reduce log I/O latency V2

Reduce log I/O latency

To ensure that log I/O is issued as the highest priority I/O, set the I/O priority of the log I/O to the highest possible. This will ensure that log I/O is not held up behind bulk data or other metadata I/O as delaying log I/O can pause the entire transaction subsystem. Introduce a new buffer flag to allow us to tag the log buffers so we can discriminate when issuing the I/O.

Version 2:
- don't use realtime priority class

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/linux-2.6/xfs_buf.c |    3 +++
 fs/xfs/linux-2.6/xfs_buf.h |    5 ++++-
 fs/xfs/xfs_log.c           |    2 ++
 3 files changed, 9 insertions(+), 1 deletion(-)

Index: 2.6.x-xfs-new/fs/xfs/linux-2.6/xfs_buf.c
===================================================================

fs/xfs/linux-2.6/xfs_buf.c +3 -0

@@ -1198,6 +1198,9 @@ next_chunk:
 
 submit_io:
 	if (likely(bio->bi_size)) {
+		/* log I/O should not be delayed by anything except realtime. */
+		if (bp->b_flags & XBF_LOG_BUFFER)
+			bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 0));
 		submit_bio(rw, bio);
 		if (size)
 			goto next_chunk;

Index: 2.6.x-xfs-new/fs/xfs/linux-2.6/xfs_buf.h
===================================================================

fs/xfs/linux-2.6/xfs_buf.h +4 -1

@@ -53,7 +53,8 @@ typedef enum {
 	XBF_DELWRI = (1 << 6),  /* buffer has dirty pages                  */
 	XBF_STALE = (1 << 7),	/* buffer has been staled, do not find it  */
 	XBF_FS_MANAGED = (1 << 8),  /* filesystem controls freeing memory  */
- 	XBF_ORDERED = (1 << 11),    /* use ordered writes		   */
+	XBF_LOG_BUFFER = (1 << 9),  /* Buffer issued by the log		   */
+	XBF_ORDERED = (1 << 11),    /* use ordered writes		   */
 	XBF_READ_AHEAD = (1 << 12), /* asynchronous read-ahead		   */
 
 	/* flags used only as arguments to access routines */

@@ -339,6 +340,8 @@ extern void xfs_buf_trace(xfs_buf_t *, c
 #define XFS_BUF_TARGET(bp)		((bp)->b_target)
 #define XFS_BUFTARG_NAME(target)	xfs_buf_target_name(target)
 
+#define XFS_BUF_SET_LOGBUF(bp)	((bp)->b_flags |= XBF_LOG_BUFFER)
+
 static inline int xfs_bawrite(void *mp, xfs_buf_t *bp)
 {
 	bp->b_fspriv3 = mp;

Index: 2.6.x-xfs-new/fs/xfs/xfs_log.c
===================================================================

fs/xfs/xfs_log.c +2 -0

@@ -1443,6 +1443,8 @@ xlog_sync(xlog_t		*log,
 	XFS_BUF_ZEROFLAGS(bp);
 	XFS_BUF_BUSY(bp);
 	XFS_BUF_ASYNC(bp);
+	XFS_BUF_SET_LOGBUF(bp);
+
 	/*
 	 * Do an ordered write for the log block.
 	 * Its unnecessary to flush the first split block in the log wrap case.

Looks good Dave. Shouldn't we also tag the second buffer in the split log write case?

Quoted 2 lines · Lachlan McIlroy

Looks good Dave. Shouldn't we also tag the second buffer in the split log write case?

Hmm - I thought it was being tagged. looks like I missed a reject on my last set of patch re-orderings - updated patch attached.

---

Reduce log I/O latency

To ensure that log I/O is issued as the highest priority I/O, set the I/O priority of the log I/O to the highest possible. This will ensure that log I/O is not held up behind bulk data or other metadata I/O as delaying log I/O can pause the entire transaction subsystem. Introduce a new buffer flag to allow us to tag the log buffers so we can discriminate when issuing the I/O.

Signed-off-by Dave Chinner <[email protected]>

---
 fs/xfs/linux-2.6/xfs_buf.c |    3 +++
 fs/xfs/linux-2.6/xfs_buf.h |    5 ++++-
 fs/xfs/xfs_log.c           |    3 +++
 3 files changed, 10 insertions(+), 1 deletion(-)

Index: 2.6.x-xfs-new/fs/xfs/linux-2.6/xfs_buf.c
===================================================================

fs/xfs/linux-2.6/xfs_buf.c +3 -0

@@ -1198,6 +1198,9 @@ next_chunk:
 
 submit_io:
 	if (likely(bio->bi_size)) {
+		/* log I/O should not be delayed by anything except realtime. */
+		if (bp->b_flags & XBF_LOG_BUFFER)
+			bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 0));
 		submit_bio(rw, bio);
 		if (size)
 			goto next_chunk;

Index: 2.6.x-xfs-new/fs/xfs/linux-2.6/xfs_buf.h
===================================================================

fs/xfs/linux-2.6/xfs_buf.h +4 -1

@@ -53,7 +53,8 @@ typedef enum {
 	XBF_DELWRI = (1 << 6),  /* buffer has dirty pages                  */
 	XBF_STALE = (1 << 7),	/* buffer has been staled, do not find it  */
 	XBF_FS_MANAGED = (1 << 8),  /* filesystem controls freeing memory  */
- 	XBF_ORDERED = (1 << 11),    /* use ordered writes		   */
+	XBF_LOG_BUFFER = (1 << 9),  /* Buffer issued by the log		   */
+	XBF_ORDERED = (1 << 11),    /* use ordered writes		   */
 	XBF_READ_AHEAD = (1 << 12), /* asynchronous read-ahead		   */
 
 	/* flags used only as arguments to access routines */

@@ -339,6 +340,8 @@ extern void xfs_buf_trace(xfs_buf_t *, c
 #define XFS_BUF_TARGET(bp)		((bp)->b_target)
 #define XFS_BUFTARG_NAME(target)	xfs_buf_target_name(target)
 
+#define XFS_BUF_SET_LOGBUF(bp)	((bp)->b_flags |= XBF_LOG_BUFFER)
+
 static inline int xfs_bawrite(void *mp, xfs_buf_t *bp)
 {
 	bp->b_fspriv3 = mp;

Index: 2.6.x-xfs-new/fs/xfs/xfs_log.c
===================================================================

fs/xfs/xfs_log.c +3 -0

@@ -1462,6 +1462,8 @@ xlog_sync(xlog_t		*log,
 	XFS_BUF_ZEROFLAGS(bp);
 	XFS_BUF_BUSY(bp);
 	XFS_BUF_ASYNC(bp);
+	XFS_BUF_SET_LOGBUF(bp);
+
 	/*
 	 * Do an ordered write for the log block.
 	 * Its unnecessary to flush the first split block in the log wrap case.

@@ -1499,6 +1501,7 @@ xlog_sync(xlog_t		*log,
 		XFS_BUF_ZEROFLAGS(bp);
 		XFS_BUF_BUSY(bp);
 		XFS_BUF_ASYNC(bp);
+		XFS_BUF_SET_LOGBUF(bp);
 		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
 			XFS_BUF_ORDERED(bp);
 		dptr = XFS_BUF_PTR(bp);