[XFS] Don't block pdflush when writing back inodes

When pdflush is writing back inodes, it can get stuck on inode cluster
buffers that are currently under I/O. This occurs when we write data to
multiple inodes in the same inode cluster at the same time.

Effectively, delayed allocation marks the inode dirty during the data
writeback. Hence if the inode cluster was flushed during the writeback of
the first inode, the writeback of the second inode will block waiting for
the inode cluster write to complete before writing it again for the newly
dirtied inode.

Basically, we want to avoid this from happening so we don't block pdflush
and slow down all of writeback. Hence we introduce a non-blocking async
inode flush flag that pdflush uses. If this flag is set, we use
non-blocking operations (e.g. try locks) whereever we can to avoid
blocking or extra I/O being issued.

SGI-PV: 970925
SGI-Modid: xfs-linux-melb:xfs-kern:30501a

Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>

1 files changed, 12 insertions, 43 deletions

diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 40b95e3a88b..14140f6225b 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -3468,29 +3468,6 @@ xfs_inode_flush(
 	    ((iip == NULL) || !(iip->ili_format.ilf_fields & XFS_ILOG_ALL)))
 		return 0;
 
-	if (flags & FLUSH_LOG) {
-		if (iip && iip->ili_last_lsn) {
-			xlog_t		*log = mp->m_log;
-			xfs_lsn_t	sync_lsn;
-			int		log_flags = XFS_LOG_FORCE;
-
-			spin_lock(&log->l_grant_lock);
-			sync_lsn = log->l_last_sync_lsn;
-			spin_unlock(&log->l_grant_lock);
-
-			if ((XFS_LSN_CMP(iip->ili_last_lsn, sync_lsn) > 0)) {
-				if (flags & FLUSH_SYNC)
-					log_flags |= XFS_LOG_SYNC;
-				error = xfs_log_force(mp, iip->ili_last_lsn, log_flags);
-				if (error)
-					return error;
-			}
-
-			if (ip->i_update_core == 0)
-				return 0;
-		}
-	}
-
 	/*
 	 * We make this non-blocking if the inode is contended,
 	 * return EAGAIN to indicate to the caller that they
@@ -3498,30 +3475,22 @@ xfs_inode_flush(
 	 * blocking on inodes inside another operation right
 	 * now, they get caught later by xfs_sync.
 	 */
-	if (flags & FLUSH_INODE) {
-		int	flush_flags;
-
-		if (flags & FLUSH_SYNC) {
-			xfs_ilock(ip, XFS_ILOCK_SHARED);
-			xfs_iflock(ip);
-		} else if (xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
-			if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip)) {
-				xfs_iunlock(ip, XFS_ILOCK_SHARED);
-				return EAGAIN;
-			}
-		} else {
+	if (flags & FLUSH_SYNC) {
+		xfs_ilock(ip, XFS_ILOCK_SHARED);
+		xfs_iflock(ip);
+	} else if (xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
+		if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip)) {
+			xfs_iunlock(ip, XFS_ILOCK_SHARED);
 			return EAGAIN;
 		}
-
-		if (flags & FLUSH_SYNC)
-			flush_flags = XFS_IFLUSH_SYNC;
-		else
-			flush_flags = XFS_IFLUSH_ASYNC;
-
-		error = xfs_iflush(ip, flush_flags);
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	} else {
+		return EAGAIN;
 	}
 
+	error = xfs_iflush(ip, (flags & FLUSH_SYNC) ? XFS_IFLUSH_SYNC
+						    : XFS_IFLUSH_ASYNC_NOBLOCK);
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
 	return error;
 }