github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-06-05 04:56:13 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph
b0643e59cf
linux/fs/btrfs
History
Dennis Zhou b0643e59cf 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>
2020-01-20 16:40:57 +01:00
..
tests btrfs: drop create parameter to btrfs_get_extent() 2020-01-20 16:40:55 +01:00
acl.c btrfs: cleanup btrfs_setxattr_trans and drop transaction parameter 2019-04-29 19:02:44 +02:00
async-thread.c btrfs: add __pure attribute to functions 2019-11-18 12:46:52 +01:00
async-thread.h btrfs: add __pure attribute to functions 2019-11-18 12:46:52 +01:00
backref.c Btrfs: fix deadlock between fiemap and transaction commits 2019-07-30 18:25:12 +02:00
backref.h btrfs: fiemap: preallocate ulists for btrfs_check_shared 2019-07-01 13:34:53 +02:00
block-group.c btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
block-group.h btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
block-rsv.c btrfs: use btrfs_try_granting_tickets in update_global_rsv 2019-09-09 14:59:19 +02:00
block-rsv.h btrfs: migrate the global_block_rsv helpers to block-rsv.c 2019-07-02 12:30:55 +02:00
btrfs_inode.h Btrfs: remove unnecessary delalloc mutex for inodes 2019-11-18 17:51:46 +01:00
check-integrity.c btrfs: remove superfluous BUG_ON() in integrity checks 2020-01-20 16:40:52 +01:00
check-integrity.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
compression.c btrfs: get rid of at_offset parameter to btrfs_lookup_bio_sums() 2020-01-20 16:40:54 +01:00
compression.h btrfs: compression: remove ops pointer from workspace_manager 2019-11-18 12:46:59 +01:00
ctree.c Btrfs: fix removal logic of the tree mod log that leads to use-after-free issues 2019-12-13 14:09:25 +01:00
ctree.h btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
delalloc-space.c Btrfs: remove unnecessary delalloc mutex for inodes 2019-11-18 17:51:46 +01:00
delalloc-space.h btrfs: migrate the delalloc space stuff to it's own home 2019-07-04 17:26:17 +02:00
delayed-inode.c btrfs: use refcount_inc_not_zero in kill_all_nodes 2019-11-18 12:46:51 +01:00
delayed-inode.h Btrfs: delayed-inode: use rb_first_cached for ins_root and del_root 2018-10-15 17:23:33 +02:00
delayed-ref.c btrfs: rename btrfs_space_info_add_old_bytes 2019-09-09 14:59:18 +02:00
delayed-ref.h btrfs: migrate the delayed refs rsv code 2019-07-04 17:26:17 +02:00
dev-replace.c btrfs: add __pure attribute to functions 2019-11-18 12:46:52 +01:00
dev-replace.h btrfs: add __pure attribute to functions 2019-11-18 12:46:52 +01:00
dir-item.c btrfs: remove unused parameter fs_info from btrfs_extend_item 2019-04-29 19:02:50 +02:00
discard.c btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
discard.h btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
disk-io.c btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
disk-io.h btrfs: drop create parameter to btrfs_get_extent() 2020-01-20 16:40:55 +01:00
export.c btrfs: drop unused parameter is_new from btrfs_iget 2019-11-18 12:46:52 +01:00
export.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
extent_io.c btrfs: simplify compressed/inline check in __extent_writepage_io() 2020-01-20 16:40:55 +01:00
extent_io.h btrfs: drop create parameter to btrfs_get_extent() 2020-01-20 16:40:55 +01:00
extent_map.c btrfs: remove extent_map::bdev 2019-11-18 23:43:44 +01:00
extent_map.h btrfs: remove extent_map::bdev 2019-11-18 23:43:44 +01:00
extent-io-tree.h btrfs: move the failrec tree stuff into extent-io-tree.h 2019-11-18 12:46:47 +01:00
extent-tree.c btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
file-item.c btrfs: make btrfs_ordered_extent naming consistent with btrfs_file_extent_item 2020-01-20 16:40:54 +01:00
file.c btrfs: drop create parameter to btrfs_get_extent() 2020-01-20 16:40:55 +01:00
free-space-cache.c btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
free-space-cache.h btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
free-space-tree.c btrfs: rename btrfs_block_group_cache 2019-11-18 17:51:51 +01:00
free-space-tree.h btrfs: rename btrfs_block_group_cache 2019-11-18 17:51:51 +01:00
inode-item.c btrfs: Make btrfs_find_name_in_ext_backref return struct btrfs_inode_extref 2019-09-09 14:59:16 +02:00
inode-map.c btrfs: keep track of which extents have been discarded 2020-01-20 16:40:57 +01:00
inode-map.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
inode.c btrfs: rename DISCARD mount option to to DISCARD_SYNC 2020-01-20 16:40:57 +01:00
ioctl.c btrfs: drop create parameter to btrfs_get_extent() 2020-01-20 16:40:55 +01:00
Kconfig btrfs: add Kconfig dependency for BLAKE2B 2019-12-09 17:56:06 +01:00
locking.c btrfs: document extent buffer locking 2019-11-18 17:51:50 +01:00
locking.h btrfs: move btrfs_unlock_up_safe to other locking functions 2019-11-18 12:46:49 +01:00
lzo.c btrfs: compression: inline free_workspace 2019-11-18 12:46:59 +01:00
Makefile btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
misc.h btrfs: add 64bit safe helper for power of two checks 2019-11-18 12:46:50 +01:00
ordered-data.c btrfs: make btrfs_ordered_extent naming consistent with btrfs_file_extent_item 2020-01-20 16:40:54 +01:00
ordered-data.h btrfs: make btrfs_ordered_extent naming consistent with btrfs_file_extent_item 2020-01-20 16:40:54 +01:00
orphan.c btrfs: replace GPL boilerplate by SPDX -- sources 2018-04-12 16:29:51 +02:00
print-tree.c btrfs: Remove unneeded semicolon 2020-01-20 16:40:55 +01:00
print-tree.h btrfs: print-tree: debugging output enhancement 2018-04-20 19:18:16 +02:00
props.c btrfs: props: remove unnecessary hash_init() 2019-11-18 12:46:55 +01:00
props.h btrfs: delete unused function btrfs_set_prop_trans 2019-04-29 19:02:54 +02:00
qgroup.c btrfs: qgroup: return ENOTCONN instead of EINVAL when quotas are not enabled 2020-01-20 16:40:50 +01:00
qgroup.h btrfs: rename btrfs_block_group_cache 2019-11-18 17:51:51 +01:00
raid56.c btrfs: remove pointless local variable in lock_stripe_add() 2019-11-18 12:47:00 +01:00
raid56.h btrfs: constify map parameter for nr_parity_stripes and nr_data_stripes 2019-07-01 13:34:58 +02:00
rcu-string.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
reada.c btrfs: rename btrfs_block_group_cache 2019-11-18 17:51:51 +01:00
ref-verify.c btrfs: fix uninitialized ret in ref-verify 2019-10-03 15:00:56 +02:00
ref-verify.h btrfs: ref-verify: Use btrfs_ref to refactor btrfs_ref_tree_mod() 2019-04-29 19:02:49 +02:00
relocation.c btrfs: make btrfs_ordered_extent naming consistent with btrfs_file_extent_item 2020-01-20 16:40:54 +01:00
root-tree.c btrfs: do not delete mismatched root refs 2020-01-08 14:44:24 +01:00
scrub.c Btrfs: fix block group remaining RO forever after error during device replace 2019-11-18 18:07:55 +01:00
send.c btrfs: send: remove WARN_ON for readonly mount 2019-12-13 14:10:46 +01:00
send.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
space-info.c btrfs: don't pass system_chunk into can_overcommit 2020-01-20 16:40:52 +01:00
space-info.h Btrfs: remove wait queue from space_info structure 2019-11-18 17:51:46 +01:00
struct-funcs.c btrfs: tie extent buffer and it's token together 2019-09-09 14:59:16 +02:00
super.c btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
sysfs.c btrfs: sysfs, merge btrfs_sysfs_add devices_kobj and fsid 2020-01-20 16:40:50 +01:00
sysfs.h btrfs: sysfs, merge btrfs_sysfs_add devices_kobj and fsid 2020-01-20 16:40:50 +01:00
transaction.c btrfs: rename btrfs_block_group_cache 2019-11-18 17:51:51 +01:00
transaction.h btrfs: Rename btrfs_join_transaction_nolock 2019-11-18 12:46:54 +01:00
tree-checker.c btrfs: tree-checker: Verify location key for DIR_ITEM/DIR_INDEX 2020-01-20 16:40:56 +01:00
tree-checker.h btrfs: get fs_info from eb in btrfs_check_chunk_valid 2019-04-29 19:02:39 +02:00
tree-defrag.c btrfs: open code now trivial btrfs_set_lock_blocking 2019-02-25 14:13:27 +01:00
tree-log.c btrfs: Remove redundant WARN_ON in walk_down_log_tree 2020-01-20 16:40:51 +01:00
tree-log.h btrfs: get fs_info from trans in btrfs_set_log_full_commit 2019-04-29 19:02:41 +02:00
ulist.c btrfs: replace GPL boilerplate by SPDX -- sources 2018-04-12 16:29:51 +02:00
ulist.h btrfs: replace GPL boilerplate by SPDX -- headers 2018-04-12 16:29:46 +02:00
uuid-tree.c btrfs: handle ENOENT in btrfs_uuid_tree_iterate 2019-12-13 14:10:45 +01:00
volumes.c btrfs: add the beginning of async discard, discard workqueue 2020-01-20 16:40:57 +01:00
volumes.h btrfs: sysfs, rename devices kobject holder to devices_kobj 2020-01-20 16:40:49 +01:00
xattr.c Btrfs: fix failure to persist compression property xattr deletion on fsync 2019-06-17 16:37:17 +02:00
xattr.h btrfs: cleanup btrfs_setxattr_trans and drop transaction parameter 2019-04-29 19:02:44 +02:00
zlib.c btrfs: compression: inline free_workspace 2019-11-18 12:46:59 +01:00
zstd.c btrfs: compression: inline free_workspace 2019-11-18 12:46:59 +01:00