Btrfs: set plug for fsync
PATCH 1/1 Btrfs: set plug for fsync
Setting plug can merge adjacent IOs before dispatching IOs to the disk driver.
Without plug, it'd not be a problem for single disk usecases, but for multiple disks using raid profile, a large IO can be split to several IOs of stripe length, and plug can be helpful to bring them together for each disk so that we can save several disk access.
Moreover, fsync issues synchronous writes, so plug can really take effect.
--- fs/btrfs/file.c | 3 +++ 1 file changed, 3 insertions(+)
fs/btrfs/file.c +3 -0
@@ -2018,10 +2018,13 @@ int btrfs_release_file(struct inode *inode, struct file *filp)static int start_ordered_ops (struct inode *inode,loff_t start,loff_t end) {int ret; +struct blk_plug plug; +blk_start_plug (&plug);atomic_inc (&BTRFS_I (inode)->sync_writers); ret =btrfs_fdatawrite_range (inode, start, end);atomic_dec (&BTRFS_I (inode)->sync_writers); +blk_finish_plug (&plug);return ret; }
Signature · 1 line
2.9.4
Quoted 21 lines · Liu Bo
Setting plug can merge adjacent IOs before dispatching IOs to the disk driver.
Without plug, it'd not be a problem for single disk usecases, but for multiple disks using raid profile, a large IO can be split to several IOs of stripe length, and plug can be helpful to bring them together for each disk so that we can save several disk access.
Moreover, fsync issues synchronous writes, so plug can really take effect.
Signed-off-by Liu Bo <[email protected]>--- fs/btrfs/file.c | 3 +++ 1 file changed, 3 insertions(+)fs/btrfs/file.c +0
-0
fs/btrfs/file.c int btrfs_release_file(struct inode *inode, struct file *filp) · line 2023
Quoted 6 lines
fs/btrfs/file.c +2
-0@@ -2018,10 +2018,13 @@ int btrfs_release_file(struct inode *inode, struct file *filp)static int start_ordered_ops (struct inode *inode,loff_t start,loff_t end) {int ret; +struct blk_plug plug; +blk_start_plug (&plug);
Can you please add a comment here? Essentially repeating the commit message. The plug/unplug calls are never obvious so the expectations could be documented.
Quoted 14 lines
fs/btrfs/file.c +1
-0atomic_inc (&BTRFS_I (inode)->sync_writers); ret =btrfs_fdatawrite_range (inode, start, end);atomic_dec (&BTRFS_I (inode)->sync_writers); +blk_finish_plug (&plug);return ret; }Signature · 6 lines
2.9.4 -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
PATCH v2 1/1 Btrfs: set plug for fsync
In reply to Liu BoSetting plug can merge adjacent IOs before dispatching IOs to the disk driver.
Without plug, it'd not be a problem for single disk usecases, but for multiple disks using raid profile, a large IO can be split to several IOs of stripe length, and plug can be helpful to bring them together for each disk so that we can save several disk access.
Moreover, fsync issues synchronous writes, so plug can really take effect.
---
v2: Explain why setting plug makes sense.
fs/btrfs/file.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
fs/btrfs/file.c +10 -0
@@ -2018,10 +2018,20 @@ int btrfs_release_file(struct inode *inode, struct file *filp)static int start_ordered_ops (struct inode *inode,loff_t start,loff_t end) {int ret; +struct blk_plug plug; +/* +* This is only called in fsync, which would do synchronous +* writes, so a plug can merge adjacent IOs as much as +* possible. Esp. in case of multiple disks using raid +* profile, a large IO can be split to several segments of +* stripe length(64K). +*/ +blk_start_plug (&plug);atomic_inc (&BTRFS_I (inode)->sync_writers); ret =btrfs_fdatawrite_range (inode, start, end);atomic_dec (&BTRFS_I (inode)->sync_writers); +blk_finish_plug (&plug);return ret; }
Signature · 1 line
2.9.4
Quoted 8 lines · Liu Bo
Setting plug can merge adjacent IOs before dispatching IOs to the disk driver.
Without plug, it'd not be a problem for single disk usecases, but for multiple disks using raid profile, a large IO can be split to several IOs of stripe length, and plug can be helpful to bring them together for each disk so that we can save several disk access.
Quoted 4 lines
Moreover, fsync issues synchronous writes, so plug can really take effect.
Signed-off-by Liu Bo <[email protected]>