[PATCH] xfs: improve metadata I/O merging in the elevator

[Christoph Hellwig]

I had the patch below from Dave in my queue for a while, but previously
couldn't really reproduce his numbers.  After some discussions of the
bio types I've reteseted it again and can see constant improvements when
using cfq on my large array box with it (5-10% for the sequential create
workloads), but still nothing on deadline.  Given that people also want
it for better marking in blktrace it might be time to put it in.

Comments?

-- 

From: Dave Chinner <dgc at sgi.com>
Subject: xfs: improve metadata I/O merging in the elevator

Change all async metadata buffers to use [READ|WRITE]_META I/O types
so that the I/O doesn't get issued immediately. This allows merging
of adjacent metadata requests but still prioritises them over bulk
data. This shows a 10-15% improvement in sequential create speed of
small files.

Don't include the log buffers in this classification - leave them
as sync types so they are issued immediately.

Signed-off-by: Dave Chinner <dgc at sgi.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>

Index: xfs/fs/xfs/linux-2.6/xfs_buf.c
===================================================================
--- xfs.orig/fs/xfs/linux-2.6/xfs_buf.c	2009-11-12 17:10:19.852253847 +0100
+++ xfs/fs/xfs/linux-2.6/xfs_buf.c	2009-11-12 17:13:55.334003777 +0100
@@ -1177,10 +1177,14 @@ _xfs_buf_ioapply(
 	if (bp->b_flags & XBF_ORDERED) {
 		ASSERT(!(bp->b_flags & XBF_READ));
 		rw = WRITE_BARRIER;
-	} else if (bp->b_flags & _XBF_RUN_QUEUES) {
+	} else if (bp->b_flags & XBF_LOG_BUFFER) {
 		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
 		bp->b_flags &= ~_XBF_RUN_QUEUES;
 		rw = (bp->b_flags & XBF_WRITE) ? WRITE_SYNC : READ_SYNC;
+	} else if (bp->b_flags & _XBF_RUN_QUEUES) {
+		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
+		bp->b_flags &= ~_XBF_RUN_QUEUES;
+		rw = (bp->b_flags & XBF_WRITE) ? WRITE : READ_META;
 	} else {
 		rw = (bp->b_flags & XBF_WRITE) ? WRITE :
 		     (bp->b_flags & XBF_READ_AHEAD) ? READA : READ;
Index: xfs/fs/xfs/linux-2.6/xfs_buf.h
===================================================================
--- xfs.orig/fs/xfs/linux-2.6/xfs_buf.h	2009-11-12 17:10:19.857278370 +0100
+++ xfs/fs/xfs/linux-2.6/xfs_buf.h	2009-11-12 17:13:55.334003777 +0100
@@ -55,6 +55,7 @@ typedef enum {
 	XBF_FS_MANAGED = (1 << 8),  /* filesystem controls freeing memory  */
  	XBF_ORDERED = (1 << 11),    /* use ordered writes		   */
 	XBF_READ_AHEAD = (1 << 12), /* asynchronous read-ahead		   */
+	XBF_LOG_BUFFER = (1 << 13), /* this is a buffer used for the log   */
 
 	/* flags used only as arguments to access routines */
 	XBF_LOCK = (1 << 14),       /* lock requested			   */
Index: xfs/fs/xfs/xfs_log.c
===================================================================
--- xfs.orig/fs/xfs/xfs_log.c	2009-11-12 17:10:20.267254560 +0100
+++ xfs/fs/xfs/xfs_log.c	2009-11-12 17:13:55.335004184 +0100
@@ -1524,6 +1524,7 @@ xlog_sync(xlog_t		*log,
 	XFS_BUF_ZEROFLAGS(bp);
 	XFS_BUF_BUSY(bp);
 	XFS_BUF_ASYNC(bp);
+	bp->b_flags |= XBF_LOG_BUFFER;
 	/*
 	 * Do an ordered write for the log block.
 	 * Its unnecessary to flush the first split block in the log wrap case.
@@ -1561,6 +1562,7 @@ xlog_sync(xlog_t		*log,
 		XFS_BUF_ZEROFLAGS(bp);
 		XFS_BUF_BUSY(bp);
 		XFS_BUF_ASYNC(bp);
+		bp->b_flags |= XBF_LOG_BUFFER;
 		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
 			XFS_BUF_ORDERED(bp);
 		dptr = XFS_BUF_PTR(bp);