xfs: Use delayed write for inodes rather than async V2

We currently do background inode flush asynchronously, resulting in
inodes being written in whatever order the background writeback
issues them. Not only that, there are also blocking and non-blocking
asynchronous inode flushes, depending on where the flush comes from.

This patch completely removes asynchronous inode writeback. It
removes all the strange writeback modes and replaces them with
either a synchronous flush or a non-blocking delayed write flush.
That is, inode flushes will only issue IO directly if they are
synchronous, and background flushing may do nothing if the operation
would block (e.g. on a pinned inode or buffer lock).

Delayed write flushes will now result in the inode buffer sitting in
the delwri queue of the buffer cache to be flushed by either an AIL
push or by the xfsbufd timing out the buffer. This will allow
accumulation of dirty inode buffers in memory and allow optimisation
of inode cluster writeback at the xfsbufd level where we have much
greater queue depths than the block layer elevators. We will also
get adjacent inode cluster buffer IO merging for free when a later
patch in the series allows sorting of the delayed write buffers
before dispatch.

This effectively means that any inode that is written back by
background writeback will be seen as flush locked during AIL
pushing, and will result in the buffers being pushed from there.
This writeback path is currently non-optimal, but the next patch
in the series will fix that problem.

A side effect of this delayed write mechanism is that background
inode reclaim will no longer directly flush inodes, nor can it wait
on the flush lock. The result is that inode reclaim must leave the
inode in the reclaimable state until it is clean. Hence attempts to
reclaim a dirty inode in the background will simply skip the inode
until it is clean and this allows other mechanisms (i.e. xfsbufd) to
do more optimal writeback of the dirty buffers. As a result, the
inode reclaim code has been rewritten so that it no longer relies on
the ambiguous return values of xfs_iflush() to determine whether it
is safe to reclaim an inode.

Portions of this patch are derived from patches by Christoph
Hellwig.

Version 2:
- cleanup reclaim code as suggested by Christoph
- log background reclaim inode flush errors
- just pass sync flags to xfs_iflush

Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

1 files changed, 5 insertions, 70 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 8d0666dd170..fa31360046d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2835,8 +2835,6 @@ xfs_iflush(
 	xfs_dinode_t		*dip;
 	xfs_mount_t		*mp;
 	int			error;
-	int			noblock = (flags == XFS_IFLUSH_ASYNC_NOBLOCK);
-	enum { INT_DELWRI = (1 << 0), INT_ASYNC = (1 << 1) };
 
 	XFS_STATS_INC(xs_iflush_count);
 
@@ -2859,7 +2857,7 @@ xfs_iflush(
 	 * in the same cluster are dirty, they will probably write the inode
 	 * out for us if they occur after the log force completes.
 	 */
-	if (noblock && xfs_ipincount(ip)) {
+	if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) {
 		xfs_iunpin_nowait(ip);
 		xfs_ifunlock(ip);
 		return EAGAIN;
@@ -2893,60 +2891,10 @@ xfs_iflush(
 	}
 
 	/*
-	 * Decide how buffer will be flushed out.  This is done before
-	 * the call to xfs_iflush_int because this field is zeroed by it.
-	 */
-	if (iip != NULL && iip->ili_format.ilf_fields != 0) {
-		/*
-		 * Flush out the inode buffer according to the directions
-		 * of the caller.  In the cases where the caller has given
-		 * us a choice choose the non-delwri case.  This is because
-		 * the inode is in the AIL and we need to get it out soon.
-		 */
-		switch (flags) {
-		case XFS_IFLUSH_SYNC:
-		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
-			flags = 0;
-			break;
-		case XFS_IFLUSH_ASYNC_NOBLOCK:
-		case XFS_IFLUSH_ASYNC:
-		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
-			flags = INT_ASYNC;
-			break;
-		case XFS_IFLUSH_DELWRI:
-			flags = INT_DELWRI;
-			break;
-		default:
-			ASSERT(0);
-			flags = 0;
-			break;
-		}
-	} else {
-		switch (flags) {
-		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
-		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
-		case XFS_IFLUSH_DELWRI:
-			flags = INT_DELWRI;
-			break;
-		case XFS_IFLUSH_ASYNC_NOBLOCK:
-		case XFS_IFLUSH_ASYNC:
-			flags = INT_ASYNC;
-			break;
-		case XFS_IFLUSH_SYNC:
-			flags = 0;
-			break;
-		default:
-			ASSERT(0);
-			flags = 0;
-			break;
-		}
-	}
-
-	/*
 	 * Get the buffer containing the on-disk inode.
 	 */
 	error = xfs_itobp(mp, NULL, ip, &dip, &bp,
-				noblock ? XBF_TRYLOCK : XBF_LOCK);
+				(flags & SYNC_WAIT) ? XBF_LOCK : XBF_TRYLOCK);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
 		return error;
@@ -2974,13 +2922,10 @@ xfs_iflush(
 	if (error)
 		goto cluster_corrupt_out;
 
-	if (flags & INT_DELWRI) {
-		xfs_bdwrite(mp, bp);
-	} else if (flags & INT_ASYNC) {
-		error = xfs_bawrite(mp, bp);
-	} else {
+	if (flags & SYNC_WAIT)
 		error = xfs_bwrite(mp, bp);
-	}
+	else
+		xfs_bdwrite(mp, bp);
 	return error;
 
 corrupt_out:
@@ -3015,16 +2960,6 @@ xfs_iflush_int(
 	iip = ip->i_itemp;
 	mp = ip->i_mount;
 
-
-	/*
-	 * If the inode isn't dirty, then just release the inode
-	 * flush lock and do nothing.
-	 */
-	if (xfs_inode_clean(ip)) {
-		xfs_ifunlock(ip);
-		return 0;
-	}
-
 	/* set *dip = inode's place in the buffer */
 	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);