linux-kernel - Re: [uml-devel] BUG: soft lockup for a user mode linux image

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 for Android: free password hash cracker in your pocket

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

Message-ID: <20131011090534.GA29330@localhost>
Date:	Fri, 11 Oct 2013 17:05:34 +0800
From:	Fengguang Wu <fengguang.wu@...el.com>
To:	Toralf Förster <toralf.foerster@....de>
Cc:	Richard Weinberger <richard@....at>, Jan Kara <jack@...e.cz>,
	Geert Uytterhoeven <geert@...ux-m68k.org>,
	UML devel <user-mode-linux-devel@...ts.sourceforge.net>,
	"linux-mm@...ck.org" <linux-mm@...ck.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"akpm@...ux-foundation.org" <akpm@...ux-foundation.org>,
	hannes@...xchg.org, darrick.wong@...cle.com,
	Michal Hocko <mhocko@...e.cz>
Subject: Re: [uml-devel] BUG: soft lockup for a user mode linux image

On Fri, Oct 11, 2013 at 04:57:01PM +0800, Fengguang Wu wrote:
> On Fri, Oct 11, 2013 at 10:42:19AM +0200, Toralf Förster wrote:
> > yeah, now the picture becomes more clear
> > ...
> > net.core.warnings = 0                                                                         [ ok ]
> > ick: pause : -717
> >                  ick : min_pause : -177
> >                                    ick : max_pause : -717
> >                                                      ick: pages_dirtied : 14
> >                                                                             ick: task_ratelimit: 0
> 
> Great and thanks! So it's the max pause calculation went wrong.

However I still suspect this is not the main reason for the soft
lockup. Because schedule_timeout() will directly return on negative
timeout. So yes, we have encountered some negative pauses, however
we still need to fix the huge dirtied pages problem which should be
more fundamental. 

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/