mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-04 01:24:12 +08:00
8c6e53a79d
An inode's io_tree can be quite large and there are cases where due to delalloc it can have thousands of extent state records, which makes the red black tree have a depth of 10 or more, making the operation of count_range_bits() slow if we repeatedly call it for a range that starts where, or after, the previous one we called it for. Such use cases are when searching for delalloc in a file range that corresponds to a hole or a prealloc extent, which is done during lseek SEEK_HOLE/DATA and fiemap. So introduce a cached state parameter to count_range_bits() which we use to store the last extent state record we visited, and then allow the caller to pass it again on its next call to count_range_bits(). The next patches in the series will make fiemap and lseek use the new parameter. This change is part of a patchset that has the goal to make performance better for applications that use lseek's SEEK_HOLE and SEEK_DATA modes to iterate over the extents of a file. Two examples are the cp program from coreutils 9.0+ and the tar program (when using its --sparse / -S option). A sample test and results are listed in the changelog of the last patch in the series: 1/9 btrfs: remove leftover setting of EXTENT_UPTODATE state in an inode's io_tree 2/9 btrfs: add an early exit when searching for delalloc range for lseek/fiemap 3/9 btrfs: skip unnecessary delalloc searches during lseek/fiemap 4/9 btrfs: search for delalloc more efficiently during lseek/fiemap 5/9 btrfs: remove no longer used btrfs_next_extent_map() 6/9 btrfs: allow passing a cached state record to count_range_bits() 7/9 btrfs: update stale comment for count_range_bits() 8/9 btrfs: use cached state when looking for delalloc ranges with fiemap 9/9 btrfs: use cached state when looking for delalloc ranges with lseek Reported-by: Wang Yugui <wangyugui@e16-tech.com> Link: https://lore.kernel.org/linux-btrfs/20221106073028.71F9.409509F4@e16-tech.com/ Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5NSVicm7nYBJ7x8fFkDpno8z3PYt5aPU43Bajc1H0h1Q@mail.gmail.com/ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
234 lines
7.2 KiB
C
234 lines
7.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
#ifndef BTRFS_EXTENT_IO_TREE_H
|
|
#define BTRFS_EXTENT_IO_TREE_H
|
|
|
|
#include "misc.h"
|
|
|
|
struct extent_changeset;
|
|
struct io_failure_record;
|
|
|
|
/* Bits for the extent state */
|
|
enum {
|
|
ENUM_BIT(EXTENT_DIRTY),
|
|
ENUM_BIT(EXTENT_UPTODATE),
|
|
ENUM_BIT(EXTENT_LOCKED),
|
|
ENUM_BIT(EXTENT_NEW),
|
|
ENUM_BIT(EXTENT_DELALLOC),
|
|
ENUM_BIT(EXTENT_DEFRAG),
|
|
ENUM_BIT(EXTENT_BOUNDARY),
|
|
ENUM_BIT(EXTENT_NODATASUM),
|
|
ENUM_BIT(EXTENT_CLEAR_META_RESV),
|
|
ENUM_BIT(EXTENT_NEED_WAIT),
|
|
ENUM_BIT(EXTENT_NORESERVE),
|
|
ENUM_BIT(EXTENT_QGROUP_RESERVED),
|
|
ENUM_BIT(EXTENT_CLEAR_DATA_RESV),
|
|
/*
|
|
* Must be cleared only during ordered extent completion or on error
|
|
* paths if we did not manage to submit bios and create the ordered
|
|
* extents for the range. Should not be cleared during page release
|
|
* and page invalidation (if there is an ordered extent in flight),
|
|
* that is left for the ordered extent completion.
|
|
*/
|
|
ENUM_BIT(EXTENT_DELALLOC_NEW),
|
|
/*
|
|
* When an ordered extent successfully completes for a region marked as
|
|
* a new delalloc range, use this flag when clearing a new delalloc
|
|
* range to indicate that the VFS' inode number of bytes should be
|
|
* incremented and the inode's new delalloc bytes decremented, in an
|
|
* atomic way to prevent races with stat(2).
|
|
*/
|
|
ENUM_BIT(EXTENT_ADD_INODE_BYTES),
|
|
/*
|
|
* Set during truncate when we're clearing an entire range and we just
|
|
* want the extent states to go away.
|
|
*/
|
|
ENUM_BIT(EXTENT_CLEAR_ALL_BITS),
|
|
};
|
|
|
|
#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \
|
|
EXTENT_CLEAR_DATA_RESV)
|
|
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | \
|
|
EXTENT_ADD_INODE_BYTES | \
|
|
EXTENT_CLEAR_ALL_BITS)
|
|
|
|
/*
|
|
* Redefined bits above which are used only in the device allocation tree,
|
|
* shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
|
|
* / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
|
|
* manipulation functions
|
|
*/
|
|
#define CHUNK_ALLOCATED EXTENT_DIRTY
|
|
#define CHUNK_TRIMMED EXTENT_DEFRAG
|
|
#define CHUNK_STATE_MASK (CHUNK_ALLOCATED | \
|
|
CHUNK_TRIMMED)
|
|
|
|
enum {
|
|
IO_TREE_FS_PINNED_EXTENTS,
|
|
IO_TREE_FS_EXCLUDED_EXTENTS,
|
|
IO_TREE_BTREE_INODE_IO,
|
|
IO_TREE_INODE_IO,
|
|
IO_TREE_RELOC_BLOCKS,
|
|
IO_TREE_TRANS_DIRTY_PAGES,
|
|
IO_TREE_ROOT_DIRTY_LOG_PAGES,
|
|
IO_TREE_INODE_FILE_EXTENT,
|
|
IO_TREE_LOG_CSUM_RANGE,
|
|
IO_TREE_SELFTEST,
|
|
IO_TREE_DEVICE_ALLOC_STATE,
|
|
};
|
|
|
|
struct extent_io_tree {
|
|
struct rb_root state;
|
|
struct btrfs_fs_info *fs_info;
|
|
/* Inode associated with this tree, or NULL. */
|
|
struct btrfs_inode *inode;
|
|
|
|
/* Who owns this io tree, should be one of IO_TREE_* */
|
|
u8 owner;
|
|
|
|
spinlock_t lock;
|
|
};
|
|
|
|
struct extent_state {
|
|
u64 start;
|
|
u64 end; /* inclusive */
|
|
struct rb_node rb_node;
|
|
|
|
/* ADD NEW ELEMENTS AFTER THIS */
|
|
wait_queue_head_t wq;
|
|
refcount_t refs;
|
|
u32 state;
|
|
|
|
#ifdef CONFIG_BTRFS_DEBUG
|
|
struct list_head leak_list;
|
|
#endif
|
|
};
|
|
|
|
void extent_io_tree_init(struct btrfs_fs_info *fs_info,
|
|
struct extent_io_tree *tree, unsigned int owner);
|
|
void extent_io_tree_release(struct extent_io_tree *tree);
|
|
|
|
int lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
|
|
struct extent_state **cached);
|
|
|
|
int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
|
|
struct extent_state **cached);
|
|
|
|
int __init extent_state_init_cachep(void);
|
|
void __cold extent_state_free_cachep(void);
|
|
|
|
u64 count_range_bits(struct extent_io_tree *tree,
|
|
u64 *start, u64 search_end,
|
|
u64 max_bytes, u32 bits, int contig,
|
|
struct extent_state **cached_state);
|
|
|
|
void free_extent_state(struct extent_state *state);
|
|
int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
|
|
u32 bits, int filled, struct extent_state *cached_state);
|
|
int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
|
|
u32 bits, struct extent_changeset *changeset);
|
|
int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
|
|
u32 bits, struct extent_state **cached, gfp_t mask,
|
|
struct extent_changeset *changeset);
|
|
|
|
static inline int clear_extent_bit(struct extent_io_tree *tree, u64 start,
|
|
u64 end, u32 bits,
|
|
struct extent_state **cached)
|
|
{
|
|
return __clear_extent_bit(tree, start, end, bits, cached,
|
|
GFP_NOFS, NULL);
|
|
}
|
|
|
|
static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end,
|
|
struct extent_state **cached)
|
|
{
|
|
return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, cached,
|
|
GFP_NOFS, NULL);
|
|
}
|
|
|
|
static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
|
|
u64 end, u32 bits)
|
|
{
|
|
return clear_extent_bit(tree, start, end, bits, NULL);
|
|
}
|
|
|
|
int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
|
|
u32 bits, struct extent_changeset *changeset);
|
|
int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
|
|
u32 bits, struct extent_state **cached_state, gfp_t mask);
|
|
|
|
static inline int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start,
|
|
u64 end, u32 bits)
|
|
{
|
|
return set_extent_bit(tree, start, end, bits, NULL, GFP_NOWAIT);
|
|
}
|
|
|
|
static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
|
|
u64 end, u32 bits)
|
|
{
|
|
return set_extent_bit(tree, start, end, bits, NULL, GFP_NOFS);
|
|
}
|
|
|
|
static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
|
|
u64 end, struct extent_state **cached_state)
|
|
{
|
|
return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE,
|
|
cached_state, GFP_NOFS, NULL);
|
|
}
|
|
|
|
static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
|
|
u64 end, gfp_t mask)
|
|
{
|
|
return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL, mask);
|
|
}
|
|
|
|
static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
|
|
u64 end, struct extent_state **cached)
|
|
{
|
|
return clear_extent_bit(tree, start, end,
|
|
EXTENT_DIRTY | EXTENT_DELALLOC |
|
|
EXTENT_DO_ACCOUNTING, cached);
|
|
}
|
|
|
|
int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
|
|
u32 bits, u32 clear_bits,
|
|
struct extent_state **cached_state);
|
|
|
|
static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
|
|
u64 end, u32 extra_bits,
|
|
struct extent_state **cached_state)
|
|
{
|
|
return set_extent_bit(tree, start, end,
|
|
EXTENT_DELALLOC | extra_bits,
|
|
cached_state, GFP_NOFS);
|
|
}
|
|
|
|
static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
|
|
u64 end, struct extent_state **cached_state)
|
|
{
|
|
return set_extent_bit(tree, start, end,
|
|
EXTENT_DELALLOC | EXTENT_DEFRAG,
|
|
cached_state, GFP_NOFS);
|
|
}
|
|
|
|
static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
|
|
u64 end)
|
|
{
|
|
return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, GFP_NOFS);
|
|
}
|
|
|
|
int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
|
|
u64 *start_ret, u64 *end_ret, u32 bits,
|
|
struct extent_state **cached_state);
|
|
void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
|
|
u64 *start_ret, u64 *end_ret, u32 bits);
|
|
int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start,
|
|
u64 *start_ret, u64 *end_ret, u32 bits);
|
|
bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
|
|
u64 *end, u64 max_bytes,
|
|
struct extent_state **cached_state);
|
|
void wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u32 bits,
|
|
struct extent_state **cached_state);
|
|
|
|
#endif /* BTRFS_EXTENT_IO_TREE_H */
|