Skip to contentSkip to conversation

xfs: RCU inode freeing and lookups V2

PATCH New Dave Chinner 1 participant 3 messages Nov 29, 2010 XFS filesystem

lore
Share & tools
lore
#0 lore raw

cover xfs: RCU inode freeing and lookups V2

This series converts the XFS inode cache to use SLAB_DESTROY_BY_RCU for freeing of the inodes and uses RCU locking for all the lookups. It uses the ip->i_ino values and ip->i_flags & XFS_IRECLAIM being checked under the ip->i_flags_lock to detect inodes that have been freed during lookups.

Version 2:

- check ip->i_ino under i_flags lock on cache hit
- remove duplicate ip->i_ino == 0 check in xfs_dqrele_inode
- Fixed inode cluster walks to check for valid i_ino under i_flags_lock.
- Fixed ag walk lookups to check i_ino under i_flags_lock.

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

#1 lore raw

PATCH 1/2 xfs: convert inode cache lookups to use RCU locking

From: Dave Chinner <[email protected]>

With delayed logging greatly increasing the sustained parallelism of inode operations, the inode cache locking is showing significant read vs write contention when inode reclaim runs at the same time as lookups. There is also a lot more write lock acquistions than there are read locks (4:1 ratio) so the read locking is not really buying us much in the way of parallelism.

To avoid the read vs write contention, change the cache to use RCU locking on the read side. To avoid needing to RCU free every single inode, use the built in slab RCU freeing mechanism. This requires us to be able to detect lookups of freed inodes, so enѕure that ever freed inode has an inode number of zero and the XFS_IRECLAIM flag set. We already check the XFS_IRECLAIM flag in cache hit lookup path, but also add a check for a zero inode number as well.

We canthen convert all the read locking lockups to use RCU read side locking and hence remove all read side locking.

---
 fs/xfs/linux-2.6/xfs_sync.c |   27 ++++++++++++++++-----
 fs/xfs/xfs_iget.c           |   43 +++++++++++++++++++++++++++--------
 fs/xfs/xfs_inode.c          |   52 +++++++++++++++++++++++++++++++++----------
 3 files changed, 93 insertions(+), 29 deletions(-)
fs/xfs/linux-2.6/xfs_sync.c +20 -7
index afb0d7c..5ee02d7 100644
@@ -53,14 +53,20 @@ xfs_inode_ag_walk_grab(
 {
 	struct inode		*inode = VFS_I(ip);
 
+	/* check for stale RCU freed inode */
+	spin_lock(&ip->i_flags_lock);
+	if (!ip->i_ino)
+		goto out_unlock_noent;
+
+	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
+	if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+		goto out_unlock_noent;
+	spin_unlock(&ip->i_flags_lock);
+
 	/* nothing to sync during shutdown */
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return EFSCORRUPTED;
 
-	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
-	if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
-		return ENOENT;
-
 	/* If we can't grab the inode, it must on it's way to reclaim. */
 	if (!igrab(inode))
 		return ENOENT;
@@ -72,6 +78,10 @@ xfs_inode_ag_walk_grab(
 
 	/* inode is valid */
 	return 0;
+
+out_unlock_noent:
+	spin_unlock(&ip->i_flags_lock);
+	return ENOENT;
 }
 
 STATIC int
@@ -98,12 +108,12 @@ restart:
 		int		error = 0;
 		int		i;
 
-		read_lock(&pag->pag_ici_lock);
+		rcu_read_lock();
 		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
 					(void **)batch, first_index,
 					XFS_LOOKUP_BATCH);
 		if (!nr_found) {
-			read_unlock(&pag->pag_ici_lock);
+			rcu_read_unlock();
 			break;
 		}
 
@@ -129,7 +139,7 @@ restart:
 		}
 
 		/* unlock now we've grabbed the inodes. */
-		read_unlock(&pag->pag_ici_lock);
+		rcu_read_unlock();
 
 		for (i = 0; i < nr_found; i++) {
 			if (!batch[i])
@@ -639,6 +649,9 @@ xfs_reclaim_inode_grab(
 	struct xfs_inode	*ip,
 	int			flags)
 {
+	/* check for stale RCU freed inode */
+	if (!ip->i_ino)
+		return 1;
 
 	/*
 	 * do some unlocked checks first to avoid unnecceary lock traffic.
fs/xfs/xfs_iget.c +33 -10

109 lines not on this page · raw message

fs/xfs/xfs_inode.c +40 -12

98 lines not on this page · raw message

Signature · 6 lines
1.7.2.3

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
#2 lore raw

PATCH 2/2 xfs: convert pag_ici_lock to a spin lock

In reply to Dave Chinner

From: Dave Chinner <[email protected]>

now that we are using RCU protection for the inode cache lookups, the lock is only needed on the modification side. Hence it is not necessary for the lock to be a rwlock as there are no read side holders anymore. Convert it to a spin lock to reflect it's exclusive nature.

