[RFC] [PATCH] Cgroup based OOM killer controller

[Alan Cox]

On Tue, 27 Jan 2009 01:24:31 +0530
Balbir Singh <balbir at linux.vnet.ibm.com> wrote:

> * Nikanth Karthikesan <knikanth at suse.de> [2009-01-21 16:38:21]:
> 
> > As Alan Cox suggested/wondered in this thread, 
> > http://lkml.org/lkml/2009/1/12/235 , this is a container group based approach 
> > to override the oom killer selection without losing all the benefits of the 
> > current oom killer heuristics and oom_adj interface.
> > 
> > It adds a tunable oom.victim to the oom cgroup. The oom killer will kill the 
> > process using the usual badness value but only within the cgroup with the 
> > maximum value for oom.victim before killing any process from a cgroup with a 
> > lesser oom.victim number. Oom killing could be disabled by setting 
> > oom.victim=0.
> 
> Looking at the patch, I wonder if it is time for user space OOM
> notifications that were discussed during the containers mini-summit.
> The idea is to inform user space about OOM's and let user space take
> action, if no action is taken, the default handler kicks in.

The OLPC folks (Marcelo I believe) posted code for this and I believe
OLPC is using this functionality internally so that under memory pressure
(before we actually hit OOM) programs can respond by doing stuff like
evicting caches.