xfs: implement freezing by emptying the AIL

Now that we write back all metadata either synchronously or through
the AIL we can simply implement metadata freezing in terms of
emptying the AIL.

The implementation for this is fairly simply and straight-forward:
A new routine is added that asks the xfsaild to push the AIL to the
end and waits for it to complete and send a wakeup. The routine will
then loop if the AIL is not actually empty, and continue to do so
until the AIL is compeltely empty.

We keep an inode reclaim pass in the freeze process to avoid having
memory pressure have to reclaim inodes that require dirtying the
filesystem to be reclaimed after the freeze has completed. This
means we can also treat unmount in the exact same way as freeze.

As an upside we can now remove the radix tree based inode writeback
and xfs_unmountfs_writesb.

[ Dave Chinner:
	- Cleaned up commit message.
	- Added inode reclaim passes back into freeze.
	- Cleaned up wakeup mechanism to avoid the use of a new
	  sleep counter variable. ]

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

fs/xfs/xfs_mount.c

@@ -22,6 +22,7 @@
 #include "xfs_log.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
+#include "xfs_trans_priv.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_dir2.h"
@@ -1475,15 +1476,15 @@ xfs_unmountfs(
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
 	/*
-	 * Do a delwri reclaim pass first so that as many dirty inodes are
+	 * Flush all pending changes from the AIL.
-	 * queued up for IO as possible. Then flush the buffers before making
+	 */
-	 * a synchronous path to catch all the remaining inodes are reclaimed.
+	xfs_ail_push_all_sync(mp->m_ail);
-	 * This makes the reclaim process as quick as possible by avoiding
+
-	 * synchronous writeout and blocking on inodes already in the delwri
+	/*
-	 * state as much as possible.
+	 * And reclaim all inodes.  At this point there should be no dirty
+	 * inode, and none should be pinned or locked, but use synchronous
+	 * reclaim just to be sure.
 	 */
-	xfs_reclaim_inodes(mp, 0);
-	xfs_flush_buftarg(mp->m_ddev_targp, 1);
 	xfs_reclaim_inodes(mp, SYNC_WAIT);
 
 	xfs_qm_unmount(mp);
@@ -1519,15 +1520,12 @@ xfs_unmountfs(
 	if (error)
 		xfs_warn(mp, "Unable to update superblock counters. "
 				"Freespace may not be correct on next mount.");
-	xfs_unmountfs_writesb(mp);
 
 	/*
-	 * Make sure all buffers have been flushed and completed before
+	 * At this point we might have modified the superblock again and thus
-	 * unmounting the log.
+	 * added an item to the AIL, thus flush it again.
 	 */
-	error = xfs_flush_buftarg(mp->m_ddev_targp, 1);
+	xfs_ail_push_all_sync(mp->m_ail);
-	if (error)
-		xfs_warn(mp, "%d busy buffers during unmount.", error);
 	xfs_wait_buftarg(mp->m_ddev_targp);
 
 	xfs_log_unmount_write(mp);
@@ -1588,36 +1586,6 @@ xfs_log_sbcount(xfs_mount_t *mp)
 	return error;
 }
 
-int
-xfs_unmountfs_writesb(xfs_mount_t *mp)
-{
-	xfs_buf_t	*sbp;
-	int		error = 0;
-
-	/*
-	 * skip superblock write if fs is read-only, or
-	 * if we are doing a forced umount.
-	 */
-	if (!((mp->m_flags & XFS_MOUNT_RDONLY) ||
-		XFS_FORCED_SHUTDOWN(mp))) {
-
-		sbp = xfs_getsb(mp, 0);
-
-		XFS_BUF_UNDONE(sbp);
-		XFS_BUF_UNREAD(sbp);
-		xfs_buf_delwri_dequeue(sbp);
-		XFS_BUF_WRITE(sbp);
-		XFS_BUF_UNASYNC(sbp);
-		ASSERT(sbp->b_target == mp->m_ddev_targp);
-		xfsbdstrat(mp, sbp);
-		error = xfs_buf_iowait(sbp);
-		if (error)
-			xfs_buf_ioerror_alert(sbp, __func__);
-		xfs_buf_relse(sbp);
-	}
-	return error;
-}
-
 /*
  * xfs_mod_sb() can be used to copy arbitrary changes to the
  * in-core superblock into the superblock buffer to be logged.

