Re: [patch] memcg: give current access to memory reserves if it's trying to die

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Thu, 17 Mar 2011 22:17:58 -0700
Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:

> On Fri, 18 Mar 2011 13:35:34 +0900 KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> wrote:
> 
> > On Thu, 17 Mar 2011 16:53:19 -0700
> > Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
> > 
> > > 
> > > Was it deliberate that mem_cgroup_out_of_memory() ignores the oom
> > > notifier callbacks?
> > > 
> > 
> > I'm not sure for what purpose notifier chain for oom exists.
> > At a loock, it's for s390/powerpc Collaborative Memory Manager.. ?
> 
> commit 8bc719d3cab8414938f9ea6e33b58d8810d18068
> Author:     Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
> AuthorDate: Mon Sep 25 23:31:20 2006 -0700
> Commit:     Linus Torvalds <torvalds@xxxxxxxxxxx>
> CommitDate: Tue Sep 26 08:48:47 2006 -0700
> 
>     [PATCH] out of memory notifier
>     
>     Add a notifer chain to the out of memory killer.  If one of the registered
>     callbacks could release some memory, do not kill the process but return and
>     retry the allocation that forced the oom killer to run.
>     
>     The purpose of the notifier is to add a safety net in the presence of
>     memory ballooners.  If the resource manager inflated the balloon to a size
>     where memory allocations can not be satisfied anymore, it is better to
>     deflate the balloon a bit instead of killing processes.
>     
>     The implementation for the s390 ballooner is included.
> 
> > About memcg, notifier to userland already exists and I though I don't
> > need to call CMM callbacks (for now, there is no user with memcg, I guess.)
> 
> Seems to me that the callback should be performed.
> 

Hmm, (for now) memory cgroup just handles user's memory, so any kernel
callback cannot do anything..other than dropping file cache if some
module pins it.

> Or, perhaps, migrate it over to use the shrinker stuff, along with
> suitable handling of the scanning priority.
> 

Ah, yes. callback at oom is too late, I think.

Thanks,
-Kame


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>


[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]