system death under oom - 3.7.9

2013-04-06 Thread Ilia Mirkin
On Sat, Apr 6, 2013 at 5:01 AM, Ilia Mirkin wrote: > On Mon, Apr 1, 2013 at 4:14 PM, Christoph Lameter wrote: >> On Wed, 27 Mar 2013, Ilia Mirkin wrote: >> >>> The GPF happens at +160, which is in the argument setup for the >>> cmpxchg in slab_alloc_node. I think it's the call to >>> get_freepoin

system death under oom - 3.7.9

2013-04-06 Thread Ilia Mirkin
On Mon, Apr 1, 2013 at 4:14 PM, Christoph Lameter wrote: > On Wed, 27 Mar 2013, Ilia Mirkin wrote: > >> The GPF happens at +160, which is in the argument setup for the >> cmpxchg in slab_alloc_node. I think it's the call to >> get_freepointer(). There was a similar bug report a while back, >> http

Re: system death under oom - 3.7.9

2013-04-06 Thread Ilia Mirkin
On Sat, Apr 6, 2013 at 5:01 AM, Ilia Mirkin wrote: > On Mon, Apr 1, 2013 at 4:14 PM, Christoph Lameter wrote: >> On Wed, 27 Mar 2013, Ilia Mirkin wrote: >> >>> The GPF happens at +160, which is in the argument setup for the >>> cmpxchg in slab_alloc_node. I think it's the call to >>> get_freepoin

Re: system death under oom - 3.7.9

2013-04-06 Thread Ilia Mirkin
On Mon, Apr 1, 2013 at 4:14 PM, Christoph Lameter wrote: > On Wed, 27 Mar 2013, Ilia Mirkin wrote: > >> The GPF happens at +160, which is in the argument setup for the >> cmpxchg in slab_alloc_node. I think it's the call to >> get_freepointer(). There was a similar bug report a while back, >> http

system death under oom - 3.7.9

2013-03-29 Thread Ilia Mirkin
On Fri, Mar 29, 2013 at 11:22 AM, Michal Hocko wrote: > On Wed 27-03-13 14:25:36, Ilia Mirkin wrote: >> Hello, >> >> My system died last night apparently due to OOM conditions. Note that >> I don't have any swap set up, but my understanding is that this is not >> required. The full log is at: http

Re: system death under oom - 3.7.9

2013-03-29 Thread Ilia Mirkin
On Fri, Mar 29, 2013 at 11:22 AM, Michal Hocko wrote: > On Wed 27-03-13 14:25:36, Ilia Mirkin wrote: >> Hello, >> >> My system died last night apparently due to OOM conditions. Note that >> I don't have any swap set up, but my understanding is that this is not >> required. The full log is at: http