fs/xfs/xfs_mount.h

@@ -378,7 +378,6 @@ extern __uint64_t xfs_default_resblks(xfs_mount_t *mp);
 extern int	xfs_mountfs(xfs_mount_t *mp);
 
 extern void	xfs_unmountfs(xfs_mount_t *);
-extern int	xfs_unmountfs_writesb(xfs_mount_t *);
 extern int	xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int);
 extern int	xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *,
 			uint, int);

fs/xfs/xfs_sync.c

@@ -241,45 +241,6 @@ xfs_sync_inode_data(
 	return error;
 }
 
-STATIC int
-xfs_sync_inode_attr(
-	struct xfs_inode	*ip,
-	struct xfs_perag	*pag,
-	int			flags)
-{
-	int			error = 0;
-
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (xfs_inode_clean(ip))
-		goto out_unlock;
-	if (!xfs_iflock_nowait(ip)) {
-		if (!(flags & SYNC_WAIT))
-			goto out_unlock;
-		xfs_iflock(ip);
-	}
-
-	if (xfs_inode_clean(ip)) {
-		xfs_ifunlock(ip);
-		goto out_unlock;
-	}
-
-	error = xfs_iflush(ip, flags);
-
-	/*
-	 * We don't want to try again on non-blocking flushes that can't run
-	 * again immediately. If an inode really must be written, then that's
-	 * what the SYNC_WAIT flag is for.
-	 */
-	if (error == EAGAIN) {
-		ASSERT(!(flags & SYNC_WAIT));
-		error = 0;
-	}
-
- out_unlock:
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	return error;
-}
-
 /*
  * Write out pagecache data for the whole filesystem.
  */
@@ -300,19 +261,6 @@ xfs_sync_data(
 	return 0;
 }
 
-/*
- * Write out inode metadata (attributes) for the whole filesystem.
- */
-STATIC int
-xfs_sync_attr(
-	struct xfs_mount	*mp,
-	int			flags)
-{
-	ASSERT((flags & ~SYNC_WAIT) == 0);
-
-	return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags);
-}
-
 STATIC int
 xfs_sync_fsdata(
 	struct xfs_mount	*mp)
@@ -350,7 +298,7 @@ xfs_sync_fsdata(
  * First stage of freeze - no writers will make progress now we are here,
  * so we flush delwri and delalloc buffers here, then wait for all I/O to
  * complete.  Data is frozen at that point. Metadata is not frozen,
- * transactions can still occur here so don't bother flushing the buftarg
+ * transactions can still occur here so don't bother emptying the AIL
  * because it'll just get dirty again.
  */
 int
@@ -379,33 +327,6 @@ xfs_quiesce_data(
 	return error ? error : error2;
 }
 
-STATIC void
-xfs_quiesce_fs(
-	struct xfs_mount	*mp)
-{
-	int	count = 0, pincount;
-
-	xfs_reclaim_inodes(mp, 0);
-	xfs_flush_buftarg(mp->m_ddev_targp, 0);
-
-	/*
-	 * This loop must run at least twice.  The first instance of the loop
-	 * will flush most meta data but that will generate more meta data
-	 * (typically directory updates).  Which then must be flushed and
-	 * logged before we can write the unmount record. We also so sync
-	 * reclaim of inodes to catch any that the above delwri flush skipped.
-	 */
-	do {
-		xfs_reclaim_inodes(mp, SYNC_WAIT);
-		xfs_sync_attr(mp, SYNC_WAIT);
-		pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
-		if (!pincount) {
-			delay(50);
-			count++;
-		}
-	} while (count < 2);
-}
-
 /*
  * Second stage of a quiesce. The data is already synced, now we have to take
  * care of the metadata. New transactions are already blocked, so we need to
@@ -421,8 +342,12 @@ xfs_quiesce_attr(
 	while (atomic_read(&mp->m_active_trans) > 0)
 		delay(100);
 
-	/* flush inodes and push all remaining buffers out to disk */
+	/* reclaim inodes to do any IO before the freeze completes */
-	xfs_quiesce_fs(mp);
+	xfs_reclaim_inodes(mp, 0);
+	xfs_reclaim_inodes(mp, SYNC_WAIT);
+
+	/* flush all pending changes from the AIL */
+	xfs_ail_push_all_sync(mp->m_ail);
 
 	/*
 	 * Just warn here till VFS can correctly support
@@ -436,7 +361,12 @@ xfs_quiesce_attr(
 		xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
 				"Frozen image may not be consistent.");
 	xfs_log_unmount_write(mp);
-	xfs_unmountfs_writesb(mp);
+
+	/*
+	 * At this point we might have modified the superblock again and thus
+	 * added an item to the AIL, thus flush it again.
+	 */
+	xfs_ail_push_all_sync(mp->m_ail);
 }
 
 static void

fs/xfs/xfs_trans_ail.c

@@ -383,9 +383,8 @@ xfsaild_push(
 		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)) {
+	if (!lip) {
 		/*
 		 * AIL is empty or our push has reached the end.
 		 */
@@ -408,6 +407,7 @@ xfsaild_push(
 	 * lots of contention on the AIL lists.
 	 */
 	lsn = lip->li_lsn;
+	target = ailp->xa_target;
 	while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
 		int	lock_result;
 		/*
@@ -466,11 +466,6 @@ xfsaild_push(
 		}
 
 		spin_lock(&ailp->xa_lock);
-		/* should we bother continuing? */
-		if (XFS_FORCED_SHUTDOWN(mp))
-			break;
-		ASSERT(mp->m_log);
-
 		count++;
 
 		/*
@@ -610,6 +605,30 @@ xfs_ail_push_all(
 		xfs_ail_push(ailp, threshold_lsn);
 }
 
+/*
+ * Push out all items in the AIL immediately and wait until the AIL is empty.
+ */
+void
+xfs_ail_push_all_sync(
+	struct xfs_ail  *ailp)
+{
+	struct xfs_log_item	*lip;
+	DEFINE_WAIT(wait);
+
+	spin_lock(&ailp->xa_lock);
+	while ((lip = xfs_ail_max(ailp)) != NULL) {
+		prepare_to_wait(&ailp->xa_empty, &wait, TASK_UNINTERRUPTIBLE);
+		ailp->xa_target = lip->li_lsn;
+		wake_up_process(ailp->xa_task);
+		spin_unlock(&ailp->xa_lock);
+		schedule();
+		spin_lock(&ailp->xa_lock);
+	}
+	spin_unlock(&ailp->xa_lock);
+
+	finish_wait(&ailp->xa_empty, &wait);
+}
+
 /*
  * xfs_trans_ail_update - bulk AIL insertion operation.
  *
@@ -737,6 +756,8 @@ xfs_trans_ail_delete_bulk(
 	if (mlip_changed) {
 		if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
 			xlog_assign_tail_lsn_locked(ailp->xa_mount);
+		if (list_empty(&ailp->xa_ail))
+			wake_up_all(&ailp->xa_empty);
 		spin_unlock(&ailp->xa_lock);
 
 		xfs_log_space_wake(ailp->xa_mount);
@@ -773,6 +794,7 @@ xfs_trans_ail_init(
 	INIT_LIST_HEAD(&ailp->xa_ail);
 	INIT_LIST_HEAD(&ailp->xa_cursors);
 	spin_lock_init(&ailp->xa_lock);
+	init_waitqueue_head(&ailp->xa_empty);
 
 	ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
 			ailp->xa_mount->m_fsname);

fs/xfs/xfs_trans_priv.h

@@ -71,6 +71,7 @@ struct xfs_ail {
 	spinlock_t		xa_lock;
 	xfs_lsn_t		xa_last_pushed_lsn;
 	int			xa_log_flush;
+	wait_queue_head_t	xa_empty;
 };
 
 /*
@@ -102,6 +103,7 @@ xfs_trans_ail_delete(
 
 void			xfs_ail_push(struct xfs_ail *, xfs_lsn_t);
 void			xfs_ail_push_all(struct xfs_ail *);
+void			xfs_ail_push_all_sync(struct xfs_ail *);
 struct xfs_log_item	*xfs_ail_min(struct xfs_ail  *ailp);
 xfs_lsn_t		xfs_ail_min_lsn(struct xfs_ail *ailp);