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]

Message-ID: <2f11576a0911010529t688ed152qbb72c87c85869c45@mail.gmail.com>
Date:	Sun, 1 Nov 2009 22:29:37 +0900
From:	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
To:	David Rientjes <rientjes@...gle.com>
Cc:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.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
Subject: Re: [PATCH] oom_kill: use rss value instead of vm size for badness

> This patch would pick the memory hogging task, "test", first everytime
> just like the current implementation does.  It would then prefer Xorg,
> icedove-bin, and ktorrent next as a starting point.
>
> Admittedly, there are other heuristics that the oom killer uses to create
> a badness score.  But since this patch is only changing the baseline from
> mm->total_vm to get_mm_rss(mm), its behavior in this test case do not
> match the patch description.
>
> The vast majority of the other ooms have identical top 8 candidates:
>
> total_vm
> 673222 test
> 195695 krunner
> 168881 plasma-desktop
> 130567 ktorrent
> 127081 knotify4
> 125881 icedove-bin
> 123036 akregator
> 121869 firefox-bin
>
> rss
> 672271 test
> 42192 Xorg
> 30763 firefox-bin
> 13292 icedove-bin
> 10208 ktorrent
> 9260 akregator
> 8859 plasma-desktop
> 7528 krunner
>
> firefox-bin seems much more preferred in this case than total_vm, but Xorg
> still ranks very high with this patch compared to the current
> implementation.

Hi David,

I'm very interesting your pointing out. thanks good testing.
So, I'd like to clarify your point a bit.

following are badness list on my desktop environment (x86_64 6GB mem).
it show Xorg have pretty small badness score. Do you know why such
different happen?


score    pid        comm
==============================
56382   3241    run-mozilla.sh
23345   3289    run-mozilla.sh
21461   3050    gnome-do
20079   2867    gnome-session
14016   3258    firefox
9212    3306    firefox
8468    3115    gnome-do
6902    3325    emacs
6783    3212    tomboy
4865    2968    python
4861    2948    nautilus
4221    1       init
(snip about 100line)
548     2590    Xorg
--
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/