2007-06-12 15:07:21 +02:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
|
2007-02-02 15:18:22 +01:00
|
|
|
#ifndef __DISKIO__
|
|
|
|
#define __DISKIO__
|
|
|
|
|
2007-03-22 17:13:20 +01:00
|
|
|
#define BTRFS_SUPER_INFO_OFFSET (16 * 1024)
|
2008-04-10 22:19:33 +02:00
|
|
|
#define BTRFS_SUPER_INFO_SIZE 4096
|
2008-03-24 20:01:56 +01:00
|
|
|
struct btrfs_device;
|
2008-03-24 20:02:07 +01:00
|
|
|
struct btrfs_fs_devices;
|
2007-03-22 17:13:20 +01:00
|
|
|
|
2007-10-15 22:15:53 +02:00
|
|
|
struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
|
2008-05-12 18:59:19 +02:00
|
|
|
u32 blocksize, u64 parent_transid);
|
|
|
|
int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
|
|
|
|
u64 parent_transid);
|
2007-10-15 22:14:19 +02:00
|
|
|
struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
|
2007-10-15 22:15:53 +02:00
|
|
|
u64 bytenr, u32 blocksize);
|
2007-03-16 21:20:31 +01:00
|
|
|
int clean_tree_block(struct btrfs_trans_handle *trans,
|
2007-10-15 22:14:19 +02:00
|
|
|
struct btrfs_root *root, struct extent_buffer *buf);
|
2008-03-24 20:02:07 +01:00
|
|
|
struct btrfs_root *open_ctree(struct super_block *sb,
|
2008-05-13 19:46:40 +02:00
|
|
|
struct btrfs_fs_devices *fs_devices,
|
|
|
|
char *options);
|
2007-03-22 17:13:20 +01:00
|
|
|
int close_ctree(struct btrfs_root *root);
|
2007-03-22 20:59:16 +01:00
|
|
|
int write_ctree_super(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_root *root);
|
2008-11-12 20:34:12 +01:00
|
|
|
int btrfs_commit_super(struct btrfs_root *root);
|
2007-10-15 22:14:19 +02:00
|
|
|
struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
|
2007-10-15 22:15:53 +02:00
|
|
|
u64 bytenr, u32 blocksize);
|
2008-01-08 21:46:30 +01:00
|
|
|
struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
|
|
|
|
u64 root_objectid);
|
2007-04-09 16:42:37 +02:00
|
|
|
struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info,
|
2007-08-29 21:47:34 +02:00
|
|
|
struct btrfs_key *location,
|
|
|
|
const char *name, int namelen);
|
2008-09-05 22:13:11 +02:00
|
|
|
struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
|
2007-06-22 20:16:25 +02:00
|
|
|
struct btrfs_key *location);
|
2007-12-21 22:27:24 +01:00
|
|
|
struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
|
|
|
|
struct btrfs_key *location);
|
2008-11-12 20:34:12 +01:00
|
|
|
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
|
2007-04-12 16:43:05 +02:00
|
|
|
int btrfs_insert_dev_radix(struct btrfs_root *root,
|
|
|
|
struct block_device *bdev,
|
2007-04-12 18:14:00 +02:00
|
|
|
u64 device_id,
|
2007-04-12 16:43:05 +02:00
|
|
|
u64 block_start,
|
|
|
|
u64 num_blocks);
|
2007-09-17 16:58:06 +02:00
|
|
|
void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
|
2007-06-22 20:16:25 +02:00
|
|
|
int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root);
|
2007-10-15 22:14:19 +02:00
|
|
|
void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
|
2008-05-12 19:39:03 +02:00
|
|
|
int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid);
|
2007-10-15 22:14:19 +02:00
|
|
|
int btrfs_set_buffer_uptodate(struct extent_buffer *buf);
|
|
|
|
int wait_on_tree_block_writeback(struct btrfs_root *root,
|
|
|
|
struct extent_buffer *buf);
|
2008-05-12 18:59:19 +02:00
|
|
|
int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
|
2007-10-15 22:22:25 +02:00
|
|
|
u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len);
|
|
|
|
void btrfs_csum_final(u32 crc, char *result);
|
2008-03-24 20:01:56 +01:00
|
|
|
int btrfs_open_device(struct btrfs_device *dev);
|
2008-04-01 19:48:14 +02:00
|
|
|
int btrfs_verify_block_csum(struct btrfs_root *root,
|
|
|
|
struct extent_buffer *buf);
|
2008-04-09 22:28:12 +02:00
|
|
|
int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
|
|
|
|
int metadata);
|
2008-04-16 17:14:51 +02:00
|
|
|
int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
|
|
|
|
int rw, struct bio *bio, int mirror_num,
|
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>
2008-10-29 19:49:59 +01:00
|
|
|
unsigned long bio_flags,
|
Btrfs: Add ordered async work queues
Btrfs uses kernel threads to create async work queues for cpu intensive
operations such as checksumming and decompression. These work well,
but they make it difficult to keep IO order intact.
A single writepages call from pdflush or fsync will turn into a number
of bios, and each bio is checksummed in parallel. Once the checksum is
computed, the bio is sent down to the disk, and since we don't control
the order in which the parallel operations happen, they might go down to
the disk in almost any order.
The code deals with this somewhat by having deep work queues for a single
kernel thread, making it very likely that a single thread will process all
the bios for a single inode.
This patch introduces an explicitly ordered work queue. As work structs
are placed into the queue they are put onto the tail of a list. They have
three callbacks:
->func (cpu intensive processing here)
->ordered_func (order sensitive processing here)
->ordered_free (free the work struct, all processing is done)
The work struct has three callbacks. The func callback does the cpu intensive
work, and when it completes the work struct is marked as done.
Every time a work struct completes, the list is checked to see if the head
is marked as done. If so the ordered_func callback is used to do the
order sensitive processing and the ordered_free callback is used to do
any cleanup. Then we loop back and check the head of the list again.
This patch also changes the checksumming code to use the ordered workqueues.
One a 4 drive array, it increases streaming writes from 280MB/s to 350MB/s.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-11-07 04:03:00 +01:00
|
|
|
extent_submit_bio_hook_t *submit_bio_start,
|
|
|
|
extent_submit_bio_hook_t *submit_bio_done);
|
|
|
|
|
2008-08-15 21:34:15 +02:00
|
|
|
int btrfs_congested_async(struct btrfs_fs_info *info, int iodone);
|
2008-08-20 19:39:41 +02:00
|
|
|
unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info);
|
2008-09-05 22:13:11 +02:00
|
|
|
int btrfs_write_tree_block(struct extent_buffer *buf);
|
|
|
|
int btrfs_wait_tree_block_writeback(struct extent_buffer *buf);
|
|
|
|
int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_fs_info *fs_info);
|
|
|
|
int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
|
|
|
|
struct btrfs_fs_info *fs_info);
|
2008-09-08 17:18:08 +02:00
|
|
|
int btree_lock_page_hook(struct page *page);
|
2007-02-02 15:18:22 +01:00
|
|
|
#endif
|