linux-kernel - Re: [PATCH] oom_kill: use rss value instead of vm size for badness

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Thu, 29 Oct 2009 11:31:47 +0900
From:	Minchan Kim <minchan.kim@...il.com>
To:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc:	David Rientjes <rientjes@...gle.com>, linux-mm@...ck.org,
	linux-kernel@...r.kernel.org,
	Andrew Morton <akpm@...ux-foundation.org>,
	Hugh Dickins <hugh.dickins@...cali.co.uk>,
	Andrea Arcangeli <aarcange@...hat.com>, vedran.furac@...il.com,
	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
Subject: Re: [PATCH] oom_kill: use rss value instead of vm size for badness

On Thu, Oct 29, 2009 at 10:00 AM, KAMEZAWA Hiroyuki
<kamezawa.hiroyu@...fujitsu.com> wrote:
>> I'll wait until the next week to post a new patch.
>> We don't need rapid way.
>>
> I wrote above...but for my mental health, this is bug-fixed version.
> Sorry for my carelessness. David, thank you for your review.
> Regards,
> -Kame
> ==
> From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
>
> It's reported that OOM-Killer kills Gnone/KDE at first...
> And yes, we can reproduce it easily.
>
> Now, oom-killer uses mm->total_vm as its base value. But in recent
> applications, there are a big gap between VM size and RSS size.
> Because
>  - Applications attaches much dynamic libraries. (Gnome, KDE, etc...)
>  - Applications may alloc big VM area but use small part of them.
>    (Java, and multi-threaded applications has this tendency because
>     of default-size of stack.)
>
> I think using mm->total_vm as score for oom-kill is not good.
> By the same reason, overcommit memory can't work as expected.
> (In other words, if we depends on total_vm, using overcommit more positive
>  is a good choice.)
>
> This patch uses mm->anon_rss/file_rss as base value for calculating badness.
>
> Following is changes to OOM score(badness) on an environment with 1.6G memory
> plus memory-eater(500M & 1G).
>
> Top 10 of badness score. (The highest one is the first candidate to be killed)
> Before
> badness program
> 91228   gnome-settings-
> 94210   clock-applet
> 103202  mixer_applet2
> 106563  tomboy
> 112947  gnome-terminal
> 128944  mmap              <----------- 500M malloc
> 129332  nautilus
> 215476  bash              <----------- parent of 2 mallocs.
> 256944  mmap              <----------- 1G malloc
> 423586  gnome-session
>
> After
> badness
> 1911    mixer_applet2
> 1955    clock-applet
> 1986    xinit
> 1989    gnome-session
> 2293    nautilus
> 2955    gnome-terminal
> 4113    tomboy
> 104163  mmap             <----------- 500M malloc.
> 168577  bash             <----------- parent of 2 mallocs
> 232375  mmap             <----------- 1G malloc
>
> seems good for me. Maybe we can tweak this patch more,
> but this one will be a good one as a start point.
>
> Changelog: 2009/10/29
>  - use get_mm_rss() instead of get_mm_counter()
>
> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@...il.com>

Let's start from this.

-- 
Kind regards,
Minchan Kim
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/