On Mon, 2010-11-22 at 16:11 -0800, Andrew Morton wrote:
quoted text
> > This latest observation we understand may be due to NUMA related
> > allocation issues, and we should probably try to use numactl to ask
> > for a more even allocation. We have not yet tried this. However, it
> is not clear how any issues having to do with that would cause sudden
> > eviction of data already *in* the page cache (on whichever node). 

You don't have anybody messing with /proc/sys/vm/drop_caches, do you?

That can cause massive, otherwise unprovoked page cache eviction.  

-- Dave

--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/