diff options
| author | Chao Yu <yuchao0@huawei.com> | 2018-06-04 18:20:36 +0300 |
|---|---|---|
| committer | Jaegeuk Kim <jaegeuk@kernel.org> | 2018-06-05 00:33:20 +0300 |
| commit | c29fd0c0e26dacb7a33ad166587059818a94b4e0 (patch) | |
| tree | 6a25f17833047796fccde3cd7c4e17d35199e640 /fs/f2fs/f2fs.h | |
| parent | aae764ece6076b0852b95943c40748569c7b8585 (diff) | |
| download | linux-c29fd0c0e26dacb7a33ad166587059818a94b4e0.tar.xz | |
f2fs: let sync node IO interrupt async one
Although mixed sync/async IOs can have continuous LBA, as they have
different IO priority, block IO scheduler will add them into different
queues and commit them separately, result in splited IOs which causes
wrose performance.
This patch gives high priority to synchronous IO of nodes, means that
once synchronous flow starts, it can interrupt asynchronous writeback
flow of system flusher, so more big IOs can be expected.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Diffstat (limited to 'fs/f2fs/f2fs.h')
| -rw-r--r-- | fs/f2fs/f2fs.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f167d01443fe..4c09e770a0a3 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1201,7 +1201,7 @@ struct f2fs_sb_info { struct percpu_counter alloc_valid_block_count; /* writeback control */ - atomic_t wb_sync_req; /* count # of WB_SYNC threads */ + atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */ /* valid inode count */ struct percpu_counter total_valid_inode_count; |