diff options
author | Josef Bacik <josef@toxicpanda.com> | 2019-04-10 15:56:09 -0400 |
---|---|---|
committer | David Sterba <dsterba@suse.com> | 2019-04-29 19:25:37 +0200 |
commit | 4297ff84dc24d120753e0425702e8ad9b80ed10f (patch) | |
tree | 1067cbeed0ca1e28f56402343a6b156c6ac91bea /fs/btrfs/disk-io.c | |
parent | da9b6ec829dff9b867bb863ebb5b45b4ef2530a1 (diff) | |
download | blackbird-op-linux-4297ff84dc24d120753e0425702e8ad9b80ed10f.tar.gz blackbird-op-linux-4297ff84dc24d120753e0425702e8ad9b80ed10f.zip |
btrfs: track DIO bytes in flight
When diagnosing a slowdown of generic/224 I noticed we were not doing
anything when calling into shrink_delalloc(). This is because all
writes in 224 are O_DIRECT, not delalloc, and thus our delalloc_bytes
counter is 0, which short circuits most of the work inside of
shrink_delalloc(). However O_DIRECT writes still consume metadata
resources and generate ordered extents, which we can still wait on.
Fix this by tracking outstanding DIO write bytes, and use this as well
as the delalloc bytes counter to decide if we need to lookup and wait on
any ordered extents. If we have more DIO writes than delalloc bytes
we'll go ahead and wait on any ordered extents regardless of our flush
state as flushing delalloc is likely to not gain us anything.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
[ use dio instead of odirect in identifiers ]
Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/disk-io.c')
-rw-r--r-- | fs/btrfs/disk-io.c | 15 |
1 files changed, 14 insertions, 1 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index eb26b3239827..663efce22d98 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2633,11 +2633,17 @@ int open_ctree(struct super_block *sb, goto fail; } - ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); + ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL); if (ret) { err = ret; goto fail_srcu; } + + ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); + if (ret) { + err = ret; + goto fail_dio_bytes; + } fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); @@ -3336,6 +3342,8 @@ fail_delalloc_bytes: percpu_counter_destroy(&fs_info->delalloc_bytes); fail_dirty_metadata_bytes: percpu_counter_destroy(&fs_info->dirty_metadata_bytes); +fail_dio_bytes: + percpu_counter_destroy(&fs_info->dio_bytes); fail_srcu: cleanup_srcu_struct(&fs_info->subvol_srcu); fail: @@ -4017,6 +4025,10 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_sum(&fs_info->delalloc_bytes)); } + if (percpu_counter_sum(&fs_info->dio_bytes)) + btrfs_info(fs_info, "at unmount dio bytes count %lld", + percpu_counter_sum(&fs_info->dio_bytes)); + btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -4048,6 +4060,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); + percpu_counter_destroy(&fs_info->dio_bytes); percpu_counter_destroy(&fs_info->dev_replace.bio_counter); cleanup_srcu_struct(&fs_info->subvol_srcu); |