|
|
* If not possible, try to take as much as it's available. If the local
|
|
|
|
* reserve doesn't have enough reserved space, the delayed refs reserve
|
|
|
|
* will be refilled next time btrfs_delayed_refs_rsv_refill() is called
|
|
|
|
* by someone or if a transaction commit is triggered before that, the
|
|
|
|
* global block reserve will be used. We want to minimize using the
|
|
|
|
* global block reserve for cases we can account for in advance, to
|
|
|
|
* avoid exhausting it and reach -ENOSPC during a transaction commit.
|
|
|
|
*/
|
|
|
|
spin_lock(&local_rsv->lock);
|
|
|
|
reserved_bytes = min(num_bytes, local_rsv->reserved);
|
|
|
|
local_rsv->reserved -= reserved_bytes;
|
|
|
|
local_rsv->full = (local_rsv->reserved >= local_rsv->size);
|
|
|
|
spin_unlock(&local_rsv->lock);
|
|
|
|
|
2019-06-20 03:11:58 +08:00
|
|
|
spin_lock(&delayed_rsv->lock);
|
|
|
|
delayed_rsv->size += num_bytes;
|
btrfs: always reserve space for delayed refs when starting transaction
When starting a transaction (or joining an existing one with
btrfs_start_transaction()), we reserve space for the number of items we
want to insert in a btree, but we don't do it for the delayed refs we
will generate while using the transaction to modify (COW) extent buffers
in a btree or allocate new extent buffers. Basically how it works:
1) When we start a transaction we reserve space for the number of items
the caller wants to be inserted/modified/deleted in a btree. This space
goes to the transaction block reserve;
2) If the delayed refs block reserve is not full, its size is greater
than the amount of its reserved space, and the flush method is
BTRFS_RESERVE_FLUSH_ALL, then we attempt to reserve more space for
it corresponding to the number of items the caller wants to
insert/modify/delete in a btree;
3) The size of the delayed refs block reserve is increased when a task
creates delayed refs after COWing an extent buffer, allocating a new
one or deleting (freeing) an extent buffer. This happens after the
the task started or joined a transaction, whenever it calls
btrfs_update_delayed_refs_rsv();
4) The delayed refs block reserve is then refilled by anyone calling
btrfs_delayed_refs_rsv_refill(), either during unlink/truncate
operations or when someone else calls btrfs_start_transaction() with
a 0 number of items and flush method BTRFS_RESERVE_FLUSH_ALL;
5) As a task COWs or allocates extent buffers, it consumes space from the
transaction block reserve. When the task releases its transaction
handle (btrfs_end_transaction()) or it attempts to commit the
transaction, it releases any remaining space in the transaction block
reserve that it did not use, as not all space may have been used (due
to pessimistic space calculation) by calling btrfs_block_rsv_release()
which will try to add that unused space to the delayed refs block
reserve (if its current size is greater than its reserved space).
That transferred space may not be enough to completely fulfill the
delayed refs block reserve.
Plus we have some tasks that will attempt do modify as many leaves
as they can before getting -ENOSPC (and then reserving more space and
retrying), such as hole punching and extent cloning which call
btrfs_replace_file_extents(). Such tasks can generate therefore a
high number of delayed refs, for both metadata and data (we can't
know in advance how many file extent items we will find in a range
and therefore how many delayed refs for dropping references on data
extents we will generate);
6) If a transaction starts its commit before the delayed refs block
reserve is refilled, for example by the transaction kthread or by
someone who called btrfs_join_transaction() before starting the
commit, then when running delayed references if we don't have enough
reserved space in the delayed refs block reserve, we will consume
space from the global block reserve.
Now this doesn't make a lot of sense because:
1) We should reserve space for delayed references when starting the
transaction, since we have no guarantees the delayed refs block
reserve will be refilled;
2) If no refill happens then we will consume from the global block reserve
when running delayed refs during the transaction commit;
3) If we have a bunch of tasks calling btrfs_start_transaction() with a
number of items greater than zero and at the time the delayed refs
reserve is full, then we don't reserve any space at
btrfs_start_transaction() for the delayed refs that will be generated
by a task, and we can therefore end up using a lot of space from the
global reserve when running the delayed refs during a transaction
commit;
4) There are also other operations that result in bumping the size of the
delayed refs reserve, such as creating and deleting block groups, as
well as the need to update a block group item because we allocated or
freed an extent from the respective block group;
5) If we have a significant gap between the delayed refs reserve's size
and its reserved space, two very bad things may happen:
1) The reserved space of the global reserve may not be enough and we
fail the transaction commit with -ENOSPC when running delayed refs;
2) If the available space in the global reserve is enough it may result
in nearly exhausting it. If the fs has no more unallocated device
space for allocating a new block group and all the available space
in existing metadata block groups is not far from the global
reserve's size before we started the transaction commit, we may end
up in a situation where after the transaction commit we have too
little available metadata space, and any future transaction commit
will fail with -ENOSPC, because although we were able to reserve
space to start the transaction, we were not able to commit it, as
running delayed refs generates some more delayed refs (to update the
extent tree for example) - this includes not even being able to
commit a transaction that was started with the goal of unlinking a
file, removing an empty data block group or doing reclaim/balance,
so there's no way to release metadata space.
In the worst case the next time we mount the filesystem we may
also fail with -ENOSPC due to failure to commit a transaction to
cleanup orphan inodes. This later case was reported and hit by
someone running a SLE (SUSE Linux Enterprise) distribution for
example - where the fs had no more unallocated space that could be
used to allocate a new metadata block group, and the available
metadata space was about 1.5M, not enough to commit a transaction
to cleanup an orphan inode (or do relocation of data block groups
that were far from being full).
So improve on this situation by always reserving space for delayed refs
when calling start_transaction(), and if the flush method is
BTRFS_RESERVE_FLUSH_ALL, also try to refill the delayed refs block
reserve if it's not full. The space reserved for the delayed refs is added
to a local block reserve that is part of the transaction handle, and when
a task updates the delayed refs block reserve size, after creating a
delayed ref, the space is transferred from that local reserve to the
global delayed refs reserve (fs_info->delayed_refs_rsv). In case the
local reserve does not have enough space, which may happen for tasks
that generate a variable and potentially large number of delayed refs
(such as the hole punching and extent cloning cases mentioned before),
we transfer any available space and then rely on the current behaviour
of hoping some other task refills the delayed refs reserve or fallback
to the global block reserve.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:38 +08:00
|
|
|
delayed_rsv->reserved += reserved_bytes;
|
|
|
|
delayed_rsv->full = (delayed_rsv->reserved >= delayed_rsv->size);
|
2019-06-20 03:11:58 +08:00
|
|
|
spin_unlock(&delayed_rsv->lock);
|
|
|
|
trans->delayed_ref_updates = 0;
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
trans->delayed_ref_csum_deletions = 0;
|
2019-06-20 03:11:58 +08:00
|
|
|
}
|
|
|
|
|
2023-09-28 18:12:50 +08:00
|
|
|
/*
|
|
|
|
* Adjust the size of the delayed refs block reserve for 1 block group item
|
|
|
|
* insertion, used after allocating a block group.
|
|
|
|
*/
|
|
|
|
void btrfs_inc_delayed_refs_rsv_bg_inserts(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
|
|
|
|
|
|
|
|
spin_lock(&delayed_rsv->lock);
|
|
|
|
/*
|
|
|
|
* Inserting a block group item does not require changing the free space
|
|
|
|
* tree, only the extent tree or the block group tree, so this is all we
|
|
|
|
* need.
|
|
|
|
*/
|
|
|
|
delayed_rsv->size += btrfs_calc_insert_metadata_size(fs_info, 1);
|
|
|
|
delayed_rsv->full = false;
|
|
|
|
spin_unlock(&delayed_rsv->lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Adjust the size of the delayed refs block reserve to release space for 1
|
|
|
|
* block group item insertion.
|
|
|
|
*/
|
|
|
|
void btrfs_dec_delayed_refs_rsv_bg_inserts(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
|
|
|
|
const u64 num_bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
|
|
|
|
u64 released;
|
|
|
|
|
|
|
|
released = btrfs_block_rsv_release(fs_info, delayed_rsv, num_bytes, NULL);
|
|
|
|
if (released > 0)
|
|
|
|
trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
|
|
|
|
0, released, 0);
|
|
|
|
}
|
|
|
|
|
2023-09-28 18:12:49 +08:00
|
|
|
/*
|
|
|
|
* Adjust the size of the delayed refs block reserve for 1 block group item
|
|
|
|
* update.
|
|
|
|
*/
|
|
|
|
void btrfs_inc_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
|
|
|
|
|
|
|
|
spin_lock(&delayed_rsv->lock);
|
|
|
|
/*
|
|
|
|
* Updating a block group item does not result in new nodes/leaves and
|
|
|
|
* does not require changing the free space tree, only the extent tree
|
|
|
|
* or the block group tree, so this is all we need.
|
|
|
|
*/
|
|
|
|
delayed_rsv->size += btrfs_calc_metadata_size(fs_info, 1);
|
|
|
|
delayed_rsv->full = false;
|
|
|
|
spin_unlock(&delayed_rsv->lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Adjust the size of the delayed refs block reserve to release space for 1
|
|
|
|
* block group item update.
|
|
|
|
*/
|
|
|
|
void btrfs_dec_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info)
|
|
|
|
{
|
|
|
|
struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
|
|
|
|
const u64 num_bytes = btrfs_calc_metadata_size(fs_info, 1);
|
|
|
|
u64 released;
|
|
|
|
|
|
|
|
released = btrfs_block_rsv_release(fs_info, delayed_rsv, num_bytes, NULL);
|
|
|
|
if (released > 0)
|
|
|
|
trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
|
|
|
|
0, released, 0);
|
|
|
|
}
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
|
|
|
* Transfer bytes to our delayed refs rsv.
|
2021-01-22 17:57:55 +08:00
|
|
|
*
|
|
|
|
* @fs_info: the filesystem
|
|
|
|
* @num_bytes: number of bytes to transfer
|
2019-06-20 03:11:58 +08:00
|
|
|
*
|
2023-09-09 01:20:19 +08:00
|
|
|
* This transfers up to the num_bytes amount, previously reserved, to the
|
2019-06-20 03:11:58 +08:00
|
|
|
* delayed_refs_rsv. Any extra bytes are returned to the space info.
|
|
|
|
*/
|
|
|
|
void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
|
|
|
|
u64 num_bytes)
|
|
|
|
{
|
|
|
|
struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
|
|
|
|
u64 to_free = 0;
|
|
|
|
|
|
|
|
spin_lock(&delayed_refs_rsv->lock);
|
|
|
|
if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) {
|
|
|
|
u64 delta = delayed_refs_rsv->size -
|
|
|
|
delayed_refs_rsv->reserved;
|
|
|
|
if (num_bytes > delta) {
|
|
|
|
to_free = num_bytes - delta;
|
|
|
|
num_bytes = delta;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
to_free = num_bytes;
|
|
|
|
num_bytes = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (num_bytes)
|
|
|
|
delayed_refs_rsv->reserved += num_bytes;
|
|
|
|
if (delayed_refs_rsv->reserved >= delayed_refs_rsv->size)
|
2022-06-23 23:08:14 +08:00
|
|
|
delayed_refs_rsv->full = true;
|
2019-06-20 03:11:58 +08:00
|
|
|
spin_unlock(&delayed_refs_rsv->lock);
|
|
|
|
|
|
|
|
if (num_bytes)
|
|
|
|
trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
|
|
|
|
0, num_bytes, 1);
|
|
|
|
if (to_free)
|
2019-08-23 03:11:02 +08:00
|
|
|
btrfs_space_info_free_bytes_may_use(fs_info,
|
2019-06-20 03:11:58 +08:00
|
|
|
delayed_refs_rsv->space_info, to_free);
|
|
|
|
}
|
|
|
|
|
2022-10-27 20:21:42 +08:00
|
|
|
/*
|
|
|
|
* Refill based on our delayed refs usage.
|
2021-01-22 17:57:55 +08:00
|
|
|
*
|
|
|
|
* @fs_info: the filesystem
|
|
|
|
* @flush: control how we can flush for this reservation.
|
2019-06-20 03:11:58 +08:00
|
|
|
*
|
|
|
|
* This will refill the delayed block_rsv up to 1 items size worth of space and
|
|
|
|
* will return -ENOSPC if we can't make the reservation.
|
|
|
|
*/
|
|
|
|
int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
|
|
|
|
enum btrfs_reserve_flush_enum flush)
|
|
|
|
{
|
|
|
|
struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
|
2023-09-09 01:20:20 +08:00
|
|
|
struct btrfs_space_info *space_info = block_rsv->space_info;
|
2023-03-21 19:13:55 +08:00
|
|
|
u64 limit = btrfs_calc_delayed_ref_bytes(fs_info, 1);
|
2019-06-20 03:11:58 +08:00
|
|
|
u64 num_bytes = 0;
|
btrfs: fix race when refilling delayed refs block reserve
If we have two (or more) tasks attempting to refill the delayed refs block
reserve we can end up with the delayed block reserve being over reserved,
that is, with a reserved space greater than its size. If this happens, we
are holding to more reserved space than necessary for a while.
The race happens like this:
1) The delayed refs block reserve has a size of 8M and a reserved space of
6M for example;
2) Task A calls btrfs_delayed_refs_rsv_refill();
3) Task B also calls btrfs_delayed_refs_rsv_refill();
4) Task A sees there's a 2M difference between the size and the reserved
space of the delayed refs rsv, so it will reserve 2M of space by
calling btrfs_reserve_metadata_bytes();
5) Task B also sees that 2M difference, and like task A, it reserves
another 2M of metadata space;
6) Both task A and task B increase the reserved space of block reserve
by 2M, by calling btrfs_block_rsv_add_bytes(), so the block reserve
ends up with a size of 8M and a reserved space of 10M;
7) The extra, over reserved space will eventually be freed by some task
calling btrfs_delayed_refs_rsv_release() -> btrfs_block_rsv_release()
-> block_rsv_release_bytes(), as there we will detect the over reserve
and release that space.
So fix this by checking if we still need to add space to the delayed refs
block reserve after reserving the metadata space, and if we don't, just
release that space immediately.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:18 +08:00
|
|
|
u64 refilled_bytes;
|
|
|
|
u64 to_free;
|
2019-06-20 03:11:58 +08:00
|
|
|
int ret = -ENOSPC;
|
|
|
|
|
|
|
|
spin_lock(&block_rsv->lock);
|
|
|
|
if (block_rsv->reserved < block_rsv->size) {
|
|
|
|
num_bytes = block_rsv->size - block_rsv->reserved;
|
|
|
|
num_bytes = min(num_bytes, limit);
|
|
|
|
}
|
|
|
|
spin_unlock(&block_rsv->lock);
|
|
|
|
|
|
|
|
if (!num_bytes)
|
|
|
|
return 0;
|
|
|
|
|
2023-09-09 01:20:20 +08:00
|
|
|
ret = btrfs_reserve_metadata_bytes(fs_info, space_info, num_bytes, flush);
|
2019-06-20 03:11:58 +08:00
|
|
|
if (ret)
|
|
|
|
return ret;
|
btrfs: fix race when refilling delayed refs block reserve
If we have two (or more) tasks attempting to refill the delayed refs block
reserve we can end up with the delayed block reserve being over reserved,
that is, with a reserved space greater than its size. If this happens, we
are holding to more reserved space than necessary for a while.
The race happens like this:
1) The delayed refs block reserve has a size of 8M and a reserved space of
6M for example;
2) Task A calls btrfs_delayed_refs_rsv_refill();
3) Task B also calls btrfs_delayed_refs_rsv_refill();
4) Task A sees there's a 2M difference between the size and the reserved
space of the delayed refs rsv, so it will reserve 2M of space by
calling btrfs_reserve_metadata_bytes();
5) Task B also sees that 2M difference, and like task A, it reserves
another 2M of metadata space;
6) Both task A and task B increase the reserved space of block reserve
by 2M, by calling btrfs_block_rsv_add_bytes(), so the block reserve
ends up with a size of 8M and a reserved space of 10M;
7) The extra, over reserved space will eventually be freed by some task
calling btrfs_delayed_refs_rsv_release() -> btrfs_block_rsv_release()
-> block_rsv_release_bytes(), as there we will detect the over reserve
and release that space.
So fix this by checking if we still need to add space to the delayed refs
block reserve after reserving the metadata space, and if we don't, just
release that space immediately.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:18 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We may have raced with someone else, so check again if we the block
|
|
|
|
* reserve is still not full and release any excess space.
|
|
|
|
*/
|
|
|
|
spin_lock(&block_rsv->lock);
|
|
|
|
if (block_rsv->reserved < block_rsv->size) {
|
|
|
|
u64 needed = block_rsv->size - block_rsv->reserved;
|
|
|
|
|
|
|
|
if (num_bytes >= needed) {
|
|
|
|
block_rsv->reserved += needed;
|
|
|
|
block_rsv->full = true;
|
|
|
|
to_free = num_bytes - needed;
|
|
|
|
refilled_bytes = needed;
|
|
|
|
} else {
|
|
|
|
block_rsv->reserved += num_bytes;
|
|
|
|
to_free = 0;
|
|
|
|
refilled_bytes = num_bytes;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
to_free = num_bytes;
|
|
|
|
refilled_bytes = 0;
|
|
|
|
}
|
|
|
|
spin_unlock(&block_rsv->lock);
|
|
|
|
|
|
|
|
if (to_free > 0)
|
2023-09-09 01:20:20 +08:00
|
|
|
btrfs_space_info_free_bytes_may_use(fs_info, space_info, to_free);
|
btrfs: fix race when refilling delayed refs block reserve
If we have two (or more) tasks attempting to refill the delayed refs block
reserve we can end up with the delayed block reserve being over reserved,
that is, with a reserved space greater than its size. If this happens, we
are holding to more reserved space than necessary for a while.
The race happens like this:
1) The delayed refs block reserve has a size of 8M and a reserved space of
6M for example;
2) Task A calls btrfs_delayed_refs_rsv_refill();
3) Task B also calls btrfs_delayed_refs_rsv_refill();
4) Task A sees there's a 2M difference between the size and the reserved
space of the delayed refs rsv, so it will reserve 2M of space by
calling btrfs_reserve_metadata_bytes();
5) Task B also sees that 2M difference, and like task A, it reserves
another 2M of metadata space;
6) Both task A and task B increase the reserved space of block reserve
by 2M, by calling btrfs_block_rsv_add_bytes(), so the block reserve
ends up with a size of 8M and a reserved space of 10M;
7) The extra, over reserved space will eventually be freed by some task
calling btrfs_delayed_refs_rsv_release() -> btrfs_block_rsv_release()
-> block_rsv_release_bytes(), as there we will detect the over reserve
and release that space.
So fix this by checking if we still need to add space to the delayed refs
block reserve after reserving the metadata space, and if we don't, just
release that space immediately.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:18 +08:00
|
|
|
|
|
|
|
if (refilled_bytes > 0)
|
|
|
|
trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0,
|
|
|
|
refilled_bytes, 1);
|
2019-06-20 03:11:58 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
* compare two delayed tree backrefs with same bytenr and type
|
|
|
|
*/
|
2017-10-20 02:15:58 +08:00
|
|
|
static int comp_tree_refs(struct btrfs_delayed_tree_ref *ref1,
|
|
|
|
struct btrfs_delayed_tree_ref *ref2)
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
{
|
2024-04-13 04:42:28 +08:00
|
|
|
struct btrfs_delayed_ref_node *node = btrfs_delayed_tree_ref_to_node(ref1);
|
|
|
|
|
|
|
|
if (node->type == BTRFS_TREE_BLOCK_REF_KEY) {
|
Btrfs: compare relevant parts of delayed tree refs
A user reported a panic while running a balance. What was happening was he was
relocating a block, which added the reference to the relocation tree. Then
relocation would walk through the relocation tree and drop that reference and
free that block, and then it would walk down a snapshot which referenced the
same block and add another ref to the block. The problem is this was all
happening in the same transaction, so the parent block was free'ed up when we
drop our reference which was immediately available for allocation, and then it
was used _again_ to add a reference for the same block from a different
snapshot. This resulted in something like this in the delayed ref tree
add ref to 90234880, parent=2067398656, ref_root 1766, level 1
del ref to 90234880, parent=2067398656, ref_root 18446744073709551608, level 1
add ref to 90234880, parent=2067398656, ref_root 1767, level 1
as you can see the ref_root's don't match, because when we inc the ref we use
the header owner, which is the original tree the block belonged to, instead of
the data reloc tree. Then when we remove the extent we use the reloc tree
objectid. But none of this matters, since it is a shared reference which means
only the parent matters. When the delayed ref stuff runs it adds all the
increments first, and then does all the drops, to make sure that we don't delete
the ref if we net a positive ref count. But tree blocks aren't allowed to have
multiple refs from the same block, so this panics when it tries to add the
second ref. We need the add and the drop to cancel each other out in memory so
we only do the final add.
So to fix this we need to adjust how the delayed refs are added to the tree.
Only the ref_root matters when it is a normal backref, and only the parent
matters when it is a shared backref. So make our decision based on what ref
type we have. This allows us to keep the ref_root in memory in case anybody
wants to use it for something else, and it allows the delayed refs to be merged
properly so we don't end up with this panic.
With this patch the users image no longer panics on mount, and it has a clean
fsck after a normal mount/umount cycle. Thanks,
Cc: stable@vger.kernel.org
Reported-by: Roman Mamedov <rm@romanrm.ru>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
2013-04-02 08:36:28 +08:00
|
|
|
if (ref1->root < ref2->root)
|
|
|
|
return -1;
|
|
|
|
if (ref1->root > ref2->root)
|
|
|
|
return 1;
|
|
|
|
} else {
|
|
|
|
if (ref1->parent < ref2->parent)
|
|
|
|
return -1;
|
|
|
|
if (ref1->parent > ref2->parent)
|
|
|
|
return 1;
|
|
|
|
}
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* compare two delayed data backrefs with same bytenr and type
|
2009-03-13 22:10:06 +08:00
|
|
|
*/
|
2017-10-20 02:15:58 +08:00
|
|
|
static int comp_data_refs(struct btrfs_delayed_data_ref *ref1,
|
|
|
|
struct btrfs_delayed_data_ref *ref2)
|
2009-03-13 22:10:06 +08:00
|
|
|
{
|
2024-04-13 04:42:28 +08:00
|
|
|
struct btrfs_delayed_ref_node *node = btrfs_delayed_data_ref_to_node(ref1);
|
|
|
|
|
|
|
|
if (node->type == BTRFS_EXTENT_DATA_REF_KEY) {
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
if (ref1->root < ref2->root)
|
|
|
|
return -1;
|
|
|
|
if (ref1->root > ref2->root)
|
|
|
|
return 1;
|
|
|
|
if (ref1->objectid < ref2->objectid)
|
|
|
|
return -1;
|
|
|
|
if (ref1->objectid > ref2->objectid)
|
|
|
|
return 1;
|
|
|
|
if (ref1->offset < ref2->offset)
|
|
|
|
return -1;
|
|
|
|
if (ref1->offset > ref2->offset)
|
|
|
|
return 1;
|
|
|
|
} else {
|
|
|
|
if (ref1->parent < ref2->parent)
|
|
|
|
return -1;
|
|
|
|
if (ref1->parent > ref2->parent)
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-10-20 02:15:59 +08:00
|
|
|
static int comp_refs(struct btrfs_delayed_ref_node *ref1,
|
|
|
|
struct btrfs_delayed_ref_node *ref2,
|
|
|
|
bool check_seq)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
if (ref1->type < ref2->type)
|
|
|
|
return -1;
|
|
|
|
if (ref1->type > ref2->type)
|
|
|
|
return 1;
|
|
|
|
if (ref1->type == BTRFS_TREE_BLOCK_REF_KEY ||
|
|
|
|
ref1->type == BTRFS_SHARED_BLOCK_REF_KEY)
|
|
|
|
ret = comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref1),
|
|
|
|
btrfs_delayed_node_to_tree_ref(ref2));
|
|
|
|
else
|
|
|
|
ret = comp_data_refs(btrfs_delayed_node_to_data_ref(ref1),
|
|
|
|
btrfs_delayed_node_to_data_ref(ref2));
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
if (check_seq) {
|
|
|
|
if (ref1->seq < ref2->seq)
|
|
|
|
return -1;
|
|
|
|
if (ref1->seq > ref2->seq)
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-10-14 12:59:45 +08:00
|
|
|
/* insert a new ref to head ref rbtree */
|
2018-08-23 03:51:49 +08:00
|
|
|
static struct btrfs_delayed_ref_head *htree_insert(struct rb_root_cached *root,
|
2013-10-14 12:59:45 +08:00
|
|
|
struct rb_node *node)
|
|
|
|
{
|
2018-08-23 03:51:49 +08:00
|
|
|
struct rb_node **p = &root->rb_root.rb_node;
|
2013-10-14 12:59:45 +08:00
|
|
|
struct rb_node *parent_node = NULL;
|
|
|
|
struct btrfs_delayed_ref_head *entry;
|
|
|
|
struct btrfs_delayed_ref_head *ins;
|
|
|
|
u64 bytenr;
|
2018-08-23 03:51:49 +08:00
|
|
|
bool leftmost = true;
|
2013-10-14 12:59:45 +08:00
|
|
|
|
|
|
|
ins = rb_entry(node, struct btrfs_delayed_ref_head, href_node);
|
2017-09-30 03:43:57 +08:00
|
|
|
bytenr = ins->bytenr;
|
2013-10-14 12:59:45 +08:00
|
|
|
while (*p) {
|
|
|
|
parent_node = *p;
|
|
|
|
entry = rb_entry(parent_node, struct btrfs_delayed_ref_head,
|
|
|
|
href_node);
|
|
|
|
|
2018-08-23 03:51:49 +08:00
|
|
|
if (bytenr < entry->bytenr) {
|
2013-10-14 12:59:45 +08:00
|
|
|
p = &(*p)->rb_left;
|
2018-08-23 03:51:49 +08:00
|
|
|
} else if (bytenr > entry->bytenr) {
|
2013-10-14 12:59:45 +08:00
|
|
|
p = &(*p)->rb_right;
|
2018-08-23 03:51:49 +08:00
|
|
|
leftmost = false;
|
|
|
|
} else {
|
2013-10-14 12:59:45 +08:00
|
|
|
return entry;
|
2018-08-23 03:51:49 +08:00
|
|
|
}
|
2013-10-14 12:59:45 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
rb_link_node(node, parent_node, p);
|
2018-08-23 03:51:49 +08:00
|
|
|
rb_insert_color_cached(node, root, leftmost);
|
2013-10-14 12:59:45 +08:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2018-08-23 03:51:50 +08:00
|
|
|
static struct btrfs_delayed_ref_node* tree_insert(struct rb_root_cached *root,
|
2017-10-20 02:16:00 +08:00
|
|
|
struct btrfs_delayed_ref_node *ins)
|
|
|
|
{
|
2018-08-23 03:51:50 +08:00
|
|
|
struct rb_node **p = &root->rb_root.rb_node;
|
2017-10-20 02:16:00 +08:00
|
|
|
struct rb_node *node = &ins->ref_node;
|
|
|
|
struct rb_node *parent_node = NULL;
|
|
|
|
struct btrfs_delayed_ref_node *entry;
|
2018-08-23 03:51:50 +08:00
|
|
|
bool leftmost = true;
|
2017-10-20 02:16:00 +08:00
|
|
|
|
|
|
|
while (*p) {
|
|
|
|
int comp;
|
|
|
|
|
|
|
|
parent_node = *p;
|
|
|
|
entry = rb_entry(parent_node, struct btrfs_delayed_ref_node,
|
|
|
|
ref_node);
|
|
|
|
comp = comp_refs(ins, entry, true);
|
2018-08-23 03:51:50 +08:00
|
|
|
if (comp < 0) {
|
2017-10-20 02:16:00 +08:00
|
|
|
p = &(*p)->rb_left;
|
2018-08-23 03:51:50 +08:00
|
|
|
} else if (comp > 0) {
|
2017-10-20 02:16:00 +08:00
|
|
|
p = &(*p)->rb_right;
|
2018-08-23 03:51:50 +08:00
|
|
|
leftmost = false;
|
|
|
|
} else {
|
2017-10-20 02:16:00 +08:00
|
|
|
return entry;
|
2018-08-23 03:51:50 +08:00
|
|
|
}
|
2017-10-20 02:16:00 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
rb_link_node(node, parent_node, p);
|
2018-08-23 03:51:50 +08:00
|
|
|
rb_insert_color_cached(node, root, leftmost);
|
2017-10-20 02:16:00 +08:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2018-10-15 14:25:38 +08:00
|
|
|
static struct btrfs_delayed_ref_head *find_first_ref_head(
|
|
|
|
struct btrfs_delayed_ref_root *dr)
|
|
|
|
{
|
|
|
|
struct rb_node *n;
|
|
|
|
struct btrfs_delayed_ref_head *entry;
|
|
|
|
|
|
|
|
n = rb_first_cached(&dr->href_root);
|
|
|
|
if (!n)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
entry = rb_entry(n, struct btrfs_delayed_ref_head, href_node);
|
|
|
|
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
2018-10-15 14:25:38 +08:00
|
|
|
* Find a head entry based on bytenr. This returns the delayed ref head if it
|
|
|
|
* was able to find one, or NULL if nothing was in that spot. If return_bigger
|
|
|
|
* is given, the next bigger entry is returned if no exact match is found.
|
2009-03-13 22:10:06 +08:00
|
|
|
*/
|
2018-10-15 14:25:38 +08:00
|
|
|
static struct btrfs_delayed_ref_head *find_ref_head(
|
2018-08-23 03:51:49 +08:00
|
|
|
struct btrfs_delayed_ref_root *dr, u64 bytenr,
|
2018-10-11 13:40:38 +08:00
|
|
|
bool return_bigger)
|
2009-03-13 22:10:06 +08:00
|
|
|
{
|
2018-08-23 03:51:49 +08:00
|
|
|
struct rb_root *root = &dr->href_root.rb_root;
|
2011-09-13 21:16:43 +08:00
|
|
|
struct rb_node *n;
|
2013-10-14 12:59:45 +08:00
|
|
|
struct btrfs_delayed_ref_head *entry;
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2011-09-13 21:16:43 +08:00
|
|
|
n = root->rb_node;
|
|
|
|
entry = NULL;
|
2009-03-13 22:10:06 +08:00
|
|
|
while (n) {
|
2013-10-14 12:59:45 +08:00
|
|
|
entry = rb_entry(n, struct btrfs_delayed_ref_head, href_node);
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2017-09-30 03:43:57 +08:00
|
|
|
if (bytenr < entry->bytenr)
|
2009-03-13 22:10:06 +08:00
|
|
|
n = n->rb_left;
|
2017-09-30 03:43:57 +08:00
|
|
|
else if (bytenr > entry->bytenr)
|
2009-03-13 22:10:06 +08:00
|
|
|
n = n->rb_right;
|
|
|
|
else
|
|
|
|
return entry;
|
|
|
|
}
|
2011-09-13 21:16:43 +08:00
|
|
|
if (entry && return_bigger) {
|
2017-09-30 03:43:57 +08:00
|
|
|
if (bytenr > entry->bytenr) {
|
2013-10-14 12:59:45 +08:00
|
|
|
n = rb_next(&entry->href_node);
|
2011-09-13 21:16:43 +08:00
|
|
|
if (!n)
|
2018-10-15 14:25:38 +08:00
|
|
|
return NULL;
|
2013-10-14 12:59:45 +08:00
|
|
|
entry = rb_entry(n, struct btrfs_delayed_ref_head,
|
|
|
|
href_node);
|
2011-09-13 21:16:43 +08:00
|
|
|
}
|
|
|
|
return entry;
|
|
|
|
}
|
2009-03-13 22:10:06 +08:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2018-10-11 13:40:34 +08:00
|
|
|
int btrfs_delayed_ref_lock(struct btrfs_delayed_ref_root *delayed_refs,
|
2009-03-13 22:17:05 +08:00
|
|
|
struct btrfs_delayed_ref_head *head)
|
2009-03-13 22:10:06 +08:00
|
|
|
{
|
2018-03-16 09:21:22 +08:00
|
|
|
lockdep_assert_held(&delayed_refs->lock);
|
2009-03-13 22:17:05 +08:00
|
|
|
if (mutex_trylock(&head->mutex))
|
|
|
|
return 0;
|
|
|
|
|
2017-09-30 03:43:57 +08:00
|
|
|
refcount_inc(&head->refs);
|
2009-03-13 22:17:05 +08:00
|
|
|
spin_unlock(&delayed_refs->lock);
|
|
|
|
|
|
|
|
mutex_lock(&head->mutex);
|
|
|
|
spin_lock(&delayed_refs->lock);
|
2017-09-30 03:43:57 +08:00
|
|
|
if (RB_EMPTY_NODE(&head->href_node)) {
|
2009-03-13 22:17:05 +08:00
|
|
|
mutex_unlock(&head->mutex);
|
2017-09-30 03:43:57 +08:00
|
|
|
btrfs_put_delayed_ref_head(head);
|
2009-03-13 22:17:05 +08:00
|
|
|
return -EAGAIN;
|
|
|
|
}
|
2017-09-30 03:43:57 +08:00
|
|
|
btrfs_put_delayed_ref_head(head);
|
2009-03-13 22:17:05 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
static inline void drop_delayed_ref(struct btrfs_fs_info *fs_info,
|
|
|
|
struct btrfs_delayed_ref_root *delayed_refs,
|
2014-01-23 22:21:38 +08:00
|
|
|
struct btrfs_delayed_ref_head *head,
|
2012-08-08 04:00:32 +08:00
|
|
|
struct btrfs_delayed_ref_node *ref)
|
|
|
|
{
|
2018-03-16 09:21:22 +08:00
|
|
|
lockdep_assert_held(&head->lock);
|
2018-08-23 03:51:50 +08:00
|
|
|
rb_erase_cached(&ref->ref_node, &head->ref_tree);
|
2017-10-20 02:16:00 +08:00
|
|
|
RB_CLEAR_NODE(&ref->ref_node);
|
2017-09-30 03:43:57 +08:00
|
|
|
if (!list_empty(&ref->add_list))
|
|
|
|
list_del(&ref->add_list);
|
2012-08-08 04:00:32 +08:00
|
|
|
btrfs_put_delayed_ref(ref);
|
2014-01-23 22:21:38 +08:00
|
|
|
atomic_dec(&delayed_refs->num_entries);
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
btrfs_delayed_refs_rsv_release(fs_info, 1, 0);
|
2012-08-08 04:00:32 +08:00
|
|
|
}
|
|
|
|
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
static bool merge_ref(struct btrfs_fs_info *fs_info,
|
|
|
|
struct btrfs_delayed_ref_root *delayed_refs,
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
struct btrfs_delayed_ref_head *head,
|
|
|
|
struct btrfs_delayed_ref_node *ref,
|
|
|
|
u64 seq)
|
|
|
|
{
|
|
|
|
struct btrfs_delayed_ref_node *next;
|
2017-10-20 02:16:00 +08:00
|
|
|
struct rb_node *node = rb_next(&ref->ref_node);
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
bool done = false;
|
|
|
|
|
2017-10-20 02:16:00 +08:00
|
|
|
while (!done && node) {
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
int mod;
|
|
|
|
|
2017-10-20 02:16:00 +08:00
|
|
|
next = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
|
|
|
|
node = rb_next(node);
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
if (seq && next->seq >= seq)
|
2017-10-20 02:16:00 +08:00
|
|
|
break;
|
2017-10-20 02:15:59 +08:00
|
|
|
if (comp_refs(ref, next, false))
|
2017-10-20 02:16:00 +08:00
|
|
|
break;
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
|
|
|
|
if (ref->action == next->action) {
|
|
|
|
mod = next->ref_mod;
|
|
|
|
} else {
|
|
|
|
if (ref->ref_mod < next->ref_mod) {
|
|
|
|
swap(ref, next);
|
|
|
|
done = true;
|
|
|
|
}
|
|
|
|
mod = -next->ref_mod;
|
|
|
|
}
|
|
|
|
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
drop_delayed_ref(fs_info, delayed_refs, head, next);
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
ref->ref_mod += mod;
|
|
|
|
if (ref->ref_mod == 0) {
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
drop_delayed_ref(fs_info, delayed_refs, head, ref);
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
done = true;
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* Can't have multiples of the same ref on a tree block.
|
|
|
|
*/
|
|
|
|
WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY ||
|
|
|
|
ref->type == BTRFS_SHARED_BLOCK_REF_KEY);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return done;
|
|
|
|
}
|
|
|
|
|
2022-12-12 17:02:49 +08:00
|
|
|
void btrfs_merge_delayed_refs(struct btrfs_fs_info *fs_info,
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
struct btrfs_delayed_ref_root *delayed_refs,
|
|
|
|
struct btrfs_delayed_ref_head *head)
|
|
|
|
{
|
|
|
|
struct btrfs_delayed_ref_node *ref;
|
2017-10-20 02:16:00 +08:00
|
|
|
struct rb_node *node;
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
u64 seq = 0;
|
|
|
|
|
2018-03-16 09:21:22 +08:00
|
|
|
lockdep_assert_held(&head->lock);
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
|
2018-08-23 03:51:50 +08:00
|
|
|
if (RB_EMPTY_ROOT(&head->ref_tree.rb_root))
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
/* We don't have too many refs to merge for data. */
|
|
|
|
if (head->is_data)
|
|
|
|
return;
|
|
|
|
|
2021-03-11 22:31:12 +08:00
|
|
|
seq = btrfs_tree_mod_log_lowest_seq(fs_info);
|
2017-10-20 02:16:00 +08:00
|
|
|
again:
|
2018-08-23 03:51:50 +08:00
|
|
|
for (node = rb_first_cached(&head->ref_tree); node;
|
|
|
|
node = rb_next(node)) {
|
2017-10-20 02:16:00 +08:00
|
|
|
ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
if (seq && ref->seq >= seq)
|
|
|
|
continue;
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
if (merge_ref(fs_info, delayed_refs, head, ref, seq))
|
2017-10-20 02:16:00 +08:00
|
|
|
goto again;
|
Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:
[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>] [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08 EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS: 0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201] ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201] ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201] ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201] [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201] [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201] [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201] [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201] [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201] [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201] [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201] [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201] [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201] [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201] [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201] [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201] [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---
This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:
1) Transaction N starts, fs_info->tree_mod_seq has value 0;
2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
bytenr A is created, with a value of 1 and a seq value of 0;
3) fs_info->tree_mod_seq is incremented to 1;
4) Extent buffer A is deleted through btrfs_del_items(), which calls
btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
later returns the metadata extent associated to extent buffer A to
the free space cache (the range is not pinned), because the extent
buffer was created in the current transaction (N) and writeback never
happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
in the extent buffer).
This creates the delayed reference Ref2 for bytenr A, with a value
of -1 and a seq value of 1;
5) Delayed reference Ref2 is not merged with Ref1 when we create it,
because they have different sequence numbers (decided at
add_delayed_ref_tail_merge());
6) fs_info->tree_mod_seq is incremented to 2;
7) Some task attempts to allocate a new extent buffer (done at
extent-tree.c:find_free_extent()), but due to heavy fragmentation
and running low on metadata space the clustered allocation fails
and we fall back to unclustered allocation, which finds the
extent at offset A, so a new extent buffer at offset A is allocated.
This creates delayed reference Ref3 for bytenr A, with a value of 1
and a seq value of 2;
8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
all have different seq values;
9) We start running the delayed references (__btrfs_run_delayed_refs());
10) The delayed Ref1 is the first one being applied, which ends up
creating an inline extent backref in the extent tree;
10) Next the delayed reference Ref3 is selected for execution, and not
Ref2, because select_delayed_ref() always gives a preference for
positive references (that have an action of BTRFS_ADD_DELAYED_REF);
11) When running Ref3 we encounter alreay the inline extent backref
in the extent tree at insert_inline_extent_backref(), which makes
us hit the following BUG_ON:
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
This is always true because owner corresponds to the level of the
extent buffer/btree node in the btree.
For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.
We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:
c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
c43d160fcd5e ("btrfs: delayed-ref: Cleanup the unneeded functions.")
This issue became more exposed after the following change that was added
to 4.2 as well:
cffc3374e567 ("Btrfs: fix order by which delayed references are run")
Which in turn fixed another regression by the two commits previously
mentioned.
So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).
This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.
Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).
Fixes: c6fc24549960 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-22 16:47:34 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-04-04 20:57:42 +08:00
|
|
|
int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
|
2011-09-14 18:37:00 +08:00
|
|
|
{
|
2012-06-21 17:08:04 +08:00
|
|
|
int ret = 0;
|
2021-03-11 22:31:12 +08:00
|
|
|
u64 min_seq = btrfs_tree_mod_log_lowest_seq(fs_info);
|
|
|
|
|
|
|
|
if (min_seq != 0 && seq >= min_seq) {
|
|
|
|
btrfs_debug(fs_info,
|
2021-03-11 22:31:13 +08:00
|
|
|
"holding back delayed_ref %llu, lowest is %llu",
|
|
|
|
seq, min_seq);
|
2021-03-11 22:31:12 +08:00
|
|
|
ret = 1;
|
2011-09-14 18:37:00 +08:00
|
|
|
}
|
2012-06-21 17:08:04 +08:00
|
|
|
|
|
|
|
return ret;
|
2011-09-14 18:37:00 +08:00
|
|
|
}
|
|
|
|
|
2018-10-11 13:40:33 +08:00
|
|
|
struct btrfs_delayed_ref_head *btrfs_select_ref_head(
|
|
|
|
struct btrfs_delayed_ref_root *delayed_refs)
|
2009-03-13 22:17:05 +08:00
|
|
|
{
|
2014-01-23 22:21:38 +08:00
|
|
|
struct btrfs_delayed_ref_head *head;
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2023-05-29 23:17:03 +08:00
|
|
|
lockdep_assert_held(&delayed_refs->lock);
|
2009-03-13 22:17:05 +08:00
|
|
|
again:
|
2018-10-15 14:25:38 +08:00
|
|
|
head = find_ref_head(delayed_refs, delayed_refs->run_delayed_start,
|
|
|
|
true);
|
|
|
|
if (!head && delayed_refs->run_delayed_start != 0) {
|
2014-01-23 22:21:38 +08:00
|
|
|
delayed_refs->run_delayed_start = 0;
|
2018-10-15 14:25:38 +08:00
|
|
|
head = find_first_ref_head(delayed_refs);
|
2009-03-13 22:17:05 +08:00
|
|
|
}
|
2018-10-15 14:25:38 +08:00
|
|
|
if (!head)
|
|
|
|
return NULL;
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2014-01-23 22:21:38 +08:00
|
|
|
while (head->processing) {
|
|
|
|
struct rb_node *node;
|
|
|
|
|
|
|
|
node = rb_next(&head->href_node);
|
|
|
|
if (!node) {
|
2018-10-15 14:25:38 +08:00
|
|
|
if (delayed_refs->run_delayed_start == 0)
|
2014-01-23 22:21:38 +08:00
|
|
|
return NULL;
|
|
|
|
delayed_refs->run_delayed_start = 0;
|
|
|
|
goto again;
|
|
|
|
}
|
|
|
|
head = rb_entry(node, struct btrfs_delayed_ref_head,
|
|
|
|
href_node);
|
|
|
|
}
|
2012-12-19 16:10:10 +08:00
|
|
|
|
2023-05-29 23:17:04 +08:00
|
|
|
head->processing = true;
|
2014-01-23 22:21:38 +08:00
|
|
|
WARN_ON(delayed_refs->num_heads_ready == 0);
|
|
|
|
delayed_refs->num_heads_ready--;
|
2017-09-30 03:43:57 +08:00
|
|
|
delayed_refs->run_delayed_start = head->bytenr +
|
|
|
|
head->num_bytes;
|
2014-01-23 22:21:38 +08:00
|
|
|
return head;
|
2012-12-19 16:10:10 +08:00
|
|
|
}
|
|
|
|
|
2018-12-03 23:20:29 +08:00
|
|
|
void btrfs_delete_ref_head(struct btrfs_delayed_ref_root *delayed_refs,
|
|
|
|
struct btrfs_delayed_ref_head *head)
|
|
|
|
{
|
|
|
|
lockdep_assert_held(&delayed_refs->lock);
|
|
|
|
lockdep_assert_held(&head->lock);
|
|
|
|
|
|
|
|
rb_erase_cached(&head->href_node, &delayed_refs->href_root);
|
|
|
|
RB_CLEAR_NODE(&head->href_node);
|
|
|
|
atomic_dec(&delayed_refs->num_entries);
|
|
|
|
delayed_refs->num_heads--;
|
2023-05-29 23:17:04 +08:00
|
|
|
if (!head->processing)
|
2018-12-03 23:20:29 +08:00
|
|
|
delayed_refs->num_heads_ready--;
|
|
|
|
}
|
|
|
|
|
2015-03-30 17:03:00 +08:00
|
|
|
/*
|
|
|
|
* Helper to insert the ref_node to the tail or merge with tail.
|
|
|
|
*
|
2023-05-29 23:17:01 +08:00
|
|
|
* Return false if the ref was inserted.
|
|
|
|
* Return true if the ref was merged into an existing one (and therefore can be
|
|
|
|
* freed by the caller).
|
2015-03-30 17:03:00 +08:00
|
|
|
*/
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
static bool insert_delayed_ref(struct btrfs_trans_handle *trans,
|
2023-05-29 23:17:01 +08:00
|
|
|
struct btrfs_delayed_ref_head *href,
|
|
|
|
struct btrfs_delayed_ref_node *ref)
|
2015-03-30 17:03:00 +08:00
|
|
|
{
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
struct btrfs_delayed_ref_root *root = &trans->transaction->delayed_refs;
|
2015-03-30 17:03:00 +08:00
|
|
|
struct btrfs_delayed_ref_node *exist;
|
|
|
|
int mod;
|
|
|
|
|
|
|
|
spin_lock(&href->lock);
|
2017-10-20 02:16:00 +08:00
|
|
|
exist = tree_insert(&href->ref_tree, ref);
|
2023-05-29 23:17:02 +08:00
|
|
|
if (!exist) {
|
|
|
|
if (ref->action == BTRFS_ADD_DELAYED_REF)
|
|
|
|
list_add_tail(&ref->add_list, &href->ref_add_list);
|
|
|
|
atomic_inc(&root->num_entries);
|
|
|
|
spin_unlock(&href->lock);
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
trans->delayed_ref_updates++;
|
2023-05-29 23:17:02 +08:00
|
|
|
return false;
|
|
|
|
}
|
2015-03-30 17:03:00 +08:00
|
|
|
|
|
|
|
/* Now we are sure we can merge */
|
|
|
|
if (exist->action == ref->action) {
|
|
|
|
mod = ref->ref_mod;
|
|
|
|
} else {
|
|
|
|
/* Need to change action */
|
|
|
|
if (exist->ref_mod < ref->ref_mod) {
|
|
|
|
exist->action = ref->action;
|
|
|
|
mod = -exist->ref_mod;
|
|
|
|
exist->ref_mod = ref->ref_mod;
|
btrfs: improve delayed refs iterations
This issue was found when I tried to delete a heavily reflinked file,
when deleting such files, other transaction operation will not have a
chance to make progress, for example, start_transaction() will blocked
in wait_current_trans(root) for long time, sometimes it even triggers
soft lockups, and the time taken to delete such heavily reflinked file
is also very large, often hundreds of seconds. Using perf top, it reports
that:
PerfTop: 7416 irqs/sec kernel:99.8% exact: 0.0% [4000Hz cpu-clock], (all, 4 CPUs)
---------------------------------------------------------------------------------------
84.37% [btrfs] [k] __btrfs_run_delayed_refs.constprop.80
11.02% [kernel] [k] delay_tsc
0.79% [kernel] [k] _raw_spin_unlock_irq
0.78% [kernel] [k] _raw_spin_unlock_irqrestore
0.45% [kernel] [k] do_raw_spin_lock
0.18% [kernel] [k] __slab_alloc
It seems __btrfs_run_delayed_refs() took most cpu time, after some debug
work, I found it's select_delayed_ref() causing this issue, for a delayed
head, in our case, it'll be full of BTRFS_DROP_DELAYED_REF nodes, but
select_delayed_ref() will firstly try to iterate node list to find
BTRFS_ADD_DELAYED_REF nodes, obviously it's a disaster in this case, and
waste much time.
To fix this issue, we introduce a new ref_add_list in struct btrfs_delayed_ref_head,
then in select_delayed_ref(), if this list is not empty, we can directly use
nodes in this list. With this patch, it just took about 10~15 seconds to
delte the same file. Now using perf top, it reports that:
PerfTop: 2734 irqs/sec kernel:99.5% exact: 0.0% [4000Hz cpu-clock], (all, 4 CPUs)
----------------------------------------------------------------------------------------
20.74% [kernel] [k] _raw_spin_unlock_irqrestore
16.33% [kernel] [k] __slab_alloc
5.41% [kernel] [k] lock_acquired
4.42% [kernel] [k] lock_acquire
4.05% [kernel] [k] lock_release
3.37% [kernel] [k] _raw_spin_unlock_irq
For normal files, this patch also gives help, at least we do not need to
iterate whole list to found BTRFS_ADD_DELAYED_REF nodes.
Signed-off-by: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2016-10-26 18:07:33 +08:00
|
|
|
if (ref->action == BTRFS_ADD_DELAYED_REF)
|
|
|
|
list_add_tail(&exist->add_list,
|
|
|
|
&href->ref_add_list);
|
|
|
|
else if (ref->action == BTRFS_DROP_DELAYED_REF) {
|
|
|
|
ASSERT(!list_empty(&exist->add_list));
|
|
|
|
list_del(&exist->add_list);
|
|
|
|
} else {
|
|
|
|
ASSERT(0);
|
|
|
|
}
|
2015-03-30 17:03:00 +08:00
|
|
|
} else
|
|
|
|
mod = -ref->ref_mod;
|
|
|
|
}
|
|
|
|
exist->ref_mod += mod;
|
|
|
|
|
|
|
|
/* remove existing tail if its ref_mod is zero */
|
|
|
|
if (exist->ref_mod == 0)
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
drop_delayed_ref(trans->fs_info, root, href, exist);
|
2015-03-30 17:03:00 +08:00
|
|
|
spin_unlock(&href->lock);
|
2023-05-29 23:17:02 +08:00
|
|
|
return true;
|
2015-03-30 17:03:00 +08:00
|
|
|
}
|
|
|
|
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
|
|
|
* helper function to update the accounting in the head ref
|
|
|
|
* existing and update must have the same bytenr
|
|
|
|
*/
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans,
|
2017-09-30 03:43:57 +08:00
|
|
|
struct btrfs_delayed_ref_head *existing,
|
2021-01-16 05:48:55 +08:00
|
|
|
struct btrfs_delayed_ref_head *update)
|
2009-03-13 22:10:06 +08:00
|
|
|
{
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
struct btrfs_delayed_ref_root *delayed_refs =
|
|
|
|
&trans->transaction->delayed_refs;
|
|
|
|
struct btrfs_fs_info *fs_info = trans->fs_info;
|
2015-02-03 23:50:16 +08:00
|
|
|
int old_ref_mod;
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2017-09-30 03:43:57 +08:00
|
|
|
BUG_ON(existing->is_data != update->is_data);
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2017-09-30 03:43:57 +08:00
|
|
|
spin_lock(&existing->lock);
|
2023-06-29 05:03:35 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* When freeing an extent, we may not know the owning root when we
|
|
|
|
* first create the head_ref. However, some deref before the last deref
|
|
|
|
* will know it, so we just need to update the head_ref accordingly.
|
|
|
|
*/
|
|
|
|
if (!existing->owning_root)
|
|
|
|
existing->owning_root = update->owning_root;
|
|
|
|
|
2017-09-30 03:43:57 +08:00
|
|
|
if (update->must_insert_reserved) {
|
2009-03-13 22:10:06 +08:00
|
|
|
/* if the extent was freed and then
|
|
|
|
* reallocated before the delayed ref
|
|
|
|
* entries were processed, we can end up
|
|
|
|
* with an existing head ref without
|
|
|
|
* the must_insert_reserved flag set.
|
|
|
|
* Set it again here
|
|
|
|
*/
|
2017-09-30 03:43:57 +08:00
|
|
|
existing->must_insert_reserved = update->must_insert_reserved;
|
2023-06-29 05:03:35 +08:00
|
|
|
existing->owning_root = update->owning_root;
|
2009-03-13 22:10:06 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* update the num_bytes so we make sure the accounting
|
|
|
|
* is done correctly
|
|
|
|
*/
|
|
|
|
existing->num_bytes = update->num_bytes;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2017-09-30 03:43:57 +08:00
|
|
|
if (update->extent_op) {
|
|
|
|
if (!existing->extent_op) {
|
|
|
|
existing->extent_op = update->extent_op;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
} else {
|
2017-09-30 03:43:57 +08:00
|
|
|
if (update->extent_op->update_key) {
|
|
|
|
memcpy(&existing->extent_op->key,
|
|
|
|
&update->extent_op->key,
|
|
|
|
sizeof(update->extent_op->key));
|
|
|
|
existing->extent_op->update_key = true;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
}
|
2017-09-30 03:43:57 +08:00
|
|
|
if (update->extent_op->update_flags) {
|
|
|
|
existing->extent_op->flags_to_set |=
|
|
|
|
update->extent_op->flags_to_set;
|
|
|
|
existing->extent_op->update_flags = true;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
}
|
2017-09-30 03:43:57 +08:00
|
|
|
btrfs_free_delayed_extent_op(update->extent_op);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
}
|
|
|
|
}
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
2014-01-23 22:21:38 +08:00
|
|
|
* update the reference mod on the head to reflect this new operation,
|
|
|
|
* only need the lock for this case cause we could be processing it
|
|
|
|
* currently, for refs we just added we know we're a-ok.
|
2009-03-13 22:10:06 +08:00
|
|
|
*/
|
2017-09-30 03:43:57 +08:00
|
|
|
old_ref_mod = existing->total_ref_mod;
|
2009-03-13 22:10:06 +08:00
|
|
|
existing->ref_mod += update->ref_mod;
|
2017-09-30 03:43:57 +08:00
|
|
|
existing->total_ref_mod += update->ref_mod;
|
2015-02-03 23:50:16 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If we are going to from a positive ref mod to a negative or vice
|
|
|
|
* versa we need to make sure to adjust pending_csums accordingly.
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
* We reserve bytes for csum deletion when adding or updating a ref head
|
|
|
|
* see add_delayed_ref_head() for more details.
|
2015-02-03 23:50:16 +08:00
|
|
|
*/
|
2017-09-30 03:43:57 +08:00
|
|
|
if (existing->is_data) {
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
u64 csum_leaves =
|
|
|
|
btrfs_csum_bytes_to_leaves(fs_info,
|
|
|
|
existing->num_bytes);
|
|
|
|
|
|
|
|
if (existing->total_ref_mod >= 0 && old_ref_mod < 0) {
|
2015-02-03 23:50:16 +08:00
|
|
|
delayed_refs->pending_csums -= existing->num_bytes;
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
btrfs_delayed_refs_rsv_release(fs_info, 0, csum_leaves);
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
}
|
|
|
|
if (existing->total_ref_mod < 0 && old_ref_mod >= 0) {
|
2015-02-03 23:50:16 +08:00
|
|
|
delayed_refs->pending_csums += existing->num_bytes;
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
trans->delayed_ref_csum_deletions += csum_leaves;
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
}
|
2015-02-03 23:50:16 +08:00
|
|
|
}
|
2021-01-16 05:48:55 +08:00
|
|
|
|
2017-09-30 03:43:57 +08:00
|
|
|
spin_unlock(&existing->lock);
|
2009-03-13 22:10:06 +08:00
|
|
|
}
|
|
|
|
|
2018-04-24 22:18:22 +08:00
|
|
|
static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
|
|
|
|
struct btrfs_qgroup_extent_record *qrecord,
|
|
|
|
u64 bytenr, u64 num_bytes, u64 ref_root,
|
|
|
|
u64 reserved, int action, bool is_data,
|
2023-06-29 05:03:35 +08:00
|
|
|
bool is_system, u64 owning_root)
|
2018-04-24 22:18:22 +08:00
|
|
|
{
|
|
|
|
int count_mod = 1;
|
2023-05-29 23:17:04 +08:00
|
|
|
bool must_insert_reserved = false;
|
2018-04-24 22:18:22 +08:00
|
|
|
|
|
|
|
/* If reserved is provided, it must be a data extent. */
|
|
|
|
BUG_ON(!is_data && reserved);
|
|
|
|
|
2023-05-29 23:17:05 +08:00
|
|
|
switch (action) {
|
|
|
|
case BTRFS_UPDATE_DELAYED_HEAD:
|
2018-04-24 22:18:22 +08:00
|
|
|
count_mod = 0;
|
2023-05-29 23:17:05 +08:00
|
|
|
break;
|
|
|
|
case BTRFS_DROP_DELAYED_REF:
|
|
|
|
/*
|
|
|
|
* The head node stores the sum of all the mods, so dropping a ref
|
|
|
|
* should drop the sum in the head node by one.
|
|
|
|
*/
|
2018-04-24 22:18:22 +08:00
|
|
|
count_mod = -1;
|
2023-05-29 23:17:05 +08:00
|
|
|
break;
|
|
|
|
case BTRFS_ADD_DELAYED_EXTENT:
|
|
|
|
/*
|
|
|
|
* BTRFS_ADD_DELAYED_EXTENT means that we need to update the
|
|
|
|
* reserved accounting when the extent is finally added, or if a
|
|
|
|
* later modification deletes the delayed ref without ever
|
|
|
|
* inserting the extent into the extent allocation tree.
|
|
|
|
* ref->must_insert_reserved is the flag used to record that
|
|
|
|
* accounting mods are required.
|
|
|
|
*
|
|
|
|
* Once we record must_insert_reserved, switch the action to
|
|
|
|
* BTRFS_ADD_DELAYED_REF because other special casing is not
|
|
|
|
* required.
|
|
|
|
*/
|
2023-05-29 23:17:04 +08:00
|
|
|
must_insert_reserved = true;
|
2023-05-29 23:17:05 +08:00
|
|
|
break;
|
|
|
|
}
|
2018-04-24 22:18:22 +08:00
|
|
|
|
|
|
|
refcount_set(&head_ref->refs, 1);
|
|
|
|
head_ref->bytenr = bytenr;
|
|
|
|
head_ref->num_bytes = num_bytes;
|
|
|
|
head_ref->ref_mod = count_mod;
|
btrfs: record simple quota deltas in delayed refs
At the moment that we run delayed refs, we make the final ref-count
based decision on creating/removing extent (and metadata) items.
Therefore, it is exactly the spot to hook up simple quotas.
There are a few important subtleties to the fields we must collect to
accurately track simple quotas, particularly when removing an extent.
When removing a data extent, the ref could be in any tree (due to
reflink, for example) and so we need to recover the owning root id from
the owner ref item. When removing a metadata extent, we know the owning
root from the owner field in the header when we create the delayed ref,
so we can recover it from there.
We must also be careful to handle reservations properly to not leaked
reserved space. The happy path is freeing the reservation when the
simple quota delta runs on a data extent. If that doesn't happen, due to
refs canceling out or some error, the ref head already has the
must_insert_reserved machinery to handle this, so we piggy back on that
and use it to clean up the reserved data.
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-06-29 02:00:15 +08:00
|
|
|
head_ref->reserved_bytes = reserved;
|
2018-04-24 22:18:22 +08:00
|
|
|
head_ref->must_insert_reserved = must_insert_reserved;
|
2023-06-29 05:03:35 +08:00
|
|
|
head_ref->owning_root = owning_root;
|
2018-04-24 22:18:22 +08:00
|
|
|
head_ref->is_data = is_data;
|
|
|
|
head_ref->is_system = is_system;
|
2018-08-23 03:51:50 +08:00
|
|
|
head_ref->ref_tree = RB_ROOT_CACHED;
|
2018-04-24 22:18:22 +08:00
|
|
|
INIT_LIST_HEAD(&head_ref->ref_add_list);
|
|
|
|
RB_CLEAR_NODE(&head_ref->href_node);
|
2023-05-29 23:17:04 +08:00
|
|
|
head_ref->processing = false;
|
2018-04-24 22:18:22 +08:00
|
|
|
head_ref->total_ref_mod = count_mod;
|
|
|
|
spin_lock_init(&head_ref->lock);
|
|
|
|
mutex_init(&head_ref->mutex);
|
|
|
|
|
|
|
|
if (qrecord) {
|
|
|
|
if (ref_root && reserved) {
|
btrfs: qgroup: Move reserved data accounting from btrfs_delayed_ref_head to btrfs_qgroup_extent_record
[BUG]
Btrfs/139 will fail with a high probability if the testing machine (VM)
has only 2G RAM.
Resulting the final write success while it should fail due to EDQUOT,
and the fs will have quota exceeding the limit by 16K.
The simplified reproducer will be: (needs a 2G ram VM)
$ mkfs.btrfs -f $dev
$ mount $dev $mnt
$ btrfs subv create $mnt/subv
$ btrfs quota enable $mnt
$ btrfs quota rescan -w $mnt
$ btrfs qgroup limit -e 1G $mnt/subv
$ for i in $(seq -w 1 8); do
xfs_io -f -c "pwrite 0 128M" $mnt/subv/file_$i > /dev/null
echo "file $i written" > /dev/kmsg
done
$ sync
$ btrfs qgroup show -pcre --raw $mnt
The last pwrite will not trigger EDQUOT and final 'qgroup show' will
show something like:
qgroupid rfer excl max_rfer max_excl parent child
-------- ---- ---- -------- -------- ------ -----
0/5 16384 16384 none none --- ---
0/256 1073758208 1073758208 none 1073741824 --- ---
And 1073758208 is larger than
> 1073741824.
[CAUSE]
It's a bug in btrfs qgroup data reserved space management.
For quota limit, we must ensure that:
reserved (data + metadata) + rfer/excl <= limit
Since rfer/excl is only updated at transaction commmit time, reserved
space needs to be taken special care.
One important part of reserved space is data, and for a new data extent
written to disk, we still need to take the reserved space until
rfer/excl numbers get updated.
Originally when an ordered extent finishes, we migrate the reserved
qgroup data space from extent_io tree to delayed ref head of the data
extent, expecting delayed ref will only be cleaned up at commit
transaction time.
However for small RAM machine, due to memory pressure dirty pages can be
flushed back to disk without committing a transaction.
The related events will be something like:
file 1 written
btrfs_finish_ordered_io: ino=258 ordered offset=0 len=54947840
btrfs_finish_ordered_io: ino=258 ordered offset=54947840 len=5636096
btrfs_finish_ordered_io: ino=258 ordered offset=61153280 len=57344
btrfs_finish_ordered_io: ino=258 ordered offset=61210624 len=8192
btrfs_finish_ordered_io: ino=258 ordered offset=60583936 len=569344
cleanup_ref_head: num_bytes=54947840
cleanup_ref_head: num_bytes=5636096
cleanup_ref_head: num_bytes=569344
cleanup_ref_head: num_bytes=57344
cleanup_ref_head: num_bytes=8192
^^^^^^^^^^^^^^^^ This will free qgroup data reserved space
file 2 written
...
file 8 written
cleanup_ref_head: num_bytes=8192
...
btrfs_commit_transaction <<< the only transaction committed during
the test
When file 2 is written, we have already freed 128M reserved qgroup data
space for ino 258. Thus later write won't trigger EDQUOT.
This allows us to write more data beyond qgroup limit.
In my 2G ram VM, it could reach about 1.2G before hitting EDQUOT.
[FIX]
By moving reserved qgroup data space from btrfs_delayed_ref_head to
btrfs_qgroup_extent_record, we can ensure that reserved qgroup data
space won't be freed half way before commit transaction, thus fix the
problem.
Fixes: f64d5ca86821 ("btrfs: delayed_ref: Add new function to record reserved space into delayed ref")
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2019-01-23 15:15:12 +08:00
|
|
|
qrecord->data_rsv = reserved;
|
|
|
|
qrecord->data_rsv_refroot = ref_root;
|
2018-04-24 22:18:22 +08:00
|
|
|
}
|
|
|
|
qrecord->bytenr = bytenr;
|
|
|
|
qrecord->num_bytes = num_bytes;
|
|
|
|
qrecord->old_roots = NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
* helper function to actually insert a head node into the rbtree.
|
2009-03-13 22:10:06 +08:00
|
|
|
* this does all the dirty work in terms of maintaining the correct
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
* overall modification count.
|
2009-03-13 22:10:06 +08:00
|
|
|
*/
|
2014-01-23 22:21:38 +08:00
|
|
|
static noinline struct btrfs_delayed_ref_head *
|
2018-04-19 16:06:37 +08:00
|
|
|
add_delayed_ref_head(struct btrfs_trans_handle *trans,
|
2017-09-30 03:43:57 +08:00
|
|
|
struct btrfs_delayed_ref_head *head_ref,
|
2015-04-16 14:34:17 +08:00
|
|
|
struct btrfs_qgroup_extent_record *qrecord,
|
2023-05-29 23:17:00 +08:00
|
|
|
int action, bool *qrecord_inserted_ret)
|
2009-03-13 22:10:06 +08:00
|
|
|
{
|
2014-01-23 22:21:38 +08:00
|
|
|
struct btrfs_delayed_ref_head *existing;
|
2009-03-13 22:10:06 +08:00
|
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
2023-05-29 23:17:00 +08:00
|
|
|
bool qrecord_inserted = false;
|
2009-03-13 22:10:06 +08:00
|
|
|
|
|
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
2018-04-24 22:18:24 +08:00
|
|
|
|
2015-04-16 14:34:17 +08:00
|
|
|
/* Record qgroup extent info if provided */
|
|
|
|
if (qrecord) {
|
2018-04-24 22:18:23 +08:00
|
|
|
if (btrfs_qgroup_trace_extent_nolock(trans->fs_info,
|
btrfs: qgroup: Refactor btrfs_qgroup_insert_dirty_extent()
Refactor btrfs_qgroup_insert_dirty_extent() function, to two functions:
1. btrfs_qgroup_insert_dirty_extent_nolock()
Almost the same with original code.
For delayed_ref usage, which has delayed refs locked.
Change the return value type to int, since caller never needs the
pointer, but only needs to know if they need to free the allocated
memory.
2. btrfs_qgroup_insert_dirty_extent()
The more encapsulated version.
Will do the delayed_refs lock, memory allocation, quota enabled check
and other things.
The original design is to keep exported functions to minimal, but since
more btrfs hacks exposed, like replacing path in balance, we need to
record dirty extents manually, so we have to add such functions.
Also, add comment for both functions, to info developers how to keep
qgroup correct when doing hacks.
Cc: Mark Fasheh <mfasheh@suse.de>
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-and-Tested-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
2016-08-15 10:36:50 +08:00
|
|
|
delayed_refs, qrecord))
|
2015-04-16 14:34:17 +08:00
|
|
|
kfree(qrecord);
|
2017-02-15 10:43:03 +08:00
|
|
|
else
|
2023-05-29 23:17:00 +08:00
|
|
|
qrecord_inserted = true;
|
2015-04-16 14:34:17 +08:00
|
|
|
}
|
|
|
|
|
2018-04-19 16:06:37 +08:00
|
|
|
trace_add_delayed_ref_head(trans->fs_info, head_ref, action);
|
Btrfs: add initial tracepoint support for btrfs
Tracepoints can provide insight into why btrfs hits bugs and be greatly
helpful for debugging, e.g
dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0
dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0
btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0)
btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0)
btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8
flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA
flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0)
flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0)
flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0)
btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0)
btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0)
Here is what I have added:
1) ordere_extent:
btrfs_ordered_extent_add
btrfs_ordered_extent_remove
btrfs_ordered_extent_start
btrfs_ordered_extent_put
These provide critical information to understand how ordered_extents are
updated.
2) extent_map:
btrfs_get_extent
extent_map is used in both read and write cases, and it is useful for tracking
how btrfs specific IO is running.
3) writepage:
__extent_writepage
btrfs_writepage_end_io_hook
Pages are cirtical resourses and produce a lot of corner cases during writeback,
so it is valuable to know how page is written to disk.
4) inode:
btrfs_inode_new
btrfs_inode_request
btrfs_inode_evict
These can show where and when a inode is created, when a inode is evicted.
5) sync:
btrfs_sync_file
btrfs_sync_fs
These show sync arguments.
6) transaction:
btrfs_transaction_commit
In transaction based filesystem, it will be useful to know the generation and
who does commit.
7) back reference and cow:
btrfs_delayed_tree_ref
btrfs_delayed_data_ref
btrfs_delayed_ref_head
btrfs_cow_block
Btrfs natively supports back references, these tracepoints are helpful on
understanding btrfs's COW mechanism.
8) chunk:
btrfs_chunk_alloc
btrfs_chunk_free
Chunk is a link between physical offset and logical offset, and stands for space
infomation in btrfs, and these are helpful on tracing space things.
9) reserved_extent:
btrfs_reserved_extent_alloc
btrfs_reserved_extent_free
These can show how btrfs uses its space.
Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-03-24 19:18:59 +08:00
|
|
|
|
2014-01-23 22:21:38 +08:00
|
|
|
existing = htree_insert(&delayed_refs->href_root,
|
|
|
|
&head_ref->href_node);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
if (existing) {
|
2021-01-16 05:48:55 +08:00
|
|
|
update_existing_head_ref(trans, existing, head_ref);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
/*
|
|
|
|
* we've updated the existing ref, free the newly
|
|
|
|
* allocated ref
|
|
|
|
*/
|
2012-11-21 10:21:28 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
|
2014-01-23 22:21:38 +08:00
|
|
|
head_ref = existing;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
} else {
|
btrfs: reserve space for delayed refs on a per ref basis
Currently when reserving space for delayed refs we do it on a per ref head
basis. This is generally enough because most back refs for an extent end
up being inlined in the extent item - with the default leaf size of 16K we
can have at most 33 inline back refs (this is calculated by the macro
BTRFS_MAX_EXTENT_ITEM_SIZE()). The amount of bytes reserved for each ref
head is given by btrfs_calc_delayed_ref_bytes(), which basically
corresponds to a single path for insertion into the extent tree plus
another path for insertion into the free space tree if it's enabled.
However if we have reached the limit of inline refs or we have a mix of
inline and non-inline refs, then we will need to insert a non-inline ref
and update the existing extent item to update the total number of
references for the extent. This implies we need reserved space for two
insertion paths in the extent tree, but we only reserved for one path.
The extent item and the non-inline ref item may be located in different
leaves, or even if they are located in the same leaf, after updating the
extent item and before inserting the non-inline ref item, the extent
buffers in the btree path may have been written (due to memory pressure
for e.g.), in which case we need to COW the entire path again. In this
case since we have not reserved enough space for the delayed refs block
reserve, we will use the global block reserve.
If we are in a situation where the fs has no more unallocated space enough
to allocate a new metadata block group and available space in the existing
metadata block groups is close to the maximum size of the global block
reserve (512M), we may end up consuming too much of the free metadata
space to the point where we can't commit any future transaction because it
will fail, with -ENOSPC, during its commit when trying to allocate an
extent for some COW operation (running delayed refs generated by running
delayed refs or COWing the root tree's root node at commit_cowonly_roots()
for example). Such dramatic scenario can happen if we have many delayed
refs that require the insertion of non-inline ref items, due to too many
reflinks or snapshots. We also have situations where we use the global
block reserve because we could not in advance know that we will need
space to update some trees (block group creation for example), so this
all adds up to increase the chances of exhausting the global block reserve
and making any future transaction commit to fail with -ENOSPC and turn
the fs into RO mode, or fail the mount operation in case the mount needs
to start and commit a transaction, such as when we have orphans to cleanup
for example - such case was reported and hit by someone running a SLE
(SUSE Linux Enterprise) distribution for example - where the fs had no
more unallocated space that could be used to allocate a new metadata block
group, and the available metadata space was about 1.5M, not enough to
commit a transaction to cleanup an orphan inode (or do relocation of data
block groups that were far from being full).
So reserve space for delayed refs by individual refs and not by ref heads,
as we may need to COW multiple extent tree paths due to non-inline ref
items.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:35 +08:00
|
|
|
/*
|
|
|
|
* We reserve the amount of bytes needed to delete csums when
|
|
|
|
* adding the ref head and not when adding individual drop refs
|
|
|
|
* since the csum items are deleted only after running the last
|
|
|
|
* delayed drop ref (the data extent's ref count drops to 0).
|
|
|
|
*/
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
if (head_ref->is_data && head_ref->ref_mod < 0) {
|
2018-04-24 22:18:24 +08:00
|
|
|
delayed_refs->pending_csums += head_ref->num_bytes;
|
btrfs: stop doing excessive space reservation for csum deletion
Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:
1) It uses btrfs_calc_insert_metadata_size() which is excessive because
we only need to delete csum items from the csum tree, we don't need
to insert any items, so btrfs_calc_metadata_size() is all we need (as
it computes space needed to delete an item);
2) If the free space tree is enabled, it doubles the amount of space,
which is pointless for csum deletion since we don't need to touch the
free space tree or any other tree other than the csum tree.
So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.
For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:
$ cat test.sh
#!/bin/bash
DEV=/dev/nullb0
MNT=/mnt/test
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
# 100G gives at least 983040 extents with a size of 128K.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar
# Flush all delalloc and clear all metadata from memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
rm -f $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "rm took $dur milliseconds"
umount $MNT
Before this change rm took: 7504 milliseconds
After this change rm took: 6574 milliseconds (-12.4%)
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2023-09-09 01:20:37 +08:00
|
|
|
trans->delayed_ref_csum_deletions +=
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
btrfs_csum_bytes_to_leaves(trans->fs_info,
|
|
|
|
head_ref->num_bytes);
|
|
|
|
}
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
delayed_refs->num_heads++;
|
|
|
|
delayed_refs->num_heads_ready++;
|
2014-01-23 22:21:38 +08:00
|
|
|
atomic_inc(&delayed_refs->num_entries);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
}
|
2017-02-15 10:43:03 +08:00
|
|
|
if (qrecord_inserted_ret)
|
|
|
|
*qrecord_inserted_ret = qrecord_inserted;
|
2018-04-24 22:18:24 +08:00
|
|
|
|
2014-01-23 22:21:38 +08:00
|
|
|
return head_ref;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
}
|
|
|
|
|
2018-04-24 22:18:17 +08:00
|
|
|
/*
|
2023-09-08 07:09:25 +08:00
|
|
|
* Initialize the structure which represents a modification to a an extent.
|
2018-04-24 22:18:17 +08:00
|
|
|
*
|
|
|
|
* @fs_info: Internal to the mounted filesystem mount structure.
|
|
|
|
*
|
|
|
|
* @ref: The structure which is going to be initialized.
|
|
|
|
*
|
|
|
|
* @bytenr: The logical address of the extent for which a modification is
|
|
|
|
* going to be recorded.
|
|
|
|
*
|
|
|
|
* @num_bytes: Size of the extent whose modification is being recorded.
|
|
|
|
*
|
|
|
|
* @ref_root: The id of the root where this modification has originated, this
|
|
|
|
* can be either one of the well-known metadata trees or the
|
|
|
|
* subvolume id which references this extent.
