[PATCH 1/3] [PATCH] xfs: Non-blocking inode locking in IO completion

[PATCH 1/3] [PATCH] xfs: Non-blocking inode locking in IO completion

[Dave Chinner]

>From 77d7a0c2eeb285c9069e15396703d0cb9690ac50 Wed, 17 Feb 2010 05:36:29 +0000

The introduction of barriers to loop devices has created a new IO
order completion dependency that XFS does not handle. The loop
device implements barriers using fsync and so turns a log IO in the
XFS filesystem on the loop device into a data IO in the backing
filesystem. That is, the completion of log IOs in the loop
filesystem are now dependent on completion of data IO in the backing
filesystem.

This can cause deadlocks when a flush daemon issues a log force with
an inode locked because the IO completion of IO on the inode is
blocked by the inode lock. This in turn prevents further data IO
completion from occuring on all XFS filesystems on that CPU (due to
the shared nature of the completion queues). This then prevents the
log IO from completing because the log is waiting for data IO
completion as well.

The fix for this new completion order dependency issue is to make
the IO completion inode locking non-blocking. If the inode lock
can't be grabbed, simply requeue the IO completion back to the work
queue so that it can be processed later. This prevents the
completion queue from being blocked and allows data IO completion on
other inodes to proceed, hence avoiding completion order dependent
deadlocks.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/linux-2.6/xfs_aops.c |   93 ++++++++++++++++++++++++++-----------------
 1 files changed, 56 insertions(+), 37 deletions(-)

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 66abe36..1c65a2b 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -163,14 +163,17 @@ xfs_ioend_new_eof(
 }
 
 /*
- * Update on-disk file size now that data has been written to disk.
- * The current in-memory file size is i_size.  If a write is beyond
- * eof i_new_size will be the intended file size until i_size is
- * updated.  If this write does not extend all the way to the valid
- * file size then restrict this update to the end of the write.
+ * Update on-disk file size now that data has been written to disk.  The
+ * current in-memory file size is i_size.  If a write is beyond eof i_new_size
+ * will be the intended file size until i_size is updated.  If this write does
+ * not extend all the way to the valid file size then restrict this update to
+ * the end of the write.
+ *
+ * This function does not block as blocking on the inode lock in IO completion
+ * can lead to IO completion order dependency deadlocks.. If it can't get the
+ * inode ilock it will return EAGAIN. Callers must handle this.
  */
-
-STATIC void
+STATIC int
 xfs_setfilesize(
 	xfs_ioend_t		*ioend)
 {
@@ -181,9 +184,11 @@ xfs_setfilesize(
 	ASSERT(ioend->io_type != IOMAP_READ);
 
 	if (unlikely(ioend->io_error))
-		return;
+		return 0;
+
+	if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+		return EAGAIN;
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	isize = xfs_ioend_new_eof(ioend);
 	if (isize) {
 		ip->i_d.di_size = isize;
@@ -191,6 +196,28 @@ xfs_setfilesize(
 	}
 
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return 0;
+}
+
+/*
+ * Schedule IO completion handling on a xfsdatad if this was
+ * the final hold on this ioend. If we are asked to wait,
+ * flush the workqueue.
+ */
+STATIC void
+xfs_finish_ioend(
+	xfs_ioend_t	*ioend,
+	int		wait)
+{
+	if (atomic_dec_and_test(&ioend->io_remaining)) {
+		struct workqueue_struct *wq;
+
+		wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
+			xfsconvertd_workqueue : xfsdatad_workqueue;
+		queue_work(wq, &ioend->io_work);
+		if (wait)
+			flush_workqueue(wq);
+	}
 }
 
 /*
@@ -198,11 +225,11 @@ xfs_setfilesize(
  */
 STATIC void
 xfs_end_io(
-	struct work_struct	*work)
+	struct work_struct *work)
 {
-	xfs_ioend_t		*ioend =
-		container_of(work, xfs_ioend_t, io_work);
-	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	xfs_ioend_t	*ioend = container_of(work, xfs_ioend_t, io_work);
+	struct xfs_inode *ip = XFS_I(ioend->io_inode);
+	int		error;
 
 	/*
 	 * For unwritten extents we need to issue transactions to convert a
@@ -210,7 +237,6 @@ xfs_end_io(
 	 */
 	if (ioend->io_type == IOMAP_UNWRITTEN &&
 	    likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
-		int error;
 
 		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
 						 ioend->io_size);
@@ -222,30 +248,23 @@ xfs_end_io(
 	 * We might have to update the on-disk file size after extending
 	 * writes.
 	 */
-	if (ioend->io_type != IOMAP_READ)
-		xfs_setfilesize(ioend);
-	xfs_destroy_ioend(ioend);
-}
-
-/*
- * Schedule IO completion handling on a xfsdatad if this was
- * the final hold on this ioend. If we are asked to wait,
- * flush the workqueue.
- */
-STATIC void
-xfs_finish_ioend(
-	xfs_ioend_t	*ioend,
-	int		wait)
-{
-	if (atomic_dec_and_test(&ioend->io_remaining)) {
-		struct workqueue_struct *wq;
-
-		wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
-			xfsconvertd_workqueue : xfsdatad_workqueue;
-		queue_work(wq, &ioend->io_work);
-		if (wait)
-			flush_workqueue(wq);
+	if (ioend->io_type != IOMAP_READ) {
+		error = xfs_setfilesize(ioend);
+		ASSERT(!error || error == EAGAIN);
 	}
+
+	/*
+	 * If we didn't complete processing of the ioend, requeue it to the
+	 * tail of the workqueue for another attempt later. Otherwise destroy
+	 * it.
+	 */
+	if (error == EAGAIN) {
+		atomic_inc(&ioend->io_remaining);
+		xfs_finish_ioend(ioend, 0);
+		/* ensure we don't spin on blocked ioends */
+		delay(1);
+	} else
+		xfs_destroy_ioend(ioend);
 }
 
 /*
-- 
1.6.5

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

[PATCH 3/3] [PATCH] xfs: check for more work before sleeping in xfssyncd

[Dave Chinner]

>From 20f6b2c785cf187445f126321638ab8ba7aa7494 Thu, 4 Mar 2010 01:46:23 +0000

xfssyncd processes a queue of work by detaching the queue and
then iterating over all the work items. It then sleeps for a
time period or until new work comes in. If new work is queued
while xfssyncd is actively processing the detached work queue,
it will not process that new work until after a sleep timeout
or the next work event queued wakes it.

Fix this by checking the work queue again before going to sleep.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/linux-2.6/xfs_sync.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 687e9fc..6b6b394 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -613,7 +613,8 @@ xfssyncd(
 	set_freezable();
 	timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
 	for (;;) {
-		timeleft = schedule_timeout_interruptible(timeleft);
+		if (list_empty(&mp->m_sync_list))
+			timeleft = schedule_timeout_interruptible(timeleft);
 		/* swsusp */
 		try_to_freeze();
 		if (kthread_should_stop() && list_empty(&mp->m_sync_list))
@@ -633,8 +634,7 @@ xfssyncd(
 			list_add_tail(&mp->m_sync_work.w_list,
 					&mp->m_sync_list);
 		}
-		list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
-			list_move(&work->w_list, &tmp);
+		list_splice_init(&mp->m_sync_list, &tmp);
 		spin_unlock(&mp->m_sync_lock);
 
 		list_for_each_entry_safe(work, n, &tmp, w_list) {
-- 
1.6.5

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs