linux-kernel - Re: Found the commit that causes the OOMs

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: <20090701112705.GA3102@localhost>
Date:	Wed, 1 Jul 2009 19:27:05 +0800
From:	Wu Fengguang <fengguang.wu@...il.com>
To:	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
Cc:	Rik van Riel <riel@...hat.com>,
	David Woodhouse <dwmw2@...radead.org>,
	David Howells <dhowells@...hat.com>,
	Minchan Kim <minchan.kim@...il.com>,
	Mel Gorman <mel@....ul.ie>,
	Johannes Weiner <hannes@...xchg.org>,
	Andrew Morton <akpm@...ux-foundation.org>,
	LKML <linux-kernel@...r.kernel.org>,
	Christoph Lameter <cl@...ux-foundation.org>,
	"peterz@...radead.org" <peterz@...radead.org>,
	"tytso@....edu" <tytso@....edu>,
	"linux-mm@...ck.org" <linux-mm@...ck.org>,
	"elladan@...imo.com" <elladan@...imo.com>,
	"npiggin@...e.de" <npiggin@...e.de>,
	"Barnes, Jesse" <jesse.barnes@...el.com>
Subject: Re: Found the commit that causes the OOMs

On Wed, Jul 01, 2009 at 01:30:51PM +0900, KOSAKI Motohiro wrote:
> > > > The question is: Why kswapd reclaims are absent here?

Ah, maybe kswapd simply didn't have the opportunity to be scheduled
for running, because msgctl11 is busy forking thousands of processes?

> > > if direct reclaim isolate all pages, kswapd can't reclaim any pages.
> > 
> > OOM will occur in that condition. What happened before that time?
> 
> maybe yes, maybe no.
> At first test, the system still have droppable file cache. if direct
> reclaim luckly take it, the benchmark become successful end, I
> think.

Yes that's the main difference between first and second run. Note that
file cache can be dropped quickly, while the pageout of tmpfs pages
populated by msgctl11 itself takes time.

Thanks,
Fengguang
--
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/