90 lines
2.8 KiB
Diff
90 lines
2.8 KiB
Diff
|
From 81837831b2fd688ee7387a5870e6fd5f136f7825 Mon Sep 17 00:00:00 2001
|
||
|
|
From: Johannes Weiner <hannes@cmpxchg.org>
|
||
|
|
Date: Fri, 1 Oct 2010 07:43:54 +0000
|
||
|
|
Subject: xfs: properly account for reclaimed inodes
|
||
|
|
|
||
|
|
When marking an inode reclaimable, a per-AG counter is increased, the
|
||
|
|
inode is tagged reclaimable in its per-AG tree, and, when this is the
|
||
|
|
first reclaimable inode in the AG, the AG entry in the per-mount tree
|
||
|
|
is also tagged.
|
||
|
|
|
||
|
|
When an inode is finally reclaimed, however, it is only deleted from
|
||
|
|
the per-AG tree. Neither the counter is decreased, nor is the parent
|
||
|
|
tree's AG entry untagged properly.
|
||
|
|
|
||
|
|
Since the tags in the per-mount tree are not cleared, the inode
|
||
|
|
shrinker iterates over all AGs that have had reclaimable inodes at one
|
||
|
|
point in time.
|
||
|
|
|
||
|
|
The counters on the other hand signal an increasing amount of slab
|
||
|
|
objects to reclaim. Since "70e60ce xfs: convert inode shrinker to
|
||
|
|
per-filesystem context" this is not a real issue anymore because the
|
||
|
|
shrinker bails out after one iteration.
|
||
|
|
|
||
|
|
But the problem was observable on a machine running v2.6.34, where the
|
||
|
|
reclaimable work increased and each process going into direct reclaim
|
||
|
|
eventually got stuck on the xfs inode shrinking path, trying to scan
|
||
|
|
several million objects.
|
||
|
|
|
||
|
|
Fix this by properly unwinding the reclaimable-state tracking of an
|
||
|
|
inode when it is reclaimed.
|
||
|
|
|
||
|
|
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
|
||
|
|
Cc: stable@kernel.org
|
||
|
|
Reviewed-by: Dave Chinner <dchinner@redhat.com>
|
||
|
|
Signed-off-by: Alex Elder <aelder@sgi.com>
|
||
|
|
---
|
||
|
|
fs/xfs/linux-2.6/xfs_sync.c | 19 ++++++++++++++-----
|
||
|
|
1 files changed, 14 insertions(+), 5 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
|
||
|
|
index 97275c5..15f3370 100644
|
||
|
|
--- a/fs/xfs/linux-2.6/xfs_sync.c
|
||
|
|
+++ b/fs/xfs/linux-2.6/xfs_sync.c
|
||
|
|
@@ -751,14 +751,11 @@ xfs_inode_set_reclaim_tag(
|
||
|
|
xfs_perag_put(pag);
|
||
|
|
}
|
||
|
|
|
||
|
|
-void
|
||
|
|
-__xfs_inode_clear_reclaim_tag(
|
||
|
|
- xfs_mount_t *mp,
|
||
|
|
+STATIC void
|
||
|
|
+__xfs_inode_clear_reclaim(
|
||
|
|
xfs_perag_t *pag,
|
||
|
|
xfs_inode_t *ip)
|
||
|
|
{
|
||
|
|
- radix_tree_tag_clear(&pag->pag_ici_root,
|
||
|
|
- XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
|
||
|
|
pag->pag_ici_reclaimable--;
|
||
|
|
if (!pag->pag_ici_reclaimable) {
|
||
|
|
/* clear the reclaim tag from the perag radix tree */
|
||
|
|
@@ -772,6 +769,17 @@ __xfs_inode_clear_reclaim_tag(
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
+void
|
||
|
|
+__xfs_inode_clear_reclaim_tag(
|
||
|
|
+ xfs_mount_t *mp,
|
||
|
|
+ xfs_perag_t *pag,
|
||
|
|
+ xfs_inode_t *ip)
|
||
|
|
+{
|
||
|
|
+ radix_tree_tag_clear(&pag->pag_ici_root,
|
||
|
|
+ XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
|
||
|
|
+ __xfs_inode_clear_reclaim(pag, ip);
|
||
|
|
+}
|
||
|
|
+
|
||
|
|
/*
|
||
|
|
* Inodes in different states need to be treated differently, and the return
|
||
|
|
* value of xfs_iflush is not sufficient to get this right. The following table
|
||
|
|
@@ -921,6 +929,7 @@ reclaim:
|
||
|
|
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);
|
||
|
|
|
||
|
|
/*
|
||
|
|
--
|
||
|
|
1.7.3.2
|
||
|
|
|