mirror of
https://github.com/torvalds/linux.git
synced 2024-11-28 23:21:31 +00:00
59c7b566a3
Currently we index free space on offset only, because usually we have a hint from the allocator that we want to honor for locality reasons. However if we fail to use this hint we have to go back to a brute force search through the free space entries to find a large enough extent. With sufficiently fragmented free space this becomes quite expensive, as we have to linearly search all of the free space entries to find if we have a part that's long enough. To fix this add a cached rb tree to index based on free space entry bytes. This will allow us to quickly look up the largest chunk in the free space tree for this block group, and stop searching once we've found an entry that is too small to satisfy our allocation. We simply choose to use this tree if we're searching from the beginning of the block group, as we know we do not care about locality at that point. I wrote an allocator test that creates a 10TiB ram backed null block device and then fallocates random files until the file system is full. I think go through and delete all of the odd files. Then I spawn 8 threads that fallocate 64MiB files (1/2 our extent size cap) until the file system is full again. I use bcc's funclatency to measure the latency of find_free_extent. The baseline results are nsecs : count distribution 0 -> 1 : 0 | | 2 -> 3 : 0 | | 4 -> 7 : 0 | | 8 -> 15 : 0 | | 16 -> 31 : 0 | | 32 -> 63 : 0 | | 64 -> 127 : 0 | | 128 -> 255 : 0 | | 256 -> 511 : 10356 |**** | 512 -> 1023 : 58242 |************************* | 1024 -> 2047 : 74418 |******************************** | 2048 -> 4095 : 90393 |****************************************| 4096 -> 8191 : 79119 |*********************************** | 8192 -> 16383 : 35614 |*************** | 16384 -> 32767 : 13418 |***** | 32768 -> 65535 : 12811 |***** | 65536 -> 131071 : 17090 |******* | 131072 -> 262143 : 26465 |*********** | 262144 -> 524287 : 40179 |***************** | 524288 -> 1048575 : 55469 |************************ | 1048576 -> 2097151 : 48807 |********************* | 2097152 -> 4194303 : 26744 |*********** | 4194304 -> 8388607 : 35351 |*************** | 8388608 -> 16777215 : 13918 |****** | 16777216 -> 33554431 : 21 | | avg = 908079 nsecs, total: 580889071441 nsecs, count: 639690 And the patch results are nsecs : count distribution 0 -> 1 : 0 | | 2 -> 3 : 0 | | 4 -> 7 : 0 | | 8 -> 15 : 0 | | 16 -> 31 : 0 | | 32 -> 63 : 0 | | 64 -> 127 : 0 | | 128 -> 255 : 0 | | 256 -> 511 : 6883 |** | 512 -> 1023 : 54346 |********************* | 1024 -> 2047 : 79170 |******************************** | 2048 -> 4095 : 98890 |****************************************| 4096 -> 8191 : 81911 |********************************* | 8192 -> 16383 : 27075 |********** | 16384 -> 32767 : 14668 |***** | 32768 -> 65535 : 13251 |***** | 65536 -> 131071 : 15340 |****** | 131072 -> 262143 : 26715 |********** | 262144 -> 524287 : 43274 |***************** | 524288 -> 1048575 : 53870 |********************* | 1048576 -> 2097151 : 55368 |********************** | 2097152 -> 4194303 : 41036 |**************** | 4194304 -> 8388607 : 24927 |********** | 8388608 -> 16777215 : 33 | | 16777216 -> 33554431 : 9 | | avg = 623599 nsecs, total: 397259314759 nsecs, count: 637042 There's a little variation in the amount of calls done because of timing of the threads with metadata requirements, but the avg, total, and count's are relatively consistent between runs (usually within 2-5% of each other). As you can see here we have around a 30% decrease in average latency with a 30% decrease in overall time spent in find_free_extent. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
155 lines
5.3 KiB
C
155 lines
5.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 2009 Oracle. All rights reserved.
|
|
*/
|
|
|
|
#ifndef BTRFS_FREE_SPACE_CACHE_H
|
|
#define BTRFS_FREE_SPACE_CACHE_H
|
|
|
|
/*
|
|
* This is the trim state of an extent or bitmap.
|
|
*
|
|
* BTRFS_TRIM_STATE_TRIMMING is special and used to maintain the state of a
|
|
* bitmap as we may need several trims to fully trim a single bitmap entry.
|
|
* This is reset should any free space other than trimmed space be added to the
|
|
* bitmap.
|
|
*/
|
|
enum btrfs_trim_state {
|
|
BTRFS_TRIM_STATE_UNTRIMMED,
|
|
BTRFS_TRIM_STATE_TRIMMED,
|
|
BTRFS_TRIM_STATE_TRIMMING,
|
|
};
|
|
|
|
struct btrfs_free_space {
|
|
struct rb_node offset_index;
|
|
struct rb_node bytes_index;
|
|
u64 offset;
|
|
u64 bytes;
|
|
u64 max_extent_size;
|
|
unsigned long *bitmap;
|
|
struct list_head list;
|
|
enum btrfs_trim_state trim_state;
|
|
s32 bitmap_extents;
|
|
};
|
|
|
|
static inline bool btrfs_free_space_trimmed(struct btrfs_free_space *info)
|
|
{
|
|
return (info->trim_state == BTRFS_TRIM_STATE_TRIMMED);
|
|
}
|
|
|
|
static inline bool btrfs_free_space_trimming_bitmap(
|
|
struct btrfs_free_space *info)
|
|
{
|
|
return (info->trim_state == BTRFS_TRIM_STATE_TRIMMING);
|
|
}
|
|
|
|
struct btrfs_free_space_ctl {
|
|
spinlock_t tree_lock;
|
|
struct rb_root free_space_offset;
|
|
struct rb_root_cached free_space_bytes;
|
|
u64 free_space;
|
|
int extents_thresh;
|
|
int free_extents;
|
|
int total_bitmaps;
|
|
int unit;
|
|
u64 start;
|
|
s32 discardable_extents[BTRFS_STAT_NR_ENTRIES];
|
|
s64 discardable_bytes[BTRFS_STAT_NR_ENTRIES];
|
|
const struct btrfs_free_space_op *op;
|
|
void *private;
|
|
struct mutex cache_writeout_mutex;
|
|
struct list_head trimming_ranges;
|
|
};
|
|
|
|
struct btrfs_free_space_op {
|
|
bool (*use_bitmap)(struct btrfs_free_space_ctl *ctl,
|
|
struct btrfs_free_space *info);
|
|
};
|
|
|
|
struct btrfs_io_ctl {
|
|
void *cur, *orig;
|
|
struct page *page;
|
|
struct page **pages;
|
|
struct btrfs_fs_info *fs_info;
|
|
struct inode *inode;
|
|
unsigned long size;
|
|
int index;
|
|
int num_pages;
|
|
int entries;
|
|
int bitmaps;
|
|
};
|
|
|
|
struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
|
|
struct btrfs_path *path);
|
|
int create_free_space_inode(struct btrfs_trans_handle *trans,
|
|
struct btrfs_block_group *block_group,
|
|
struct btrfs_path *path);
|
|
int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans,
|
|
struct inode *inode,
|
|
struct btrfs_block_group *block_group);
|
|
|
|
int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_block_rsv *rsv);
|
|
int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
|
|
struct btrfs_block_group *block_group,
|
|
struct inode *inode);
|
|
int load_free_space_cache(struct btrfs_block_group *block_group);
|
|
int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
|
|
struct btrfs_block_group *block_group,
|
|
struct btrfs_path *path);
|
|
int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
|
|
struct btrfs_block_group *block_group,
|
|
struct btrfs_path *path);
|
|
|
|
void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group,
|
|
struct btrfs_free_space_ctl *ctl);
|
|
int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_free_space_ctl *ctl,
|
|
u64 bytenr, u64 size,
|
|
enum btrfs_trim_state trim_state);
|
|
int btrfs_add_free_space(struct btrfs_block_group *block_group,
|
|
u64 bytenr, u64 size);
|
|
int btrfs_add_free_space_unused(struct btrfs_block_group *block_group,
|
|
u64 bytenr, u64 size);
|
|
int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group,
|
|
u64 bytenr, u64 size);
|
|
int btrfs_remove_free_space(struct btrfs_block_group *block_group,
|
|
u64 bytenr, u64 size);
|
|
void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
|
|
void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group);
|
|
bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group);
|
|
u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
|
|
u64 offset, u64 bytes, u64 empty_size,
|
|
u64 *max_extent_size);
|
|
void btrfs_dump_free_space(struct btrfs_block_group *block_group,
|
|
u64 bytes);
|
|
int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
|
|
struct btrfs_free_cluster *cluster,
|
|
u64 offset, u64 bytes, u64 empty_size);
|
|
void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster);
|
|
u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
|
|
struct btrfs_free_cluster *cluster, u64 bytes,
|
|
u64 min_start, u64 *max_extent_size);
|
|
void btrfs_return_cluster_to_free_space(
|
|
struct btrfs_block_group *block_group,
|
|
struct btrfs_free_cluster *cluster);
|
|
int btrfs_trim_block_group(struct btrfs_block_group *block_group,
|
|
u64 *trimmed, u64 start, u64 end, u64 minlen);
|
|
int btrfs_trim_block_group_extents(struct btrfs_block_group *block_group,
|
|
u64 *trimmed, u64 start, u64 end, u64 minlen,
|
|
bool async);
|
|
int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
|
|
u64 *trimmed, u64 start, u64 end, u64 minlen,
|
|
u64 maxlen, bool async);
|
|
|
|
bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info);
|
|
int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active);
|
|
/* Support functions for running our sanity tests */
|
|
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
|
|
int test_add_free_space_entry(struct btrfs_block_group *cache,
|
|
u64 offset, u64 bytes, bool bitmap);
|
|
int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes);
|
|
#endif
|
|
|
|
#endif
|