Re: [RFC] [PATCH] Cgroup based OOM killer controller

[Balbir Singh]

* KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx> [2009-01-27 16:02:34]:

> Hi
> 
> > > > 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.
> 

I did see the patches on linux-mm, but a more generic cgroup patch
would help both cases, in the absence of cgroups, the default cgroup
will contain all tasks and can carry out the handling.

> Confused.
> 
> As far as I know, people want the method of flexible cache treating.
> but oom seems less flexible than userland notification.
> 
> Why do you think notification is bad?

I did not find Alan's message confusing or stating that notification
was bad, but I might be misreading it.

-- 
	Balbir
--
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/