[PATCH 0/2] xfs: patches for 3.2

[PATCH 0/2] xfs: patches for 3.2

[Dave Chinner]

These are the two patches I have outstanding for 3.2. I've dropped
the xfsbufd changes from the series as Christoph and I have been
discussing ways to change metadata writeback that make the xfsbufd
redundant. Hence there's no need to change it now...

I've dropped all the interface changes from the xfs buf allocation
code change, simplifying it lots, and fixed the problems reported
with it. I've also fixed a bug in the AIL log force reduction patch
that caused the AIL to get stuck when pinned buffers caused the
stuck processing to loop.

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

[PATCH 1/2] xfs: Don't allocate new buffers on every call to _xfs_buf_find

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

Stats show that for an 8-way unlink @ ~80,000 unlinks/s we are doing
~1 million cache hit lookups to ~3000 buffer creates. That's almost
3 orders of magnitude more cahce hits than misses, so optimising for
cache hits is quite important. In the cache hit case, we do not need
to allocate a new buffer in case of a cache miss, so we are
effectively hitting the allocator for no good reason for vast the
majority of calls to _xfs_buf_find. 8-way create workloads are
showing similar cache hit/miss ratios.

The result is profiles that look like this:

     samples  pcnt function                        DSO
     _______ _____ _______________________________ _________________

     1036.00 10.0% _xfs_buf_find                   [kernel.kallsyms]
      582.00  5.6% kmem_cache_alloc                [kernel.kallsyms]
      519.00  5.0% __memcpy                        [kernel.kallsyms]
      468.00  4.5% __ticket_spin_lock              [kernel.kallsyms]
      388.00  3.7% kmem_cache_free                 [kernel.kallsyms]
      331.00  3.2% xfs_log_commit_cil              [kernel.kallsyms]


Further, there is a fair bit of work involved in initialising a new
buffer once a cache miss has occurred and we currently do that under
the rbtree spinlock. That increases spinlock hold time on what are
heavily used trees.

To fix this, remove the initialisation of the buffer from
_xfs_buf_find() and only allocate the new buffer once we've had a
cache miss. Initialise the buffer immediately after allocating it in
xfs_buf_get, too, so that is it ready for insert if we get another
cache miss after allocation. This minimises lock hold time and
avoids unnecessary allocator churn. The resulting profiles look
like:

     samples  pcnt function                    DSO
     _______ _____ ___________________________ _________________

     8111.00  9.1% _xfs_buf_find               [kernel.kallsyms]
     4380.00  4.9% __memcpy                    [kernel.kallsyms]
     4341.00  4.8% __ticket_spin_lock          [kernel.kallsyms]
     3401.00  3.8% kmem_cache_alloc            [kernel.kallsyms]
     2856.00  3.2% xfs_log_commit_cil          [kernel.kallsyms]
     2625.00  2.9% __kmalloc                   [kernel.kallsyms]
     2380.00  2.7% kfree                       [kernel.kallsyms]
     2016.00  2.3% kmem_cache_free             [kernel.kallsyms]

Showing a significant reduction in time spent doing allocation and
freeing from slabs (kmem_cache_alloc and kmem_cache_free).

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_buf.c |   48 ++++++++++++++++++++++++++++--------------------
 1 files changed, 28 insertions(+), 20 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index e3af850..6785b7b 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -477,8 +477,6 @@ _xfs_buf_find(
 
 	/* No match found */
 	if (new_bp) {
-		_xfs_buf_initialize(new_bp, btp, range_base,
-				range_length, flags);
 		rb_link_node(&new_bp->b_rbnode, parent, rbp);
 		rb_insert_color(&new_bp->b_rbnode, &pag->pag_buf_tree);
 		/* the buffer keeps the perag reference until it is freed */
@@ -521,35 +519,53 @@ found:
 }
 
 /*
- *	Assembles a buffer covering the specified range.
- *	Storage in memory for all portions of the buffer will be allocated,
- *	although backing storage may not be.
+ * Assembles a buffer covering the specified range. The code is optimised for
+ * cache hits, as metadata intensive workloads will see 3 orders of magnitude
+ * more hits than misses.
  */
-xfs_buf_t *
+struct xfs_buf *
 xfs_buf_get(
 	xfs_buftarg_t		*target,/* target for buffer		*/
 	xfs_off_t		ioff,	/* starting offset of range	*/
 	size_t			isize,	/* length of range		*/
 	xfs_buf_flags_t		flags)
 {
-	xfs_buf_t		*bp, *new_bp;
+	struct xfs_buf		*bp;
+	struct xfs_buf		*new_bp;
 	int			error = 0;
 
+	bp = _xfs_buf_find(target, ioff, isize, flags, NULL);
+	if (likely(bp))
+		goto found;
+
 	new_bp = xfs_buf_allocate(flags);
 	if (unlikely(!new_bp))
 		return NULL;
 
+	_xfs_buf_initialize(new_bp, target,
+			    ioff << BBSHIFT, isize << BBSHIFT, flags);
+
 	bp = _xfs_buf_find(target, ioff, isize, flags, new_bp);
+	if (!bp) {
+		xfs_buf_deallocate(new_bp);
+		return NULL;
+	}
+
 	if (bp == new_bp) {
 		error = xfs_buf_allocate_memory(bp, flags);
 		if (error)
 			goto no_buffer;
-	} else {
+	} else
 		xfs_buf_deallocate(new_bp);
-		if (unlikely(bp == NULL))
-			return NULL;
-	}
 
+	/*
+	 * Now we have a workable buffer, fill in the block number so
+	 * that we can do IO on it.
+	 */
+	bp->b_bn = ioff;
+	bp->b_count_desired = bp->b_buffer_length;
+
+found:
 	if (!(bp->b_flags & XBF_MAPPED)) {
 		error = _xfs_buf_map_pages(bp, flags);
 		if (unlikely(error)) {
@@ -560,18 +576,10 @@ xfs_buf_get(
 	}
 
 	XFS_STATS_INC(xb_get);
-
-	/*
-	 * Always fill in the block number now, the mapped cases can do
-	 * their own overlay of this later.
-	 */
-	bp->b_bn = ioff;
-	bp->b_count_desired = bp->b_buffer_length;
-
 	trace_xfs_buf_get(bp, flags, _RET_IP_);
 	return bp;
 
- no_buffer:
+no_buffer:
 	if (flags & (XBF_LOCK | XBF_TRYLOCK))
 		xfs_buf_unlock(bp);
 	xfs_buf_rele(bp);
-- 
1.7.5.4

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

Re: [PATCH 1/2] xfs: Don't allocate new buffers on every call to _xfs_buf_find

[Christoph Hellwig]

Looks good,

Reviewed-by: Christoph Hellwig <hch@lst.de>

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

Re: [PATCH 1/2] xfs: Don't allocate new buffers on every call to _xfs_buf_find

[Alex Elder]

On Fri, 2011-09-30 at 14:45 +1000, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> Stats show that for an 8-way unlink @ ~80,000 unlinks/s we are doing
> ~1 million cache hit lookups to ~3000 buffer creates. That's almost
> 3 orders of magnitude more cahce hits than misses, so optimising for
> cache hits is quite important. In the cache hit case, we do not need
> to allocate a new buffer in case of a cache miss, so we are
> effectively hitting the allocator for no good reason for vast the
> majority of calls to _xfs_buf_find. 8-way create workloads are
> showing similar cache hit/miss ratios.
> 
> The result is profiles that look like this:
> 
>      samples  pcnt function                        DSO
>      _______ _____ _______________________________ _________________
> 
>      1036.00 10.0% _xfs_buf_find                   [kernel.kallsyms]
>       582.00  5.6% kmem_cache_alloc                [kernel.kallsyms]
>       519.00  5.0% __memcpy                        [kernel.kallsyms]
>       468.00  4.5% __ticket_spin_lock              [kernel.kallsyms]
>       388.00  3.7% kmem_cache_free                 [kernel.kallsyms]
>       331.00  3.2% xfs_log_commit_cil              [kernel.kallsyms]
> 
> 
> Further, there is a fair bit of work involved in initialising a new
> buffer once a cache miss has occurred and we currently do that under
> the rbtree spinlock. That increases spinlock hold time on what are
> heavily used trees.
> 
> To fix this, remove the initialisation of the buffer from
> _xfs_buf_find() and only allocate the new buffer once we've had a
> cache miss. Initialise the buffer immediately after allocating it in
> xfs_buf_get, too, so that is it ready for insert if we get another
> cache miss after allocation. This minimises lock hold time and
> avoids unnecessary allocator churn. The resulting profiles look
> like:
> 
>      samples  pcnt function                    DSO
>      _______ _____ ___________________________ _________________
> 
>      8111.00  9.1% _xfs_buf_find               [kernel.kallsyms]
>      4380.00  4.9% __memcpy                    [kernel.kallsyms]
>      4341.00  4.8% __ticket_spin_lock          [kernel.kallsyms]
>      3401.00  3.8% kmem_cache_alloc            [kernel.kallsyms]
>      2856.00  3.2% xfs_log_commit_cil          [kernel.kallsyms]
>      2625.00  2.9% __kmalloc                   [kernel.kallsyms]
>      2380.00  2.7% kfree                       [kernel.kallsyms]
>      2016.00  2.3% kmem_cache_free             [kernel.kallsyms]
> 
> Showing a significant reduction in time spent doing allocation and
> freeing from slabs (kmem_cache_alloc and kmem_cache_free).
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>

This looks good.  I've been testing with it for several days
now as well.  I plan to commit it today or tomorrow.

Reviewed-by: Alex Elder <aelder@sgi.com>


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

[PATCH 2/2] xfs: reduce the number of log forces from tail pushing

[Dave Chinner]

From: Dave Chinner <dchinner@redhat.com>

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: Alex Elder <aelder@sgi.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_trans_ail.c  |   33 ++++++++++++++++++++-------------
 fs/xfs/xfs_trans_priv.h |    1 +
 2 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index c15aa29..9df7f9f 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 212946b..0a6eec6 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
-- 
1.7.5.4

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