|
|
|
|
*
|
|
|
|
* @action: Can be one of BTRFS_ADD_DELAYED_REF/BTRFS_DROP_DELAYED_REF or
|
|
|
|
* BTRFS_ADD_DELAYED_EXTENT
|
|
|
|
*
|
|
|
|
* @ref_type: Holds the type of the extent which is being recorded, can be
|
|
|
|
* one of BTRFS_SHARED_BLOCK_REF_KEY/BTRFS_TREE_BLOCK_REF_KEY
|
|
|
|
* when recording a metadata extent or BTRFS_SHARED_DATA_REF_KEY/
|
|
|
|
* BTRFS_EXTENT_DATA_REF_KEY when recording data extent
|
|
|
|
*/
|
|
|
|
static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
|
|
|
|
struct btrfs_delayed_ref_node *ref,
|
|
|
|
u64 bytenr, u64 num_bytes, u64 ref_root,
|
|
|
|
int action, u8 ref_type)
|
|
|
|
{
|
|
|
|
u64 seq = 0;
|
|
|
|
|
|
|
|
if (action == BTRFS_ADD_DELAYED_EXTENT)
|
|
|
|
action = BTRFS_ADD_DELAYED_REF;
|
|
|
|
|
|
|
|
if (is_fstree(ref_root))
|
|
|
|
seq = atomic64_read(&fs_info->tree_mod_seq);
|
|
|
|
|
|
|
|
refcount_set(&ref->refs, 1);
|
|
|
|
ref->bytenr = bytenr;
|
|
|
|
ref->num_bytes = num_bytes;
|
|
|
|
ref->ref_mod = 1;
|
|
|
|
ref->action = action;
|
|
|
|
ref->seq = seq;
|
|
|
|
ref->type = ref_type;
|
|
|
|
RB_CLEAR_NODE(&ref->ref_node);
|
|
|
|
INIT_LIST_HEAD(&ref->add_list);
|
|
|
|
}
|
|
|
|
|
2024-04-13 07:37:53 +08:00
|
|
|
void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 mod_root,
|
|
|
|
bool skip_qgroup)
|
2024-02-16 21:27:28 +08:00
|
|
|
{
|
|
|
|
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
|
|
|
|
/* If @real_root not set, use @root as fallback */
|
2024-04-13 07:37:53 +08:00
|
|
|
generic_ref->real_root = mod_root ?: generic_ref->ref_root;
|
2024-02-16 21:27:28 +08:00
|
|
|
#endif
|
|
|
|
generic_ref->tree_ref.level = level;
|
|
|
|
generic_ref->type = BTRFS_REF_METADATA;
|
2024-04-13 07:37:53 +08:00
|
|
|
if (skip_qgroup || !(is_fstree(generic_ref->ref_root) &&
|
2024-02-16 21:27:28 +08:00
|
|
|
(!mod_root || is_fstree(mod_root))))
|
|
|
|
generic_ref->skip_qgroup = true;
|
|
|
|
else
|
|
|
|
generic_ref->skip_qgroup = false;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2024-04-13 07:37:53 +08:00
|
|
|
void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ino, u64 offset,
|
|
|
|
u64 mod_root, bool skip_qgroup)
|
2024-02-16 21:27:28 +08:00
|
|
|
{
|
|
|
|
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
|
|
|
|
/* If @real_root not set, use @root as fallback */
|
2024-04-13 07:37:53 +08:00
|
|
|
generic_ref->real_root = mod_root ?: generic_ref->ref_root;
|
2024-02-16 21:27:28 +08:00
|
|
|
#endif
|
|
|
|
generic_ref->data_ref.ino = ino;
|
|
|
|
generic_ref->data_ref.offset = offset;
|
|
|
|
generic_ref->type = BTRFS_REF_DATA;
|
2024-04-13 07:37:53 +08:00
|
|
|
if (skip_qgroup || !(is_fstree(generic_ref->ref_root) &&
|
2024-02-16 21:27:28 +08:00
|
|
|
(!mod_root || is_fstree(mod_root))))
|
|
|
|
generic_ref->skip_qgroup = true;
|
|
|
|
else
|
|
|
|
generic_ref->skip_qgroup = false;
|
|
|
|
}
|
|
|
|
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
* add a delayed tree ref. This does all of the accounting required
|
2009-03-13 22:10:06 +08:00
|
|
|
* to make sure the delayed ref is eventually processed before this
|
|
|
|
* transaction commits.
|
|
|
|
*/
|
2018-06-20 20:48:53 +08:00
|
|
|
int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
|
2019-04-04 14:45:31 +08:00
|
|
|
struct btrfs_ref *generic_ref,
|
2021-01-16 05:48:55 +08:00
|
|
|
struct btrfs_delayed_extent_op *extent_op)
|
2009-03-13 22:10:06 +08:00
|
|
|
{
|
2018-06-20 20:48:53 +08:00
|
|
|
struct btrfs_fs_info *fs_info = trans->fs_info;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
struct btrfs_delayed_tree_ref *ref;
|
2024-04-13 04:42:28 +08:00
|
|
|
struct btrfs_delayed_ref_node *node;
|
2009-03-13 22:10:06 +08:00
|
|
|
struct btrfs_delayed_ref_head *head_ref;
|
|
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
2015-04-16 14:34:17 +08:00
|
|
|
struct btrfs_qgroup_extent_record *record = NULL;
|
2023-05-29 23:17:00 +08:00
|
|
|
bool qrecord_inserted;
|
2019-04-04 14:45:31 +08:00
|
|
|
bool is_system;
|
2023-05-29 23:17:01 +08:00
|
|
|
bool merged;
|
2019-04-04 14:45:31 +08:00
|
|
|
int action = generic_ref->action;
|
|
|
|
int level = generic_ref->tree_ref.level;
|
|
|
|
u64 bytenr = generic_ref->bytenr;
|
|
|
|
u64 num_bytes = generic_ref->len;
|
|
|
|
u64 parent = generic_ref->parent;
|
2018-04-24 22:18:20 +08:00
|
|
|
u8 ref_type;
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2024-04-13 07:37:53 +08:00
|
|
|
is_system = (generic_ref->ref_root == BTRFS_CHUNK_TREE_OBJECTID);
|
2019-04-04 14:45:31 +08:00
|
|
|
|
|
|
|
ASSERT(generic_ref->type == BTRFS_REF_METADATA && generic_ref->action);
|
2024-04-13 05:16:40 +08:00
|
|
|
node = kmem_cache_alloc(btrfs_delayed_ref_node_cachep, GFP_NOFS);
|
|
|
|
if (!node)
|
2009-03-13 22:10:06 +08:00
|
|
|
return -ENOMEM;
|
|
|
|
|
2018-06-20 23:43:12 +08:00
|
|
|
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
|
|
|
|
if (!head_ref) {
|
2024-04-13 05:16:40 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
|
2018-06-20 23:43:12 +08:00
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
2023-11-07 04:17:37 +08:00
|
|
|
if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
|
btrfs: qgroup: Move reserved data accounting from btrfs_delayed_ref_head to btrfs_qgroup_extent_record
[BUG]
Btrfs/139 will fail with a high probability if the testing machine (VM)
has only 2G RAM.
Resulting the final write success while it should fail due to EDQUOT,
and the fs will have quota exceeding the limit by 16K.
The simplified reproducer will be: (needs a 2G ram VM)
$ mkfs.btrfs -f $dev
$ mount $dev $mnt
$ btrfs subv create $mnt/subv
$ btrfs quota enable $mnt
$ btrfs quota rescan -w $mnt
$ btrfs qgroup limit -e 1G $mnt/subv
$ for i in $(seq -w 1 8); do
xfs_io -f -c "pwrite 0 128M" $mnt/subv/file_$i > /dev/null
echo "file $i written" > /dev/kmsg
done
$ sync
$ btrfs qgroup show -pcre --raw $mnt
The last pwrite will not trigger EDQUOT and final 'qgroup show' will
show something like:
qgroupid rfer excl max_rfer max_excl parent child
-------- ---- ---- -------- -------- ------ -----
0/5 16384 16384 none none --- ---
0/256 1073758208 1073758208 none 1073741824 --- ---
And 1073758208 is larger than
> 1073741824.
[CAUSE]
It's a bug in btrfs qgroup data reserved space management.
For quota limit, we must ensure that:
reserved (data + metadata) + rfer/excl <= limit
Since rfer/excl is only updated at transaction commmit time, reserved
space needs to be taken special care.
One important part of reserved space is data, and for a new data extent
written to disk, we still need to take the reserved space until
rfer/excl numbers get updated.
Originally when an ordered extent finishes, we migrate the reserved
qgroup data space from extent_io tree to delayed ref head of the data
extent, expecting delayed ref will only be cleaned up at commit
transaction time.
However for small RAM machine, due to memory pressure dirty pages can be
flushed back to disk without committing a transaction.
The related events will be something like:
file 1 written
btrfs_finish_ordered_io: ino=258 ordered offset=0 len=54947840
btrfs_finish_ordered_io: ino=258 ordered offset=54947840 len=5636096
btrfs_finish_ordered_io: ino=258 ordered offset=61153280 len=57344
btrfs_finish_ordered_io: ino=258 ordered offset=61210624 len=8192
btrfs_finish_ordered_io: ino=258 ordered offset=60583936 len=569344
cleanup_ref_head: num_bytes=54947840
cleanup_ref_head: num_bytes=5636096
cleanup_ref_head: num_bytes=569344
cleanup_ref_head: num_bytes=57344
cleanup_ref_head: num_bytes=8192
^^^^^^^^^^^^^^^^ This will free qgroup data reserved space
file 2 written
...
file 8 written
cleanup_ref_head: num_bytes=8192
...
btrfs_commit_transaction <<< the only transaction committed during
the test
When file 2 is written, we have already freed 128M reserved qgroup data
space for ino 258. Thus later write won't trigger EDQUOT.
This allows us to write more data beyond qgroup limit.
In my 2G ram VM, it could reach about 1.2G before hitting EDQUOT.
[FIX]
By moving reserved qgroup data space from btrfs_delayed_ref_head to
btrfs_qgroup_extent_record, we can ensure that reserved qgroup data
space won't be freed half way before commit transaction, thus fix the
problem.
Fixes: f64d5ca86821 ("btrfs: delayed_ref: Add new function to record reserved space into delayed ref")
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2019-01-23 15:15:12 +08:00
|
|
|
record = kzalloc(sizeof(*record), GFP_NOFS);
|
2018-06-20 23:43:12 +08:00
|
|
|
if (!record) {
|
2024-04-13 05:16:40 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
|
2018-06-20 23:43:12 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2024-04-13 05:16:40 +08:00
|
|
|
ref = btrfs_delayed_node_to_tree_ref(node);
|
2024-04-13 04:42:28 +08:00
|
|
|
|
2018-04-24 22:18:20 +08:00
|
|
|
if (parent)
|
|
|
|
ref_type = BTRFS_SHARED_BLOCK_REF_KEY;
|
|
|
|
else
|
|
|
|
ref_type = BTRFS_TREE_BLOCK_REF_KEY;
|
2018-06-20 23:43:12 +08:00
|
|
|
|
2024-04-13 04:42:28 +08:00
|
|
|
init_delayed_ref_common(fs_info, node, bytenr, num_bytes,
|
2024-04-13 07:37:53 +08:00
|
|
|
generic_ref->ref_root, action, ref_type);
|
|
|
|
ref->root = generic_ref->ref_root;
|
2018-04-24 22:18:20 +08:00
|
|
|
ref->parent = parent;
|
|
|
|
ref->level = level;
|
|
|
|
|
2018-04-24 22:18:24 +08:00
|
|
|
init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
|
2024-04-13 07:37:53 +08:00
|
|
|
generic_ref->ref_root, 0, action,
|
2023-06-29 05:03:35 +08:00
|
|
|
false, is_system, generic_ref->owning_root);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
head_ref->extent_op = extent_op;
|
|
|
|
|
|
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
|
|
|
spin_lock(&delayed_refs->lock);
|
|
|
|
|
2009-03-13 22:10:06 +08:00
|
|
|
/*
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
* insert both the head node and the new ref without dropping
|
|
|
|
* the spin lock
|
2009-03-13 22:10:06 +08:00
|
|
|
*/
|
2018-04-24 22:18:24 +08:00
|
|
|
head_ref = add_delayed_ref_head(trans, head_ref, record,
|
2021-01-16 05:48:55 +08:00
|
|
|
action, &qrecord_inserted);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
|
2024-04-13 04:42:28 +08:00
|
|
|
merged = insert_delayed_ref(trans, head_ref, node);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
spin_unlock(&delayed_refs->lock);
|
2012-05-29 23:06:54 +08:00
|
|
|
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
/*
|
|
|
|
* Need to update the delayed_refs_rsv with any changes we may have
|
|
|
|
* made.
|
|
|
|
*/
|
|
|
|
btrfs_update_delayed_refs_rsv(trans);
|
|
|
|
|
2024-04-13 04:42:28 +08:00
|
|
|
trace_add_delayed_tree_ref(fs_info, node, ref,
|
2018-04-24 22:18:20 +08:00
|
|
|
action == BTRFS_ADD_DELAYED_EXTENT ?
|
|
|
|
BTRFS_ADD_DELAYED_REF : action);
|
2023-05-29 23:17:01 +08:00
|
|
|
if (merged)
|
2024-04-13 05:16:40 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
|
2018-04-24 22:18:20 +08:00
|
|
|
|
2017-02-15 10:43:03 +08:00
|
|
|
if (qrecord_inserted)
|
btrfs: fix lock inversion problem when doing qgroup extent tracing
At btrfs_qgroup_trace_extent_post() we call btrfs_find_all_roots() with a
NULL value as the transaction handle argument, which makes that function
take the commit_root_sem semaphore, which is necessary when we don't hold
a transaction handle or any other mechanism to prevent a transaction
commit from wiping out commit roots.
However btrfs_qgroup_trace_extent_post() can be called in a context where
we are holding a write lock on an extent buffer from a subvolume tree,
namely from btrfs_truncate_inode_items(), called either during truncate
or unlink operations. In this case we end up with a lock inversion problem
because the commit_root_sem is a higher level lock, always supposed to be
acquired before locking any extent buffer.
Lockdep detects this lock inversion problem since we switched the extent
buffer locks from custom locks to semaphores, and when running btrfs/158
from fstests, it reported the following trace:
[ 9057.626435] ======================================================
[ 9057.627541] WARNING: possible circular locking dependency detected
[ 9057.628334] 5.14.0-rc2-btrfs-next-93 #1 Not tainted
[ 9057.628961] ------------------------------------------------------
[ 9057.629867] kworker/u16:4/30781 is trying to acquire lock:
[ 9057.630824] ffff8e2590f58760 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.632542]
but task is already holding lock:
[ 9057.633551] ffff8e25582d4b70 (&fs_info->commit_root_sem){++++}-{3:3}, at: iterate_extent_inodes+0x10b/0x280 [btrfs]
[ 9057.635255]
which lock already depends on the new lock.
[ 9057.636292]
the existing dependency chain (in reverse order) is:
[ 9057.637240]
-> #1 (&fs_info->commit_root_sem){++++}-{3:3}:
[ 9057.638138] down_read+0x46/0x140
[ 9057.638648] btrfs_find_all_roots+0x41/0x80 [btrfs]
[ 9057.639398] btrfs_qgroup_trace_extent_post+0x37/0x70 [btrfs]
[ 9057.640283] btrfs_add_delayed_data_ref+0x418/0x490 [btrfs]
[ 9057.641114] btrfs_free_extent+0x35/0xb0 [btrfs]
[ 9057.641819] btrfs_truncate_inode_items+0x424/0xf70 [btrfs]
[ 9057.642643] btrfs_evict_inode+0x454/0x4f0 [btrfs]
[ 9057.643418] evict+0xcf/0x1d0
[ 9057.643895] do_unlinkat+0x1e9/0x300
[ 9057.644525] do_syscall_64+0x3b/0xc0
[ 9057.645110] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 9057.645835]
-> #0 (btrfs-tree-00){++++}-{3:3}:
[ 9057.646600] __lock_acquire+0x130e/0x2210
[ 9057.647248] lock_acquire+0xd7/0x310
[ 9057.647773] down_read_nested+0x4b/0x140
[ 9057.648350] __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.649175] btrfs_read_lock_root_node+0x31/0x40 [btrfs]
[ 9057.650010] btrfs_search_slot+0x537/0xc00 [btrfs]
[ 9057.650849] scrub_print_warning_inode+0x89/0x370 [btrfs]
[ 9057.651733] iterate_extent_inodes+0x1e3/0x280 [btrfs]
[ 9057.652501] scrub_print_warning+0x15d/0x2f0 [btrfs]
[ 9057.653264] scrub_handle_errored_block.isra.0+0x135f/0x1640 [btrfs]
[ 9057.654295] scrub_bio_end_io_worker+0x101/0x2e0 [btrfs]
[ 9057.655111] btrfs_work_helper+0xf8/0x400 [btrfs]
[ 9057.655831] process_one_work+0x247/0x5a0
[ 9057.656425] worker_thread+0x55/0x3c0
[ 9057.656993] kthread+0x155/0x180
[ 9057.657494] ret_from_fork+0x22/0x30
[ 9057.658030]
other info that might help us debug this:
[ 9057.659064] Possible unsafe locking scenario:
[ 9057.659824] CPU0 CPU1
[ 9057.660402] ---- ----
[ 9057.660988] lock(&fs_info->commit_root_sem);
[ 9057.661581] lock(btrfs-tree-00);
[ 9057.662348] lock(&fs_info->commit_root_sem);
[ 9057.663254] lock(btrfs-tree-00);
[ 9057.663690]
*** DEADLOCK ***
[ 9057.664437] 4 locks held by kworker/u16:4/30781:
[ 9057.665023] #0: ffff8e25922a1148 ((wq_completion)btrfs-scrub){+.+.}-{0:0}, at: process_one_work+0x1c7/0x5a0
[ 9057.666260] #1: ffffabb3451ffe70 ((work_completion)(&work->normal_work)){+.+.}-{0:0}, at: process_one_work+0x1c7/0x5a0
[ 9057.667639] #2: ffff8e25922da198 (&ret->mutex){+.+.}-{3:3}, at: scrub_handle_errored_block.isra.0+0x5d2/0x1640 [btrfs]
[ 9057.669017] #3: ffff8e25582d4b70 (&fs_info->commit_root_sem){++++}-{3:3}, at: iterate_extent_inodes+0x10b/0x280 [btrfs]
[ 9057.670408]
stack backtrace:
[ 9057.670976] CPU: 7 PID: 30781 Comm: kworker/u16:4 Not tainted 5.14.0-rc2-btrfs-next-93 #1
[ 9057.672030] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[ 9057.673492] Workqueue: btrfs-scrub btrfs_work_helper [btrfs]
[ 9057.674258] Call Trace:
[ 9057.674588] dump_stack_lvl+0x57/0x72
[ 9057.675083] check_noncircular+0xf3/0x110
[ 9057.675611] __lock_acquire+0x130e/0x2210
[ 9057.676132] lock_acquire+0xd7/0x310
[ 9057.676605] ? __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.677313] ? lock_is_held_type+0xe8/0x140
[ 9057.677849] down_read_nested+0x4b/0x140
[ 9057.678349] ? __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.679068] __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.679760] btrfs_read_lock_root_node+0x31/0x40 [btrfs]
[ 9057.680458] btrfs_search_slot+0x537/0xc00 [btrfs]
[ 9057.681083] ? _raw_spin_unlock+0x29/0x40
[ 9057.681594] ? btrfs_find_all_roots_safe+0x11f/0x140 [btrfs]
[ 9057.682336] scrub_print_warning_inode+0x89/0x370 [btrfs]
[ 9057.683058] ? btrfs_find_all_roots_safe+0x11f/0x140 [btrfs]
[ 9057.683834] ? scrub_write_block_to_dev_replace+0xb0/0xb0 [btrfs]
[ 9057.684632] iterate_extent_inodes+0x1e3/0x280 [btrfs]
[ 9057.685316] scrub_print_warning+0x15d/0x2f0 [btrfs]
[ 9057.685977] ? ___ratelimit+0xa4/0x110
[ 9057.686460] scrub_handle_errored_block.isra.0+0x135f/0x1640 [btrfs]
[ 9057.687316] scrub_bio_end_io_worker+0x101/0x2e0 [btrfs]
[ 9057.688021] btrfs_work_helper+0xf8/0x400 [btrfs]
[ 9057.688649] ? lock_is_held_type+0xe8/0x140
[ 9057.689180] process_one_work+0x247/0x5a0
[ 9057.689696] worker_thread+0x55/0x3c0
[ 9057.690175] ? process_one_work+0x5a0/0x5a0
[ 9057.690731] kthread+0x155/0x180
[ 9057.691158] ? set_kthread_struct+0x40/0x40
[ 9057.691697] ret_from_fork+0x22/0x30
Fix this by making btrfs_find_all_roots() never attempt to lock the
commit_root_sem when it is called from btrfs_qgroup_trace_extent_post().
We can't just pass a non-NULL transaction handle to btrfs_find_all_roots()
from btrfs_qgroup_trace_extent_post(), because that would make backref
lookup not use commit roots and acquire read locks on extent buffers, and
therefore could deadlock when btrfs_qgroup_trace_extent_post() is called
from the btrfs_truncate_inode_items() code path which has acquired a write
lock on an extent buffer of the subvolume btree.
CC: stable@vger.kernel.org # 4.19+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-22 00:31:48 +08:00
|
|
|
btrfs_qgroup_trace_extent_post(trans, record);
|
2018-01-29 21:53:01 +08:00
|
|
|
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
|
|
|
|
*/
|
2018-06-20 20:48:54 +08:00
|
|
|
int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
|
2019-04-04 14:45:32 +08:00
|
|
|
struct btrfs_ref *generic_ref,
|
2021-01-16 05:48:55 +08:00
|
|
|
u64 reserved)
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
{
|
2018-06-20 20:48:54 +08:00
|
|
|
struct btrfs_fs_info *fs_info = trans->fs_info;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
struct btrfs_delayed_data_ref *ref;
|
2024-04-13 04:42:28 +08:00
|
|
|
struct btrfs_delayed_ref_node *node;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
struct btrfs_delayed_ref_head *head_ref;
|
|
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
2015-04-16 14:34:17 +08:00
|
|
|
struct btrfs_qgroup_extent_record *record = NULL;
|
2023-05-29 23:17:00 +08:00
|
|
|
bool qrecord_inserted;
|
2019-04-04 14:45:32 +08:00
|
|
|
int action = generic_ref->action;
|
2023-05-29 23:17:01 +08:00
|
|
|
bool merged;
|
2019-04-04 14:45:32 +08:00
|
|
|
u64 bytenr = generic_ref->bytenr;
|
|
|
|
u64 num_bytes = generic_ref->len;
|
|
|
|
u64 parent = generic_ref->parent;
|
2024-04-13 07:37:53 +08:00
|
|
|
u64 ref_root = generic_ref->ref_root;
|
2019-04-04 14:45:32 +08:00
|
|
|
u64 owner = generic_ref->data_ref.ino;
|
|
|
|
u64 offset = generic_ref->data_ref.offset;
|
2018-04-24 22:18:21 +08:00
|
|
|
u8 ref_type;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
|
2019-04-04 14:45:32 +08:00
|
|
|
ASSERT(generic_ref->type == BTRFS_REF_DATA && action);
|
2024-04-13 05:16:40 +08:00
|
|
|
node = kmem_cache_alloc(btrfs_delayed_ref_node_cachep, GFP_NOFS);
|
|
|
|
if (!node)
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
return -ENOMEM;
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2024-04-13 05:16:40 +08:00
|
|
|
ref = btrfs_delayed_node_to_data_ref(node);
|
2024-04-13 04:42:28 +08:00
|
|
|
|
2018-04-24 22:18:21 +08:00
|
|
|
if (parent)
|
|
|
|
ref_type = BTRFS_SHARED_DATA_REF_KEY;
|
|
|
|
else
|
|
|
|
ref_type = BTRFS_EXTENT_DATA_REF_KEY;
|
2024-04-13 04:42:28 +08:00
|
|
|
init_delayed_ref_common(fs_info, node, bytenr, num_bytes, ref_root,
|
|
|
|
action, ref_type);
|
2018-04-24 22:18:21 +08:00
|
|
|
ref->root = ref_root;
|
|
|
|
ref->parent = parent;
|
|
|
|
ref->objectid = owner;
|
|
|
|
ref->offset = offset;
|
|
|
|
|
|
|
|
|
2012-11-21 10:21:28 +08:00
|
|
|
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
|
2009-03-13 22:10:06 +08:00
|
|
|
if (!head_ref) {
|
2024-04-13 05:16:40 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
|
2009-03-13 22:10:06 +08:00
|
|
|
return -ENOMEM;
|
|
|
|
}
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
|
2023-11-07 04:17:37 +08:00
|
|
|
if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
|
btrfs: qgroup: Move reserved data accounting from btrfs_delayed_ref_head to btrfs_qgroup_extent_record
[BUG]
Btrfs/139 will fail with a high probability if the testing machine (VM)
has only 2G RAM.
Resulting the final write success while it should fail due to EDQUOT,
and the fs will have quota exceeding the limit by 16K.
The simplified reproducer will be: (needs a 2G ram VM)
$ mkfs.btrfs -f $dev
$ mount $dev $mnt
$ btrfs subv create $mnt/subv
$ btrfs quota enable $mnt
$ btrfs quota rescan -w $mnt
$ btrfs qgroup limit -e 1G $mnt/subv
$ for i in $(seq -w 1 8); do
xfs_io -f -c "pwrite 0 128M" $mnt/subv/file_$i > /dev/null
echo "file $i written" > /dev/kmsg
done
$ sync
$ btrfs qgroup show -pcre --raw $mnt
The last pwrite will not trigger EDQUOT and final 'qgroup show' will
show something like:
qgroupid rfer excl max_rfer max_excl parent child
-------- ---- ---- -------- -------- ------ -----
0/5 16384 16384 none none --- ---
0/256 1073758208 1073758208 none 1073741824 --- ---
And 1073758208 is larger than
> 1073741824.
[CAUSE]
It's a bug in btrfs qgroup data reserved space management.
For quota limit, we must ensure that:
reserved (data + metadata) + rfer/excl <= limit
Since rfer/excl is only updated at transaction commmit time, reserved
space needs to be taken special care.
One important part of reserved space is data, and for a new data extent
written to disk, we still need to take the reserved space until
rfer/excl numbers get updated.
Originally when an ordered extent finishes, we migrate the reserved
qgroup data space from extent_io tree to delayed ref head of the data
extent, expecting delayed ref will only be cleaned up at commit
transaction time.
However for small RAM machine, due to memory pressure dirty pages can be
flushed back to disk without committing a transaction.
The related events will be something like:
file 1 written
btrfs_finish_ordered_io: ino=258 ordered offset=0 len=54947840
btrfs_finish_ordered_io: ino=258 ordered offset=54947840 len=5636096
btrfs_finish_ordered_io: ino=258 ordered offset=61153280 len=57344
btrfs_finish_ordered_io: ino=258 ordered offset=61210624 len=8192
btrfs_finish_ordered_io: ino=258 ordered offset=60583936 len=569344
cleanup_ref_head: num_bytes=54947840
cleanup_ref_head: num_bytes=5636096
cleanup_ref_head: num_bytes=569344
cleanup_ref_head: num_bytes=57344
cleanup_ref_head: num_bytes=8192
^^^^^^^^^^^^^^^^ This will free qgroup data reserved space
file 2 written
...
file 8 written
cleanup_ref_head: num_bytes=8192
...
btrfs_commit_transaction <<< the only transaction committed during
the test
When file 2 is written, we have already freed 128M reserved qgroup data
space for ino 258. Thus later write won't trigger EDQUOT.
This allows us to write more data beyond qgroup limit.
In my 2G ram VM, it could reach about 1.2G before hitting EDQUOT.
[FIX]
By moving reserved qgroup data space from btrfs_delayed_ref_head to
btrfs_qgroup_extent_record, we can ensure that reserved qgroup data
space won't be freed half way before commit transaction, thus fix the
problem.
Fixes: f64d5ca86821 ("btrfs: delayed_ref: Add new function to record reserved space into delayed ref")
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2019-01-23 15:15:12 +08:00
|
|
|
record = kzalloc(sizeof(*record), GFP_NOFS);
|
2015-04-16 14:34:17 +08:00
|
|
|
if (!record) {
|
2024-04-13 05:16:40 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
|
2015-04-16 14:34:17 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_head_cachep,
|
|
|
|
head_ref);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-04-24 22:18:24 +08:00
|
|
|
init_delayed_ref_head(head_ref, record, bytenr, num_bytes, ref_root,
|
2023-06-29 05:03:35 +08:00
|
|
|
reserved, action, true, false, generic_ref->owning_root);
|
2016-12-14 03:39:34 +08:00
|
|
|
head_ref->extent_op = NULL;
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
|
2009-03-13 22:10:06 +08:00
|
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
|
|
|
spin_lock(&delayed_refs->lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* insert both the head node and the new ref without dropping
|
|
|
|
* the spin lock
|
|
|
|
*/
|
2018-04-24 22:18:24 +08:00
|
|
|
head_ref = add_delayed_ref_head(trans, head_ref, record,
|
2021-01-16 05:48:55 +08:00
|
|
|
action, &qrecord_inserted);
|
2009-03-13 22:10:06 +08:00
|
|
|
|
2024-04-13 04:42:28 +08:00
|
|
|
merged = insert_delayed_ref(trans, head_ref, node);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
spin_unlock(&delayed_refs->lock);
|
2012-05-29 23:06:54 +08:00
|
|
|
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
/*
|
|
|
|
* Need to update the delayed_refs_rsv with any changes we may have
|
|
|
|
* made.
|
|
|
|
*/
|
|
|
|
btrfs_update_delayed_refs_rsv(trans);
|
|
|
|
|
2024-04-13 04:42:28 +08:00
|
|
|
trace_add_delayed_data_ref(trans->fs_info, node, ref,
|
2018-04-24 22:18:21 +08:00
|
|
|
action == BTRFS_ADD_DELAYED_EXTENT ?
|
|
|
|
BTRFS_ADD_DELAYED_REF : action);
|
2023-05-29 23:17:01 +08:00
|
|
|
if (merged)
|
2024-04-13 05:16:40 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_node_cachep, node);
|
2018-04-24 22:18:21 +08:00
|
|
|
|
|
|
|
|
2017-02-15 10:43:03 +08:00
|
|
|
if (qrecord_inserted)
|
btrfs: fix lock inversion problem when doing qgroup extent tracing
At btrfs_qgroup_trace_extent_post() we call btrfs_find_all_roots() with a
NULL value as the transaction handle argument, which makes that function
take the commit_root_sem semaphore, which is necessary when we don't hold
a transaction handle or any other mechanism to prevent a transaction
commit from wiping out commit roots.
However btrfs_qgroup_trace_extent_post() can be called in a context where
we are holding a write lock on an extent buffer from a subvolume tree,
namely from btrfs_truncate_inode_items(), called either during truncate
or unlink operations. In this case we end up with a lock inversion problem
because the commit_root_sem is a higher level lock, always supposed to be
acquired before locking any extent buffer.
Lockdep detects this lock inversion problem since we switched the extent
buffer locks from custom locks to semaphores, and when running btrfs/158
from fstests, it reported the following trace:
[ 9057.626435] ======================================================
[ 9057.627541] WARNING: possible circular locking dependency detected
[ 9057.628334] 5.14.0-rc2-btrfs-next-93 #1 Not tainted
[ 9057.628961] ------------------------------------------------------
[ 9057.629867] kworker/u16:4/30781 is trying to acquire lock:
[ 9057.630824] ffff8e2590f58760 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.632542]
but task is already holding lock:
[ 9057.633551] ffff8e25582d4b70 (&fs_info->commit_root_sem){++++}-{3:3}, at: iterate_extent_inodes+0x10b/0x280 [btrfs]
[ 9057.635255]
which lock already depends on the new lock.