---
 fs/xfs/linux-2.6/xfs_sync.c |   14 +++++++-------
 fs/xfs/xfs_ag.h             |    2 +-
 fs/xfs/xfs_iget.c           |   10 +++++-----
 fs/xfs/xfs_mount.c          |    2 +-
 4 files changed, 14 insertions(+), 14 deletions(-)
fs/xfs/linux-2.6/xfs_sync.c +7 -7
index 5ee02d7..d3b3b4f 100644
@@ -602,12 +602,12 @@ xfs_inode_set_reclaim_tag(
 	struct xfs_perag *pag;
 
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-	write_lock(&pag->pag_ici_lock);
+	spin_lock(&pag->pag_ici_lock);
 	spin_lock(&ip->i_flags_lock);
 	__xfs_inode_set_reclaim_tag(pag, ip);
 	__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
 	spin_unlock(&ip->i_flags_lock);
-	write_unlock(&pag->pag_ici_lock);
+	spin_unlock(&pag->pag_ici_lock);
 	xfs_perag_put(pag);
 }
 
@@ -808,12 +808,12 @@ reclaim:
 	 * added to the tree assert that it's been there before to catch
 	 * problems with the inode life time early on.
 	 */
-	write_lock(&pag->pag_ici_lock);
+	spin_lock(&pag->pag_ici_lock);
 	if (!radix_tree_delete(&pag->pag_ici_root,
 				XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
 		ASSERT(0);
 	__xfs_inode_clear_reclaim(pag, ip);
-	write_unlock(&pag->pag_ici_lock);
+	spin_unlock(&pag->pag_ici_lock);
 
 	/*
 	 * Here we do an (almost) spurious inode lock in order to coordinate
@@ -877,14 +877,14 @@ restart:
 			struct xfs_inode *batch[XFS_LOOKUP_BATCH];
 			int	i;
 
-			write_lock(&pag->pag_ici_lock);
+			spin_lock(&pag->pag_ici_lock);
 			nr_found = radix_tree_gang_lookup_tag(
 					&pag->pag_ici_root,
 					(void **)batch, first_index,
 					XFS_LOOKUP_BATCH,
 					XFS_ICI_RECLAIM_TAG);
 			if (!nr_found) {
-				write_unlock(&pag->pag_ici_lock);
+				spin_unlock(&pag->pag_ici_lock);
 				break;
 			}
 
@@ -911,7 +911,7 @@ restart:
 			}
 
 			/* unlock now we've grabbed the inodes. */
-			write_unlock(&pag->pag_ici_lock);
+			spin_unlock(&pag->pag_ici_lock);
 
 			for (i = 0; i < nr_found; i++) {
 				if (!batch[i])
fs/xfs/xfs_ag.h +1 -1
index 63c7a1a..58632cc 100644
@@ -227,7 +227,7 @@ typedef struct xfs_perag {
 
 	atomic_t        pagf_fstrms;    /* # of filestreams active in this AG */
 
-	rwlock_t	pag_ici_lock;	/* incore inode lock */
+	spinlock_t	pag_ici_lock;	/* incore inode cache lock */
 	struct radix_tree_root pag_ici_root;	/* incore inode cache root */
 	int		pag_ici_reclaimable;	/* reclaimable inodes */
 	struct mutex	pag_ici_reclaim_lock;	/* serialisation point */
fs/xfs/xfs_iget.c +5 -5
index 0d2b6d2..f6845e1 100644
@@ -236,14 +236,14 @@ xfs_iget_cache_hit(
 			goto out_error;
 		}
 
-		write_lock(&pag->pag_ici_lock);
+		spin_lock(&pag->pag_ici_lock);
 		spin_lock(&ip->i_flags_lock);
 		ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM);
 		ip->i_flags |= XFS_INEW;
 		__xfs_inode_clear_reclaim_tag(mp, pag, ip);
 		inode->i_state = I_NEW;
 		spin_unlock(&ip->i_flags_lock);
-		write_unlock(&pag->pag_ici_lock);
+		spin_unlock(&pag->pag_ici_lock);
 	} else {
 		/* If the VFS inode is being torn down, pause and try again. */
 		if (!igrab(inode)) {
@@ -321,7 +321,7 @@ xfs_iget_cache_miss(
 			BUG();
 	}
 
-	write_lock(&pag->pag_ici_lock);
+	spin_lock(&pag->pag_ici_lock);
 
 	/* insert the new inode */
 	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
@@ -336,14 +336,14 @@ xfs_iget_cache_miss(
 	ip->i_udquot = ip->i_gdquot = NULL;
 	xfs_iflags_set(ip, XFS_INEW);
 
-	write_unlock(&pag->pag_ici_lock);
+	spin_unlock(&pag->pag_ici_lock);
 	radix_tree_preload_end();
 
 	*ipp = ip;
 	return 0;
 
 out_preload_end:
-	write_unlock(&pag->pag_ici_lock);
+	spin_unlock(&pag->pag_ici_lock);
 	radix_tree_preload_end();
 	if (lock_flags)
 		xfs_iunlock(ip, lock_flags);
fs/xfs/xfs_mount.c +1 -1
index 98cb266..a33ab94 100644
@@ -634,7 +634,7 @@ xfs_initialize_perag(
 			goto out_unwind;
 		pag->pag_agno = index;
 		pag->pag_mount = mp;
-		rwlock_init(&pag->pag_ici_lock);
+		spin_lock_init(&pag->pag_ici_lock);
 		mutex_init(&pag->pag_ici_reclaim_lock);
 		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
 		spin_lock_init(&pag->pag_buf_lock);
Signature · 6 lines
1.7.2.3

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs