2008-01-09 04:46:30 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public
|
|
|
|
* License v2 as published by the Free Software Foundation.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
* General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public
|
|
|
|
* License along with this program; if not, write to the
|
|
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
|
|
* Boston, MA 021110-1307, USA.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef __BTRFS_ORDERED_DATA__
|
|
|
|
#define __BTRFS_ORDERED_DATA__
|
|
|
|
|
2008-07-18 01:53:27 +08:00
|
|
|
/* one of these per inode */
|
2008-01-09 04:46:30 +08:00
|
|
|
struct btrfs_ordered_inode_tree {
|
2008-07-18 00:53:50 +08:00
|
|
|
struct mutex mutex;
|
2008-01-09 04:46:30 +08:00
|
|
|
struct rb_root tree;
|
2008-07-18 00:53:50 +08:00
|
|
|
struct rb_node *last;
|
2008-01-09 04:46:30 +08:00
|
|
|
};
|
|
|
|
|
2008-07-18 01:53:27 +08:00
|
|
|
/*
|
|
|
|
* these are used to collect checksums done just before bios submission.
|
|
|
|
* They are attached via a list into the ordered extent, and
|
|
|
|
* checksum items are inserted into the tree after all the blocks in
|
|
|
|
* the ordered extent are on disk
|
|
|
|
*/
|
2008-07-18 00:53:50 +08:00
|
|
|
struct btrfs_sector_sum {
|
Btrfs: move data checksumming into a dedicated tree
Btrfs stores checksums for each data block. Until now, they have
been stored in the subvolume trees, indexed by the inode that is
referencing the data block. This means that when we read the inode,
we've probably read in at least some checksums as well.
But, this has a few problems:
* The checksums are indexed by logical offset in the file. When
compression is on, this means we have to do the expensive checksumming
on the uncompressed data. It would be faster if we could checksum
the compressed data instead.
* If we implement encryption, we'll be checksumming the plain text and
storing that on disk. This is significantly less secure.
* For either compression or encryption, we have to get the plain text
back before we can verify the checksum as correct. This makes the raid
layer balancing and extent moving much more expensive.
* It makes the front end caching code more complex, as we have touch
the subvolume and inodes as we cache extents.
* There is potentitally one copy of the checksum in each subvolume
referencing an extent.
The solution used here is to store the extent checksums in a dedicated
tree. This allows us to index the checksums by phyiscal extent
start and length. It means:
* The checksum is against the data stored on disk, after any compression
or encryption is done.
* The checksum is stored in a central location, and can be verified without
following back references, or reading inodes.
This makes compression significantly faster by reducing the amount of
data that needs to be checksummed. It will also allow much faster
raid management code in general.
The checksums are indexed by a key with a fixed objectid (a magic value
in ctree.h) and offset set to the starting byte of the extent. This
allows us to copy the checksum items into the fsync log tree directly (or
any other tree), without having to invent a second format for them.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
|
|
|
/* bytenr on disk */
|
|
|
|
u64 bytenr;
|
2008-07-18 00:53:50 +08:00
|
|
|
u32 sum;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct btrfs_ordered_sum {
|
Btrfs: move data checksumming into a dedicated tree
Btrfs stores checksums for each data block. Until now, they have
been stored in the subvolume trees, indexed by the inode that is
referencing the data block. This means that when we read the inode,
we've probably read in at least some checksums as well.
But, this has a few problems:
* The checksums are indexed by logical offset in the file. When
compression is on, this means we have to do the expensive checksumming
on the uncompressed data. It would be faster if we could checksum
the compressed data instead.
* If we implement encryption, we'll be checksumming the plain text and
storing that on disk. This is significantly less secure.
* For either compression or encryption, we have to get the plain text
back before we can verify the checksum as correct. This makes the raid
layer balancing and extent moving much more expensive.
* It makes the front end caching code more complex, as we have touch
the subvolume and inodes as we cache extents.
* There is potentitally one copy of the checksum in each subvolume
referencing an extent.
The solution used here is to store the extent checksums in a dedicated
tree. This allows us to index the checksums by phyiscal extent
start and length. It means:
* The checksum is against the data stored on disk, after any compression
or encryption is done.
* The checksum is stored in a central location, and can be verified without
following back references, or reading inodes.
This makes compression significantly faster by reducing the amount of
data that needs to be checksummed. It will also allow much faster
raid management code in general.
The checksums are indexed by a key with a fixed objectid (a magic value
in ctree.h) and offset set to the starting byte of the extent. This
allows us to copy the checksum items into the fsync log tree directly (or
any other tree), without having to invent a second format for them.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
|
|
|
/* bytenr is the start of this extent on disk */
|
|
|
|
u64 bytenr;
|
|
|
|
|
2008-07-18 18:17:13 +08:00
|
|
|
/*
|
|
|
|
* this is the length in bytes covered by the sums array below.
|
|
|
|
*/
|
|
|
|
unsigned long len;
|
2008-07-18 00:53:50 +08:00
|
|
|
struct list_head list;
|
2008-07-18 01:53:27 +08:00
|
|
|
/* last field is a variable length array of btrfs_sector_sums */
|
2008-07-23 11:06:42 +08:00
|
|
|
struct btrfs_sector_sum sums[];
|
2008-07-18 00:53:50 +08:00
|
|
|
};
|
|
|
|
|
2008-07-18 01:53:27 +08:00
|
|
|
/*
|
|
|
|
* bits for the flags field:
|
|
|
|
*
|
|
|
|
* BTRFS_ORDERED_IO_DONE is set when all of the blocks are written.
|
|
|
|
* It is used to make sure metadata is inserted into the tree only once
|
|
|
|
* per extent.
|
|
|
|
*
|
|
|
|
* BTRFS_ORDERED_COMPLETE is set when the extent is removed from the
|
|
|
|
* rbtree, just before waking any waiters. It is used to indicate the
|
|
|
|
* IO is done and any metadata is inserted into the tree.
|
|
|
|
*/
|
2008-07-18 00:53:50 +08:00
|
|
|
#define BTRFS_ORDERED_IO_DONE 0 /* set when all the pages are written */
|
2008-07-18 01:53:27 +08:00
|
|
|
|
2008-07-18 00:53:50 +08:00
|
|
|
#define BTRFS_ORDERED_COMPLETE 1 /* set when removed from the tree */
|
|
|
|
|
2008-08-06 01:05:02 +08:00
|
|
|
#define BTRFS_ORDERED_NOCOW 2 /* set when we want to write in place */
|
|
|
|
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
#define BTRFS_ORDERED_COMPRESSED 3 /* writing a compressed extent */
|
|
|
|
|
2008-10-31 02:25:28 +08:00
|
|
|
#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to prealloced extent */
|
|
|
|
|
2008-07-18 00:53:50 +08:00
|
|
|
struct btrfs_ordered_extent {
|
2008-07-18 01:53:27 +08:00
|
|
|
/* logical offset in the file */
|
2008-07-18 00:53:50 +08:00
|
|
|
u64 file_offset;
|
2008-07-18 01:53:27 +08:00
|
|
|
|
|
|
|
/* disk byte number */
|
2008-07-18 00:53:50 +08:00
|
|
|
u64 start;
|
2008-07-18 01:53:27 +08:00
|
|
|
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
/* ram length of the extent in bytes */
|
2008-07-18 00:53:50 +08:00
|
|
|
u64 len;
|
2008-07-18 01:53:27 +08:00
|
|
|
|
Btrfs: Add zlib compression support
This is a large change for adding compression on reading and writing,
both for inline and regular extents. It does some fairly large
surgery to the writeback paths.
Compression is off by default and enabled by mount -o compress. Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.
If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.
* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler. This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.
* Inline extents are inserted at delalloc time now. This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.
* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.
From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field. Neither the encryption or the
'other' field are currently used.
In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k. This is a
software only limit, the disk format supports u64 sized compressed extents.
In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k. This is a software only limit
and will be subject to tuning later.
Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data. This way additional encodings can be
layered on without having to figure out which encoding to checksum.
Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread. This makes it tricky to
spread the compression load across all the cpus on the box. We'll have to
look at parallel pdflush walks of dirty inodes at a later time.
Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-10-30 02:49:59 +08:00
|
|
|
/* extent length on disk */
|
|
|
|
u64 disk_len;
|
|
|
|
|
2009-09-03 04:53:46 +08:00
|
|
|
/* number of bytes that still need writing */
|
|
|
|
u64 bytes_left;
|
|
|
|
|
2008-07-18 01:53:27 +08:00
|
|
|
/* flags (described above) */
|
2008-07-18 00:53:50 +08:00
|
|
|
unsigned long flags;
|
2008-07-18 01:53:27 +08:00
|
|
|
|
|
|
|
/* reference count */
|
2008-07-18 00:53:50 +08:00
|
|
|
atomic_t refs;
|
2008-07-18 01:53:27 +08:00
|
|
|
|
2008-07-24 23:57:52 +08:00
|
|
|
/* the inode we belong to */
|
|
|
|
struct inode *inode;
|
|
|
|
|
2008-07-18 01:53:27 +08:00
|
|
|
/* list of checksums for insertion when the extent io is done */
|
2008-07-18 00:53:50 +08:00
|
|
|
struct list_head list;
|
2008-07-18 01:53:27 +08:00
|
|
|
|
|
|
|
/* used to wait for the BTRFS_ORDERED_COMPLETE bit */
|
2008-07-18 00:53:50 +08:00
|
|
|
wait_queue_head_t wait;
|
2008-07-18 01:53:27 +08:00
|
|
|
|
|
|
|
/* our friendly rbtree entry */
|
2008-07-18 00:53:50 +08:00
|
|
|
struct rb_node rb_node;
|
2008-07-24 23:57:52 +08:00
|
|
|
|
|
|
|
/* a per root list of all the pending ordered extents */
|
|
|
|
struct list_head root_extent_list;
|
2008-07-18 00:53:50 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
2008-07-18 01:53:27 +08:00
|
|
|
/*
|
|
|
|
* calculates the total size you need to allocate for an ordered sum
|
|
|
|
* structure spanning 'bytes' in the file
|
|
|
|
*/
|
2008-07-23 21:26:26 +08:00
|
|
|
static inline int btrfs_ordered_sum_size(struct btrfs_root *root,
|
|
|
|
unsigned long bytes)
|
2008-07-18 00:53:50 +08:00
|
|
|
{
|
|
|
|
unsigned long num_sectors = (bytes + root->sectorsize - 1) /
|
|
|
|
root->sectorsize;
|
2008-07-18 18:17:13 +08:00
|
|
|
num_sectors++;
|
2008-07-18 00:53:50 +08:00
|
|
|
return sizeof(struct btrfs_ordered_sum) +
|
|
|
|
num_sectors * sizeof(struct btrfs_sector_sum);
|
|
|
|
}
|
|
|
|
|
2008-01-09 04:46:30 +08:00
|
|
|
static inline void
|
|
|
|
btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t)
|
|
|
|
{
|
2008-07-18 00:53:50 +08:00
|
|
|
mutex_init(&t->mutex);
|
2008-01-09 04:46:30 +08:00
|
|
|
t->tree.rb_node = NULL;
|
2008-07-18 00:53:50 +08:00
|
|
|
t->last = NULL;
|
2008-01-09 04:46:30 +08:00
|
|
|
}
|
|
|
|
|
2008-07-18 00:53:50 +08:00
|
|
|
int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
|
|
|
|
int btrfs_remove_ordered_extent(struct inode *inode,
|
|
|
|
struct btrfs_ordered_extent *entry);
|
|
|
|
int btrfs_dec_test_ordered_pending(struct inode *inode,
|
|
|
|
u64 file_offset, u64 io_size);
|
|
|
|
int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
|
2008-10-31 02:25:28 +08:00
|
|
|
u64 start, u64 len, u64 disk_len, int tyep);
|
2008-07-18 18:17:13 +08:00
|
|
|
int btrfs_add_ordered_sum(struct inode *inode,
|
|
|
|
struct btrfs_ordered_extent *entry,
|
|
|
|
struct btrfs_ordered_sum *sum);
|
2008-07-18 00:53:50 +08:00
|
|
|
struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
|
|
|
|
u64 file_offset);
|
2008-07-18 01:53:27 +08:00
|
|
|
void btrfs_start_ordered_extent(struct inode *inode,
|
|
|
|
struct btrfs_ordered_extent *entry, int wait);
|
2008-10-04 00:30:02 +08:00
|
|
|
int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
|
2008-07-18 00:53:50 +08:00
|
|
|
struct btrfs_ordered_extent *
|
|
|
|
btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset);
|
2008-07-18 00:54:05 +08:00
|
|
|
int btrfs_ordered_update_i_size(struct inode *inode,
|
|
|
|
struct btrfs_ordered_extent *ordered);
|
Btrfs: move data checksumming into a dedicated tree
Btrfs stores checksums for each data block. Until now, they have
been stored in the subvolume trees, indexed by the inode that is
referencing the data block. This means that when we read the inode,
we've probably read in at least some checksums as well.
But, this has a few problems:
* The checksums are indexed by logical offset in the file. When
compression is on, this means we have to do the expensive checksumming
on the uncompressed data. It would be faster if we could checksum
the compressed data instead.
* If we implement encryption, we'll be checksumming the plain text and
storing that on disk. This is significantly less secure.
* For either compression or encryption, we have to get the plain text
back before we can verify the checksum as correct. This makes the raid
layer balancing and extent moving much more expensive.
* It makes the front end caching code more complex, as we have touch
the subvolume and inodes as we cache extents.
* There is potentitally one copy of the checksum in each subvolume
referencing an extent.
The solution used here is to store the extent checksums in a dedicated
tree. This allows us to index the checksums by phyiscal extent
start and length. It means:
* The checksum is against the data stored on disk, after any compression
or encryption is done.
* The checksum is stored in a central location, and can be verified without
following back references, or reading inodes.
This makes compression significantly faster by reducing the amount of
data that needs to be checksummed. It will also allow much faster
raid management code in general.
The checksums are indexed by a key with a fixed objectid (a magic value
in ctree.h) and offset set to the starting byte of the extent. This
allows us to copy the checksum items into the fsync log tree directly (or
any other tree), without having to invent a second format for them.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-12-09 05:58:54 +08:00
|
|
|
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum);
|
2008-08-06 01:05:02 +08:00
|
|
|
int btrfs_wait_ordered_extents(struct btrfs_root *root, int nocow_only);
|
2009-04-01 01:27:11 +08:00
|
|
|
int btrfs_run_ordered_operations(struct btrfs_root *root, int wait);
|
|
|
|
int btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root,
|
|
|
|
struct inode *inode);
|
2008-01-09 04:46:30 +08:00
|
|
|
#endif
|