[ 9057.636292]
the existing dependency chain (in reverse order) is:
[ 9057.637240]
-> #1 (&fs_info->commit_root_sem){++++}-{3:3}:
[ 9057.638138] down_read+0x46/0x140
[ 9057.638648] btrfs_find_all_roots+0x41/0x80 [btrfs]
[ 9057.639398] btrfs_qgroup_trace_extent_post+0x37/0x70 [btrfs]
[ 9057.640283] btrfs_add_delayed_data_ref+0x418/0x490 [btrfs]
[ 9057.641114] btrfs_free_extent+0x35/0xb0 [btrfs]
[ 9057.641819] btrfs_truncate_inode_items+0x424/0xf70 [btrfs]
[ 9057.642643] btrfs_evict_inode+0x454/0x4f0 [btrfs]
[ 9057.643418] evict+0xcf/0x1d0
[ 9057.643895] do_unlinkat+0x1e9/0x300
[ 9057.644525] do_syscall_64+0x3b/0xc0
[ 9057.645110] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 9057.645835]
-> #0 (btrfs-tree-00){++++}-{3:3}:
[ 9057.646600] __lock_acquire+0x130e/0x2210
[ 9057.647248] lock_acquire+0xd7/0x310
[ 9057.647773] down_read_nested+0x4b/0x140
[ 9057.648350] __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.649175] btrfs_read_lock_root_node+0x31/0x40 [btrfs]
[ 9057.650010] btrfs_search_slot+0x537/0xc00 [btrfs]
[ 9057.650849] scrub_print_warning_inode+0x89/0x370 [btrfs]
[ 9057.651733] iterate_extent_inodes+0x1e3/0x280 [btrfs]
[ 9057.652501] scrub_print_warning+0x15d/0x2f0 [btrfs]
[ 9057.653264] scrub_handle_errored_block.isra.0+0x135f/0x1640 [btrfs]
[ 9057.654295] scrub_bio_end_io_worker+0x101/0x2e0 [btrfs]
[ 9057.655111] btrfs_work_helper+0xf8/0x400 [btrfs]
[ 9057.655831] process_one_work+0x247/0x5a0
[ 9057.656425] worker_thread+0x55/0x3c0
[ 9057.656993] kthread+0x155/0x180
[ 9057.657494] ret_from_fork+0x22/0x30
[ 9057.658030]
other info that might help us debug this:
[ 9057.659064] Possible unsafe locking scenario:
[ 9057.659824] CPU0 CPU1
[ 9057.660402] ---- ----
[ 9057.660988] lock(&fs_info->commit_root_sem);
[ 9057.661581] lock(btrfs-tree-00);
[ 9057.662348] lock(&fs_info->commit_root_sem);
[ 9057.663254] lock(btrfs-tree-00);
[ 9057.663690]
*** DEADLOCK ***
[ 9057.664437] 4 locks held by kworker/u16:4/30781:
[ 9057.665023] #0: ffff8e25922a1148 ((wq_completion)btrfs-scrub){+.+.}-{0:0}, at: process_one_work+0x1c7/0x5a0
[ 9057.666260] #1: ffffabb3451ffe70 ((work_completion)(&work->normal_work)){+.+.}-{0:0}, at: process_one_work+0x1c7/0x5a0
[ 9057.667639] #2: ffff8e25922da198 (&ret->mutex){+.+.}-{3:3}, at: scrub_handle_errored_block.isra.0+0x5d2/0x1640 [btrfs]
[ 9057.669017] #3: ffff8e25582d4b70 (&fs_info->commit_root_sem){++++}-{3:3}, at: iterate_extent_inodes+0x10b/0x280 [btrfs]
[ 9057.670408]
stack backtrace:
[ 9057.670976] CPU: 7 PID: 30781 Comm: kworker/u16:4 Not tainted 5.14.0-rc2-btrfs-next-93 #1
[ 9057.672030] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[ 9057.673492] Workqueue: btrfs-scrub btrfs_work_helper [btrfs]
[ 9057.674258] Call Trace:
[ 9057.674588] dump_stack_lvl+0x57/0x72
[ 9057.675083] check_noncircular+0xf3/0x110
[ 9057.675611] __lock_acquire+0x130e/0x2210
[ 9057.676132] lock_acquire+0xd7/0x310
[ 9057.676605] ? __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.677313] ? lock_is_held_type+0xe8/0x140
[ 9057.677849] down_read_nested+0x4b/0x140
[ 9057.678349] ? __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.679068] __btrfs_tree_read_lock+0x24/0x110 [btrfs]
[ 9057.679760] btrfs_read_lock_root_node+0x31/0x40 [btrfs]
[ 9057.680458] btrfs_search_slot+0x537/0xc00 [btrfs]
[ 9057.681083] ? _raw_spin_unlock+0x29/0x40
[ 9057.681594] ? btrfs_find_all_roots_safe+0x11f/0x140 [btrfs]
[ 9057.682336] scrub_print_warning_inode+0x89/0x370 [btrfs]
[ 9057.683058] ? btrfs_find_all_roots_safe+0x11f/0x140 [btrfs]
[ 9057.683834] ? scrub_write_block_to_dev_replace+0xb0/0xb0 [btrfs]
[ 9057.684632] iterate_extent_inodes+0x1e3/0x280 [btrfs]
[ 9057.685316] scrub_print_warning+0x15d/0x2f0 [btrfs]
[ 9057.685977] ? ___ratelimit+0xa4/0x110
[ 9057.686460] scrub_handle_errored_block.isra.0+0x135f/0x1640 [btrfs]
[ 9057.687316] scrub_bio_end_io_worker+0x101/0x2e0 [btrfs]
[ 9057.688021] btrfs_work_helper+0xf8/0x400 [btrfs]
[ 9057.688649] ? lock_is_held_type+0xe8/0x140
[ 9057.689180] process_one_work+0x247/0x5a0
[ 9057.689696] worker_thread+0x55/0x3c0
[ 9057.690175] ? process_one_work+0x5a0/0x5a0
[ 9057.690731] kthread+0x155/0x180
[ 9057.691158] ? set_kthread_struct+0x40/0x40
[ 9057.691697] ret_from_fork+0x22/0x30
Fix this by making btrfs_find_all_roots() never attempt to lock the
commit_root_sem when it is called from btrfs_qgroup_trace_extent_post().
We can't just pass a non-NULL transaction handle to btrfs_find_all_roots()
from btrfs_qgroup_trace_extent_post(), because that would make backref
lookup not use commit roots and acquire read locks on extent buffers, and
therefore could deadlock when btrfs_qgroup_trace_extent_post() is called
from the btrfs_truncate_inode_items() code path which has acquired a write
lock on an extent buffer of the subvolume btree.
CC: stable@vger.kernel.org # 4.19+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-22 00:31:48 +08:00
|
|
|
return btrfs_qgroup_trace_extent_post(trans, record);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-03-20 18:42:34 +08:00
|
|
|
int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
u64 bytenr, u64 num_bytes,
|
|
|
|
struct btrfs_delayed_extent_op *extent_op)
|
|
|
|
{
|
|
|
|
struct btrfs_delayed_ref_head *head_ref;
|
|
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
|
|
|
2012-11-21 10:21:28 +08:00
|
|
|
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
if (!head_ref)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2018-04-24 22:18:24 +08:00
|
|
|
init_delayed_ref_head(head_ref, NULL, bytenr, num_bytes, 0, 0,
|
2023-06-29 05:03:35 +08:00
|
|
|
BTRFS_UPDATE_DELAYED_HEAD, false, false, 0);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
head_ref->extent_op = extent_op;
|
|
|
|
|
|
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
|
|
|
spin_lock(&delayed_refs->lock);
|
|
|
|
|
2018-04-24 22:18:24 +08:00
|
|
|
add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD,
|
2021-01-16 05:48:55 +08:00
|
|
|
NULL);
|
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata.
Once a filesystem has been mounted with this commit, IT WILL NO LONGER
BE MOUNTABLE BY OLDER KERNELS.
When a tree block in subvolume tree is cow'd, the reference counts of all
extents it points to are increased by one. At transaction commit time,
the old root of the subvolume is recorded in a "dead root" data structure,
and the btree it points to is later walked, dropping reference counts
and freeing any blocks where the reference count goes to 0.
The increments done during cow and decrements done after commit cancel out,
and the walk is a very expensive way to go about freeing the blocks that
are no longer referenced by the new btree root. This commit reduces the
transaction overhead by avoiding the need for dead root records.
When a non-shared tree block is cow'd, we free the old block at once, and the
new block inherits old block's references. When a tree block with reference
count > 1 is cow'd, we increase the reference counts of all extents
the new block points to by one, and decrease the old block's reference count by
one.
This dead tree avoidance code removes the need to modify the reference
counts of lower level extents when a non-shared tree block is cow'd.
But we still need to update back ref for all pointers in the block.
This is because the location of the block is recorded in the back ref
item.
We can solve this by introducing a new type of back ref. The new
back ref provides information about pointer's key, level and in which
tree the pointer lives. This information allow us to find the pointer
by searching the tree. The shortcoming of the new back ref is that it
only works for pointers in tree blocks referenced by their owner trees.
This is mostly a problem for snapshots, where resolving one of these
fuzzy back references would be O(number_of_snapshots) and quite slow.
The solution used here is to use the fuzzy back references in the common
case where a given tree block is only referenced by one root,
and use the full back references when multiple roots have a reference
on a given block.
This commit adds per subvolume red-black tree to keep trace of cached
inodes. The red-black tree helps the balancing code to find cached
inodes whose inode numbers within a given range.
This commit improves the balancing code by introducing several data
structures to keep the state of balancing. The most important one
is the back ref cache. It caches how the upper level tree blocks are
referenced. This greatly reduce the overhead of checking back ref.
The improved balancing code scales significantly better with a large
number of snapshots.
This is a very large commit and was written in a number of
pieces. But, they depend heavily on the disk format change and were
squashed together to make sure git bisect didn't end up in a
bad state wrt space balancing or the format change.
Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-06-10 22:45:14 +08:00
|
|
|
|
2009-03-13 22:10:06 +08:00
|
|
|
spin_unlock(&delayed_refs->lock);
|
btrfs: introduce delayed_refs_rsv
Traditionally we've had voodoo in btrfs to account for the space that
delayed refs may take up by having a global_block_rsv. This works most
of the time, except when it doesn't. We've had issues reported and seen
in production where sometimes the global reserve is exhausted during
transaction commit before we can run all of our delayed refs, resulting
in an aborted transaction. Because of this voodoo we have equally
dubious flushing semantics around throttling delayed refs which we often
get wrong.
So instead give them their own block_rsv. This way we can always know
exactly how much outstanding space we need for delayed refs. This
allows us to make sure we are constantly filling that reservation up
with space, and allows us to put more precise pressure on the enospc
system. Instead of doing math to see if its a good time to throttle,
the normal enospc code will be invoked if we have a lot of delayed refs
pending, and they will be run via the normal flushing mechanism.
For now the delayed_refs_rsv will hold the reservations for the delayed
refs, the block group updates, and deleting csums. We could have a
separate rsv for the block group updates, but the csum deletion stuff is
still handled via the delayed_refs so that will stay there.
Historical background:
The global reserve has grown to cover everything we don't reserve space
explicitly for, and we've grown a lot of weird ad-hoc heuristics to know
if we're running short on space and when it's time to force a commit. A
failure rate of 20-40 file systems when we run hundreds of thousands of
them isn't super high, but cleaning up this code will make things less
ugly and more predictible.
Thus the delayed refs rsv. We always know how many delayed refs we have
outstanding, and although running them generates more we can use the
global reserve for that spill over, which fits better into it's desired
use than a full blown reservation. This first approach is to simply
take how many times we're reserving space for and multiply that by 2 in
order to save enough space for the delayed refs that could be generated.
This is a niave approach and will probably evolve, but for now it works.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com> # high-level review
[ added background notes from the cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
2018-12-03 23:20:33 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Need to update the delayed_refs_rsv with any changes we may have
|
|
|
|
* made.
|
|
|
|
*/
|
|
|
|
btrfs_update_delayed_refs_rsv(trans);
|
2009-03-13 22:10:06 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2024-02-16 21:27:28 +08:00
|
|
|
void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
|
|
|
|
{
|
|
|
|
if (refcount_dec_and_test(&ref->refs)) {
|
|
|
|
WARN_ON(!RB_EMPTY_NODE(&ref->ref_node));
|
2024-04-13 05:16:40 +08:00
|
|
|
kmem_cache_free(btrfs_delayed_ref_node_cachep, ref);
|
2024-02-16 21:27:28 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2009-03-13 22:11:24 +08:00
|
|
|
/*
|
2019-03-27 23:19:55 +08:00
|
|
|
* This does a simple search for the head node for a given extent. Returns the
|
|
|
|
* head node if found, or NULL if not.
|
2009-03-13 22:11:24 +08:00
|
|
|
*/
|
|
|
|
struct btrfs_delayed_ref_head *
|
2017-01-31 04:24:37 +08:00
|
|
|
btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 bytenr)
|
2009-03-13 22:11:24 +08:00
|
|
|
{
|
2019-03-27 23:19:55 +08:00
|
|
|
lockdep_assert_held(&delayed_refs->lock);
|
|
|
|
|
2018-10-11 13:40:38 +08:00
|
|
|
return find_ref_head(delayed_refs, bytenr, false);
|
2009-03-13 22:11:24 +08:00
|
|
|
}
|
2012-11-21 10:21:28 +08:00
|
|
|
|
2018-02-20 00:24:18 +08:00
|
|
|
void __cold btrfs_delayed_ref_exit(void)
|
2012-11-21 10:21:28 +08:00
|
|
|
{
|
2016-01-29 21:36:35 +08:00
|
|
|
kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
|
2024-04-13 05:16:40 +08:00
|
|
|
kmem_cache_destroy(btrfs_delayed_ref_node_cachep);
|
2016-01-29 21:36:35 +08:00
|
|
|
kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
|
2012-11-21 10:21:28 +08:00
|
|
|
}
|
|
|
|
|
2017-11-03 07:21:50 +08:00
|
|
|
int __init btrfs_delayed_ref_init(void)
|
2012-11-21 10:21:28 +08:00
|
|
|
{
|
2024-02-24 21:47:09 +08:00
|
|
|
btrfs_delayed_ref_head_cachep = KMEM_CACHE(btrfs_delayed_ref_head, 0);
|
2012-11-21 10:21:28 +08:00
|
|
|
if (!btrfs_delayed_ref_head_cachep)
|
|
|
|
goto fail;
|
|
|
|
|
2024-04-13 05:16:40 +08:00
|
|
|
btrfs_delayed_ref_node_cachep = KMEM_CACHE(btrfs_delayed_ref_node, 0);
|
|
|
|
if (!btrfs_delayed_ref_node_cachep)
|
2012-11-21 10:21:28 +08:00
|
|
|
goto fail;
|
|
|
|
|
2024-02-24 21:47:09 +08:00
|
|
|
btrfs_delayed_extent_op_cachep = KMEM_CACHE(btrfs_delayed_extent_op, 0);
|
2012-11-21 10:21:28 +08:00
|
|
|
if (!btrfs_delayed_extent_op_cachep)
|
|
|
|
goto fail;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
|
|
btrfs_delayed_ref_exit();
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|