OpenCloudOS-Kernel/fs/btrfs/block-group.h

261 lines
8.3 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BTRFS_BLOCK_GROUP_H
#define BTRFS_BLOCK_GROUP_H
#include "free-space-cache.h"
enum btrfs_disk_cache_state {
BTRFS_DC_WRITTEN,
BTRFS_DC_ERROR,
BTRFS_DC_CLEAR,
BTRFS_DC_SETUP,
};
/*
* Control flags for do_chunk_alloc's force field CHUNK_ALLOC_NO_FORCE means to
* only allocate a chunk if we really need one.
*
* CHUNK_ALLOC_LIMITED means to only try and allocate one if we have very few
* chunks already allocated. This is used as part of the clustering code to
* help make sure we have a good pool of storage to cluster in, without filling
* the FS with empty chunks
*
* CHUNK_ALLOC_FORCE means it must try to allocate one
*/
enum btrfs_chunk_alloc_enum {
CHUNK_ALLOC_NO_FORCE,
CHUNK_ALLOC_LIMITED,
CHUNK_ALLOC_FORCE,
};
struct btrfs_caching_control {
struct list_head list;
struct mutex mutex;
wait_queue_head_t wait;
struct btrfs_work work;
struct btrfs_block_group *block_group;
u64 progress;
refcount_t count;
};
/* Once caching_thread() finds this much free space, it will wake up waiters. */
#define CACHING_CTL_WAKE_UP SZ_2M
struct btrfs_block_group {
struct btrfs_fs_info *fs_info;
struct inode *inode;
spinlock_t lock;
u64 start;
u64 length;
u64 pinned;
u64 reserved;
u64 used;
u64 delalloc_bytes;
u64 bytes_super;
u64 flags;
u64 cache_generation;
/*
* If the free space extent count exceeds this number, convert the block
* group to bitmaps.
*/
u32 bitmap_high_thresh;
/*
* If the free space extent count drops below this number, convert the
* block group back to extents.
*/
u32 bitmap_low_thresh;
/*
* It is just used for the delayed data space allocation because
* only the data space allocation and the relative metadata update
* can be done cross the transaction.
*/
struct rw_semaphore data_rwsem;
/* For raid56, this is a full stripe, without parity */
unsigned long full_stripe_len;
unsigned int ro;
unsigned int iref:1;
unsigned int has_caching_ctl:1;
unsigned int removed:1;
int disk_cache_state;
/* Cache tracking stuff */
int cached;
struct btrfs_caching_control *caching_ctl;
u64 last_byte_to_unpin;
struct btrfs_space_info *space_info;
/* Free space cache stuff */
struct btrfs_free_space_ctl *free_space_ctl;
/* Block group cache stuff */
struct rb_node cache_node;
/* For block groups in the same raid type */
struct list_head list;
/* Usage count */
atomic_t count;
/*
* List of struct btrfs_free_clusters for this block group.
* Today it will only have one thing on it, but that may change
*/
struct list_head cluster_list;
/* For delayed block group creation or deletion of empty block groups */
struct list_head bg_list;
/* For read-only block groups */
struct list_head ro_list;
btrfs: add the beginning of async discard, discard workqueue When discard is enabled, everytime a pinned extent is released back to the block_group's free space cache, a discard is issued for the extent. This is an overeager approach when it comes to discarding and helping the SSD maintain enough free space to prevent severe garbage collection situations. This adds the beginning of async discard. Instead of issuing a discard prior to returning it to the free space, it is just marked as untrimmed. The block_group is then added to a LRU which then feeds into a workqueue to issue discards at a much slower rate. Full discarding of unused block groups is still done and will be addressed in a future patch of the series. For now, we don't persist the discard state of extents and bitmaps. Therefore, our failure recovery mode will be to consider extents untrimmed. This lets us handle failure and unmounting as one in the same. On a number of Facebook webservers, I collected data every minute accounting the time we spent in btrfs_finish_extent_commit() (col. 1) and in btrfs_commit_transaction() (col. 2). btrfs_finish_extent_commit() is where we discard extents synchronously before returning them to the free space cache. discard=sync: p99 total per minute p99 total per minute Drive | extent_commit() (ms) | commit_trans() (ms) --------------------------------------------------------------- Drive A | 434 | 1170 Drive B | 880 | 2330 Drive C | 2943 | 3920 Drive D | 4763 | 5701 discard=async: p99 total per minute p99 total per minute Drive | extent_commit() (ms) | commit_trans() (ms) -------------------------------------------------------------- Drive A | 134 | 956 Drive B | 64 | 1972 Drive C | 59 | 1032 Drive D | 62 | 1200 While it's not great that the stats are cumulative over 1m, all of these servers are running the same workload and and the delta between the two are substantial. We are spending significantly less time in btrfs_finish_extent_commit() which is responsible for discarding. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-14 08:22:14 +08:00
/* For discard operations */
atomic_t trimming;
btrfs: add the beginning of async discard, discard workqueue When discard is enabled, everytime a pinned extent is released back to the block_group's free space cache, a discard is issued for the extent. This is an overeager approach when it comes to discarding and helping the SSD maintain enough free space to prevent severe garbage collection situations. This adds the beginning of async discard. Instead of issuing a discard prior to returning it to the free space, it is just marked as untrimmed. The block_group is then added to a LRU which then feeds into a workqueue to issue discards at a much slower rate. Full discarding of unused block groups is still done and will be addressed in a future patch of the series. For now, we don't persist the discard state of extents and bitmaps. Therefore, our failure recovery mode will be to consider extents untrimmed. This lets us handle failure and unmounting as one in the same. On a number of Facebook webservers, I collected data every minute accounting the time we spent in btrfs_finish_extent_commit() (col. 1) and in btrfs_commit_transaction() (col. 2). btrfs_finish_extent_commit() is where we discard extents synchronously before returning them to the free space cache. discard=sync: p99 total per minute p99 total per minute Drive | extent_commit() (ms) | commit_trans() (ms) --------------------------------------------------------------- Drive A | 434 | 1170 Drive B | 880 | 2330 Drive C | 2943 | 3920 Drive D | 4763 | 5701 discard=async: p99 total per minute p99 total per minute Drive | extent_commit() (ms) | commit_trans() (ms) -------------------------------------------------------------- Drive A | 134 | 956 Drive B | 64 | 1972 Drive C | 59 | 1032 Drive D | 62 | 1200 While it's not great that the stats are cumulative over 1m, all of these servers are running the same workload and and the delta between the two are substantial. We are spending significantly less time in btrfs_finish_extent_commit() which is responsible for discarding. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-14 08:22:14 +08:00
struct list_head discard_list;
int discard_index;
u64 discard_eligible_time;
/* For dirty block groups */
struct list_head dirty_list;
struct list_head io_list;
struct btrfs_io_ctl io_ctl;
/*
* Incremented when doing extent allocations and holding a read lock
* on the space_info's groups_sem semaphore.
* Decremented when an ordered extent that represents an IO against this
* block group's range is created (after it's added to its inode's
* root's list of ordered extents) or immediately after the allocation
* if it's a metadata extent or fallocate extent (for these cases we
* don't create ordered extents).
*/
atomic_t reservations;
/*
* Incremented while holding the spinlock *lock* by a task checking if
* it can perform a nocow write (incremented if the value for the *ro*
* field is 0). Decremented by such tasks once they create an ordered
* extent or before that if some error happens before reaching that step.
* This is to prevent races between block group relocation and nocow
* writes through direct IO.
*/
atomic_t nocow_writers;
/* Lock for free space tree operations. */
struct mutex free_space_lock;
/*
* Does the block group need to be added to the free space tree?
* Protected by free_space_lock.
*/
int needs_free_space;
/* Record locked full stripes for RAID5/6 block group */
struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
};
btrfs: add the beginning of async discard, discard workqueue When discard is enabled, everytime a pinned extent is released back to the block_group's free space cache, a discard is issued for the extent. This is an overeager approach when it comes to discarding and helping the SSD maintain enough free space to prevent severe garbage collection situations. This adds the beginning of async discard. Instead of issuing a discard prior to returning it to the free space, it is just marked as untrimmed. The block_group is then added to a LRU which then feeds into a workqueue to issue discards at a much slower rate. Full discarding of unused block groups is still done and will be addressed in a future patch of the series. For now, we don't persist the discard state of extents and bitmaps. Therefore, our failure recovery mode will be to consider extents untrimmed. This lets us handle failure and unmounting as one in the same. On a number of Facebook webservers, I collected data every minute accounting the time we spent in btrfs_finish_extent_commit() (col. 1) and in btrfs_commit_transaction() (col. 2). btrfs_finish_extent_commit() is where we discard extents synchronously before returning them to the free space cache. discard=sync: p99 total per minute p99 total per minute Drive | extent_commit() (ms) | commit_trans() (ms) --------------------------------------------------------------- Drive A | 434 | 1170 Drive B | 880 | 2330 Drive C | 2943 | 3920 Drive D | 4763 | 5701 discard=async: p99 total per minute p99 total per minute Drive | extent_commit() (ms) | commit_trans() (ms) -------------------------------------------------------------- Drive A | 134 | 956 Drive B | 64 | 1972 Drive C | 59 | 1032 Drive D | 62 | 1200 While it's not great that the stats are cumulative over 1m, all of these servers are running the same workload and and the delta between the two are substantial. We are spending significantly less time in btrfs_finish_extent_commit() which is responsible for discarding. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-12-14 08:22:14 +08:00
static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
{
return (block_group->start + block_group->length);
}
#ifdef CONFIG_BTRFS_DEBUG
static inline int btrfs_should_fragment_free_space(
struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) &&
block_group->flags & BTRFS_BLOCK_GROUP_METADATA) ||
(btrfs_test_opt(fs_info, FRAGMENT_DATA) &&
block_group->flags & BTRFS_BLOCK_GROUP_DATA);
}
#endif
struct btrfs_block_group *btrfs_lookup_first_block_group(
struct btrfs_fs_info *info, u64 bytenr);
struct btrfs_block_group *btrfs_lookup_block_group(
struct btrfs_fs_info *info, u64 bytenr);
struct btrfs_block_group *btrfs_next_block_group(
struct btrfs_block_group *cache);
void btrfs_get_block_group(struct btrfs_block_group *cache);
void btrfs_put_block_group(struct btrfs_block_group *cache);
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
const u64 start);
void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
u64 num_bytes);
int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
int btrfs_cache_block_group(struct btrfs_block_group *cache,
int load_cache_only);
void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
struct btrfs_caching_control *btrfs_get_caching_control(
struct btrfs_block_group *cache);
u64 add_new_free_space(struct btrfs_block_group *block_group,
u64 start, u64 end);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
struct btrfs_fs_info *fs_info,
const u64 chunk_offset);
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
u64 group_start, struct extent_map *em);
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
u64 type, u64 chunk_offset, u64 size);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
btrfs: scrub: Don't check free space before marking a block group RO [BUG] When running btrfs/072 with only one online CPU, it has a pretty high chance to fail: btrfs/072 12s ... _check_dmesg: something found in dmesg (see xfstests-dev/results//btrfs/072.dmesg) - output mismatch (see xfstests-dev/results//btrfs/072.out.bad) --- tests/btrfs/072.out 2019-10-22 15:18:14.008965340 +0800 +++ /xfstests-dev/results//btrfs/072.out.bad 2019-11-14 15:56:45.877152240 +0800 @@ -1,2 +1,3 @@ QA output created by 072 Silence is golden +Scrub find errors in "-m dup -d single" test ... And with the following call trace: BTRFS info (device dm-5): scrub: started on devid 1 ------------[ cut here ]------------ BTRFS: Transaction aborted (error -27) WARNING: CPU: 0 PID: 55087 at fs/btrfs/block-group.c:1890 btrfs_create_pending_block_groups+0x3e6/0x470 [btrfs] CPU: 0 PID: 55087 Comm: btrfs Tainted: G W O 5.4.0-rc1-custom+ #13 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:btrfs_create_pending_block_groups+0x3e6/0x470 [btrfs] Call Trace: __btrfs_end_transaction+0xdb/0x310 [btrfs] btrfs_end_transaction+0x10/0x20 [btrfs] btrfs_inc_block_group_ro+0x1c9/0x210 [btrfs] scrub_enumerate_chunks+0x264/0x940 [btrfs] btrfs_scrub_dev+0x45c/0x8f0 [btrfs] btrfs_ioctl+0x31a1/0x3fb0 [btrfs] do_vfs_ioctl+0x636/0xaa0 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x43/0x50 do_syscall_64+0x79/0xe0 entry_SYSCALL_64_after_hwframe+0x49/0xbe ---[ end trace 166c865cec7688e7 ]--- [CAUSE] The error number -27 is -EFBIG, returned from the following call chain: btrfs_end_transaction() |- __btrfs_end_transaction() |- btrfs_create_pending_block_groups() |- btrfs_finish_chunk_alloc() |- btrfs_add_system_chunk() This happens because we have used up all space of btrfs_super_block::sys_chunk_array. The root cause is, we have the following bad loop of creating tons of system chunks: 1. The only SYSTEM chunk is being scrubbed It's very common to have only one SYSTEM chunk. 2. New SYSTEM bg will be allocated As btrfs_inc_block_group_ro() will check if we have enough space after marking current bg RO. If not, then allocate a new chunk. 3. New SYSTEM bg is still empty, will be reclaimed During the reclaim, we will mark it RO again. 4. That newly allocated empty SYSTEM bg get scrubbed We go back to step 2, as the bg is already mark RO but still not cleaned up yet. If the cleaner kthread doesn't get executed fast enough (e.g. only one CPU), then we will get more and more empty SYSTEM chunks, using up all the space of btrfs_super_block::sys_chunk_array. [FIX] Since scrub/dev-replace doesn't always need to allocate new extent, especially chunk tree extent, so we don't really need to do chunk pre-allocation. To break above spiral, here we introduce a new parameter to btrfs_inc_block_group(), @do_chunk_alloc, which indicates whether we need extra chunk pre-allocation. For relocation, we pass @do_chunk_alloc=true, while for scrub, we pass @do_chunk_alloc=false. This should keep unnecessary empty chunks from popping up for scrub. Also, since there are two parameters for btrfs_inc_block_group_ro(), add more comment for it. Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-11-15 10:09:00 +08:00
int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
bool do_chunk_alloc);
void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
int btrfs_update_block_group(struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, int alloc);
int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
u64 ram_bytes, u64 num_bytes, int delalloc);
void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
u64 num_bytes, int delalloc);
int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
enum btrfs_chunk_alloc_enum force);
int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags);
void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
int btrfs_free_block_groups(struct btrfs_fs_info *info);
static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
{
return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA);
}
static inline u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info)
{
return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA);
}
static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
{
return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
}
static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
{
smp_mb();
return cache->cached == BTRFS_CACHE_FINISHED ||
cache->cached == BTRFS_CACHE_ERROR;
}
#endif /* BTRFS_BLOCK_GROUP_H */