linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Paul Jackson <pj@sgi.com>
To: David Rientjes <rientjes@google.com>
Cc: menage@google.com, akpm@linux-foundation.org, clameter@sgi.com,
	balbir@linux.vnet.ibm.com, linux-mm@kvack.org
Subject: Re: [patch -mm 7/5] oom: filter tasklist dump by mem_cgroup
Date: Tue, 25 Sep 2007 21:37:57 -0700	[thread overview]
Message-ID: <20070925213757.af33ef01.pj@sgi.com> (raw)
In-Reply-To: <alpine.DEB.0.9999.0709252104180.30932@chino.kir.corp.google.com>

> The OOM killer in -mm no longer checks cpuset_excl_nodes_overlap() to 
> select an overlapping task and, in fact, that function has been removed 
> entirely from kernel/cpuset.c.
> 
> If oom_kill_allocating_tasks is zero (which it is by default), the 
> tasklist is scanned and each task is checked for intersection with 
> current's mems_allowed (task->mems_allowed, not dereferencing 
> task->cpuset).  If it doesn't intersect, its "badness" score is divided by 
> eight.

Yes - I recall seeing that change go by recently.  Seemed good to me.


> Yes, absolutely.
> 
> I think Paul Menage is talking about filtering tasks that are not a member 
> of the same cpuset because we're more familiar with mem_exclusive cpusets.  
> So I think his suggestion was initially to filter based on overlapping 
> mems_allowed instead, which makes sense.
> 
> 	void dump_tasks(const struct mem_cgroup *mem)

As Paul M realized in his reply shortly ago, I missed the simple and
essential detail that we were discussing the dump routine.

It makes more sense now - thanks.

-- 
                  I won't rest till it's the best ...
                  Programmer, Linux Scalability
                  Paul Jackson <pj@sgi.com> 1.925.600.0401

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2007-09-26  4:37 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-09-25 17:13 [patch -mm 6/5] memcontrol: move mm_cgroup to header file David Rientjes
2007-09-25 17:13 ` [patch -mm 7/5] oom: filter tasklist dump by mem_cgroup David Rientjes
2007-09-25 17:48   ` Balbir Singh
2007-09-25 19:18     ` David Rientjes
2007-09-25 18:00   ` Paul Menage
2007-09-25 21:17     ` Christoph Lameter
2007-09-25 22:54       ` Paul Menage
2007-09-26  1:14     ` Paul Jackson
2007-09-26  1:20       ` David Rientjes
2007-09-26  3:56         ` Paul Jackson
2007-09-26  4:14           ` David Rientjes
2007-09-26  4:24             ` David Rientjes
2007-09-26  4:37             ` Paul Jackson [this message]
2007-09-26  1:22       ` Paul Menage
2007-09-26  3:57         ` Paul Jackson
2007-09-26  4:03           ` Paul Menage
2007-09-26  4:30             ` Paul Jackson
2007-09-25 17:18 ` [patch -mm 6/5] memcontrol: move mm_cgroup to header file Balbir Singh
2007-09-25 18:49   ` David Rientjes

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20070925213757.af33ef01.pj@sgi.com \
    --to=pj@sgi.com \
    --cc=akpm@linux-foundation.org \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=clameter@sgi.com \
    --cc=linux-mm@kvack.org \
    --cc=menage@google.com \
    --cc=rientjes@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox