lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Btrfs: use percpu counter for dirty metadata count

Browse Source 
->dirty_metadata_bytes is accessed very frequently, so use percpu
counter instead of the u64 variant to reduce the contention of
the lock.

This patch also fixed the problem that we access it without
lock protection in __btrfs_btree_balance_dirty(), which may
cause we skip the dirty pages flush.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
This commit is contained in:
Miao Xie
2013-01-29 10:09:20 +00:00
committed by Josef Bacik
parent c018daecea
commit e2d845211e
3 changed files with 42 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
fs/btrfs/extent_io.c
View File

@@ -3122,12 +3122,9 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb,
set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
spin_unlock(&eb->refs_lock);
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
spin_lock(&fs_info->delalloc_lock);
if (fs_info->dirty_metadata_bytes >= eb->len)
fs_info->dirty_metadata_bytes -= eb->len;
else
WARN_ON(1);
spin_unlock(&fs_info->delalloc_lock);
__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-eb->len,
fs_info->dirty_metadata_batch);
ret = 1;
} else {
spin_unlock(&eb->refs_lock);