Re: oomkillers gone wild.

From: Dave Jones
Date: Tue Jun 05 2012 - 13:44:58 EST


On Mon, Jun 04, 2012 at 04:30:57PM -0700, David Rientjes wrote:
> On Mon, 4 Jun 2012, Dave Jones wrote:
>
> > we picked this..
> >
> > [21623.066911] [ 588] 0 588 22206 1 2 0 0 dhclient
> >
> > over say..
> >
> > [21623.116597] [ 7092] 1000 7092 1051124 31660 3 0 0 trinity-child3
> >
> > What went wrong here ?
> >
> > And why does that score look so.. weird.
> >
>
> It sounds like it's because pid 588 has uid=0 and the adjustment for root
> processes is causing an overflow. I assume this fixes it?

Still doesn't seem right..

eg..

[42309.542776] [ pid ] uid tgid total_vm rss cpu oom_adj oom_score_adj name
..
[42309.553933] [ 500] 81 500 5435 1 4 -13 -900 dbus-daemon
..
[42309.597531] [ 9054] 1000 9054 528677 14540 3 0 0 trinity-child3
..

[42309.643057] Out of memory: Kill process 500 (dbus-daemon) score 511952 or sacrifice child
[42309.643620] Killed process 500 (dbus-daemon) total-vm:21740kB, anon-rss:0kB, file-rss:4kB

and a slew of similar 'wrong process' death spiral kills follows..


Dave

--
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/