xfs: reduce the number of log forces from tail pushing

The AIL push code will issue a log force on ever single push loop
that it exits and has encountered pinned items. It doesn't rescan
these pinned items until it revisits the AIL from the start. Hence
we only need to force the log once per walk from the start of the
AIL to the target LSN.

This results in numbers like this:

	xs_push_ail_flush.....         1456
	xs_log_force.........          1485

For an 8-way 50M inode create workload - almost all the log forces
are coming from the AIL pushing code.

Reduce the number of log forces by only forcing the log if the
previous walk found pinned buffers. This reduces the numbers to:

	xs_push_ail_flush.....          665
	xs_log_force.........           682

For the same test.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>

2 files changed, 21 insertions, 13 deletions

diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index c15aa29fa16..9df7f9f1b5e 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -372,12 +372,24 @@ xfs_ail_worker(
 	xfs_lsn_t		lsn;
 	xfs_lsn_t		target;
 	long			tout = 10;
-	int			flush_log = 0;
 	int			stuck = 0;
 	int			count = 0;
 	int			push_xfsbufd = 0;
 
+	/*
+	 * If last time we ran we encountered pinned items, force the log first
+	 * and wait for it before pushing again.
+	 */
 	spin_lock(&ailp->xa_lock);
+	if (ailp->xa_last_pushed_lsn == 0 && ailp->xa_log_flush &&
+	    !list_empty(&ailp->xa_ail)) {
+		ailp->xa_log_flush = 0;
+		spin_unlock(&ailp->xa_lock);
+		XFS_STATS_INC(xs_push_ail_flush);
+		xfs_log_force(mp, XFS_LOG_SYNC);
+		spin_lock(&ailp->xa_lock);
+	}
+
 	target = ailp->xa_target;
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
 	if (!lip || XFS_FORCED_SHUTDOWN(mp)) {
@@ -435,7 +447,7 @@ xfs_ail_worker(
 		case XFS_ITEM_PINNED:
 			XFS_STATS_INC(xs_push_ail_pinned);
 			stuck++;
-			flush_log = 1;
+			ailp->xa_log_flush++;
 			break;
 
 		case XFS_ITEM_LOCKED:
@@ -480,16 +492,6 @@ xfs_ail_worker(
 	xfs_trans_ail_cursor_done(ailp, &cur);
 	spin_unlock(&ailp->xa_lock);
 
-	if (flush_log) {
-		/*
-		 * If something we need to push out was pinned, then
-		 * push out the log so it will become unpinned and
-		 * move forward in the AIL.
-		 */
-		XFS_STATS_INC(xs_push_ail_flush);
-		xfs_log_force(mp, 0);
-	}
-
 	if (push_xfsbufd) {
 		/* we've got delayed write buffers to flush */
 		wake_up_process(mp->m_ddev_targp->bt_task);
@@ -500,6 +502,7 @@ out_done:
 	if (!count) {
 		/* We're past our target or empty, so idle */
 		ailp->xa_last_pushed_lsn = 0;
+		ailp->xa_log_flush = 0;
 
 		/*
 		 * We clear the XFS_AIL_PUSHING_BIT first before checking
@@ -532,9 +535,13 @@ out_done:
 		 * were stuck.
 		 *
 		 * Backoff a bit more to allow some I/O to complete before
-		 * continuing from where we were.
+		 * restarting from the start of the AIL. This prevents us
+		 * from spinning on the same items, and if they are pinned will
+		 * all the restart to issue a log force to unpin the stuck
+		 * items.
 		 */
 		tout = 20;
+		ailp->xa_last_pushed_lsn = 0;
 	}
 
 	/* There is more to do, requeue us.  */
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 212946b9723..0a6eec6d472 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -71,6 +71,7 @@ struct xfs_ail {
 	struct delayed_work	xa_work;
 	xfs_lsn_t		xa_last_pushed_lsn;
 	unsigned long		xa_flags;
+	int			xa_log_flush;
 };
 
 #define XFS_AIL_PUSHING_BIT	0