Messages in this thread | | | Date | Thu, 28 Apr 2011 09:56:58 +1000 | From | Dave Chinner <> | Subject | Re: 2.6.39-rc4+: oom-killer busy killing tasks |
| |
On Thu, Apr 28, 2011 at 08:16:29AM +0900, Minchan Kim wrote: > On Wed, Apr 27, 2011 at 7:28 PM, Dave Chinner <david@fromorbit.com> wrote: > > On Wed, Apr 27, 2011 at 12:46:51AM -0700, Christian Kujau wrote: > >> On Wed, 27 Apr 2011 at 12:26, Dave Chinner wrote: > >> > What this shows is that VFS inode cache memory usage increases until > >> > about the 550 sample mark before the VM starts to reclaim it with > >> > extreme prejudice. At that point, I'd expect the XFS inode cache to > >> > then shrink, and it doesn't. I've got no idea why the either the > >> > >> Do you remember any XFS changes past 2.6.38 that could be related to > >> something like this? > > > > There's plenty of changes that coul dbe the cause - we've changed > > the inode reclaim to run in the background out of a workqueue as > > well as via the shrinker, so it could even be workqueue starvation > > causing the the problem... > > RCU free starvation is another possibility? > https://lkml.org/lkml/2011/4/25/124
You know, I've been waching that thread with interest, but it didn't seem to be related. However, now that I go look at the config file provided, I see:
CONFIG_TINY_RCU=y # CONFIG_SMP is not set CONFIG_PREEMPT_NONE=y
which means it probably is the same rcu free starvation problem as reported in that thread.
Cheers,
Dave. -- Dave Chinner david@fromorbit.com
| |