Re: OOM-killer and strange RSS value in 3.9-rc7

From: Michal Hocko
Date: Fri May 03 2013 - 11:34:56 EST


On Fri 03-05-13 15:25:25, Christoph Lameter wrote:
> On Fri, 3 May 2013, Han Pingtian wrote:
>
> > On Thu, May 02, 2013 at 03:10:15PM +0000, Christoph Lameter wrote:
> > > On Thu, 2 May 2013, Han Pingtian wrote:
> > >
> > > > Looks like "ibmvscsi" + "slub" can trigger this problem.
> > >
> > > And the next merge of the slab-next tree will also cause SLAB to trigger
> > > this issue. I would like to have this fixes. The slab allocator purpose is
> > > to servr objects that are a fraction of a page and not objects that are
> > > larger than the maximum allowed sizes of the page allocator.
> >
> > So the problem is in memory management code, not in ibmvscis? And looks
> > like there is a fix already?
>
> Both should be fixed.

Could you point to the specific commit(s), please?

> Making requests for large amounts of memory from an allocator that is
> supposed to hand out fraction of a page does not make sense.

AFAIR there were lots of objects in size-512 as well.

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