xfs: bulk AIL insertion during transaction commit

When inserting items into the AIL from the transaction committed
callbacks, we take the AIL lock for every single item that is to be
inserted. For a CIL checkpoint commit, this can be tens of thousands
of individual inserts, yet almost all of the items will be inserted
at the same point in the AIL because they have the same index.

To reduce the overhead and contention on the AIL lock for such
operations, introduce a "bulk insert" operation which allows a list
of log items with the same LSN to be inserted in a single operation
via a list splice. To do this, we need to pre-sort the log items
being committed into a temporary list for insertion.

The complexity is that not every log item will end up with the same
LSN, and not every item is actually inserted into the AIL. Items
that don't match the commit LSN will be inserted and unpinned as per
the current one-at-a-time method (relatively rare), while items that
are not to be inserted will be unpinned and freed immediately. Items
that are to be inserted at the given commit lsn are placed in a
temporary array and inserted into the AIL in bulk each time the
array fills up.

As a result of this, we trade off AIL hold time for a significant
reduction in traffic. lock_stat output shows that the worst case
hold time is unchanged, but contention from AIL inserts drops by an
order of magnitude and the number of lock traversal decreases
significantly.

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

1 files changed, 78 insertions, 1 deletions

diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index f6d956b..f80a067 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1350,7 +1350,7 @@ xfs_trans_fill_vecs(
  * they could be immediately flushed and we'd have to race with the flusher
  * trying to pull the item from the AIL as we add it.
  */
-void
+static void
 xfs_trans_item_committed(
 	struct xfs_log_item	*lip,
 	xfs_lsn_t		commit_lsn,
@@ -1425,6 +1425,83 @@ xfs_trans_committed(
 	xfs_trans_free(tp);
 }
 
+static inline void
+xfs_log_item_batch_insert(
+	struct xfs_ail		*ailp,
+	struct xfs_log_item	**log_items,
+	int			nr_items,
+	xfs_lsn_t		commit_lsn)
+{
+	int	i;
+
+	spin_lock(&ailp->xa_lock);
+	/* xfs_trans_ail_update_bulk drops ailp->xa_lock */
+	xfs_trans_ail_update_bulk(ailp, log_items, nr_items, commit_lsn);
+
+	for (i = 0; i < nr_items; i++)
+		IOP_UNPIN(log_items[i], 0);
+}
+
+/*
+ * Bulk operation version of xfs_trans_committed that takes a log vector of
+ * items to insert into the AIL. This uses bulk AIL insertion techniques to
+ * minimise lock traffic.
+ */
+void
+xfs_trans_committed_bulk(
+	struct xfs_ail		*ailp,
+	struct xfs_log_vec	*log_vector,
+	xfs_lsn_t		commit_lsn,
+	int			aborted)
+{
+#define LOG_ITEM_BATCH_SIZE	32
+	struct xfs_log_item	*log_items[LOG_ITEM_BATCH_SIZE];
+	struct xfs_log_vec	*lv;
+	int			i = 0;
+
+	/* unpin all the log items */
+	for (lv = log_vector; lv; lv = lv->lv_next ) {
+		struct xfs_log_item	*lip = lv->lv_item;
+		xfs_lsn_t		item_lsn;
+
+		if (aborted)
+			lip->li_flags |= XFS_LI_ABORTED;
+		item_lsn = IOP_COMMITTED(lip, commit_lsn);
+
+		/* item_lsn of -1 means the item was freed */
+		if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
+			continue;
+
+		if (item_lsn != commit_lsn) {
+
+			/*
+			 * Not a bulk update option due to unusual item_lsn.
+			 * Push into AIL immediately, rechecking the lsn once
+			 * we have the ail lock. Then unpin the item.
+			 */
+			spin_lock(&ailp->xa_lock);
+			if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0)
+				xfs_trans_ail_update(ailp, lip, item_lsn);
+			else
+				spin_unlock(&ailp->xa_lock);
+			IOP_UNPIN(lip, 0);
+			continue;
+		}
+
+		/* Item is a candidate for bulk AIL insert.  */
+		log_items[i++] = lv->lv_item;
+		if (i >= LOG_ITEM_BATCH_SIZE) {
+			xfs_log_item_batch_insert(ailp, log_items,
+					LOG_ITEM_BATCH_SIZE, commit_lsn);
+			i = 0;
+		}
+	}
+
+	/* make sure we insert the remainder! */
+	if (i)
+		xfs_log_item_batch_insert(ailp, log_items, i, commit_lsn);
+}
+
 /*
  * Called from the trans_commit code when we notice that
  * the filesystem is in the middle of a forced shutdown.