xfs
[Top] [All Lists]

Re: [patch] xfs: properly account for reclaimed inodes

To: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: Re: [patch] xfs: properly account for reclaimed inodes
From: Dave Chinner <david@xxxxxxxxxxxxx>
Date: Sat, 2 Oct 2010 00:02:37 +1000
Cc: xfs@xxxxxxxxxxx, John Hawley <warthog9@xxxxxxxxxx>, linux-kernel@xxxxxxxxxxxxxxx, stable@xxxxxxxxxx
In-reply-to: <20101001074354.GF2618@xxxxxxxxxxx>
References: <20101001074354.GF2618@xxxxxxxxxxx>
User-agent: Mutt/1.5.20 (2009-06-14)
On Fri, Oct 01, 2010 at 09:43:54AM +0200, Johannes Weiner wrote:
> 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@xxxxxxxxxxx>
> Cc: stable@xxxxxxxxxx

Looks OK to me, and has run through a few hours of testing without
problems.

Reviewed-by: Dave Chinner <dchinner@xxxxxxxxxx>

Cheers,

Dave.
-- 
Dave Chinner
david@xxxxxxxxxxxxx

<Prev in Thread] Current Thread [Next in Thread>