linux-kernel - Re: 2.6.39: crash w/threadirqs option enabled

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: <alpine.LFD.2.02.1105201819310.3078@ionos>
Date:	Fri, 20 May 2011 18:22:35 +0200 (CEST)
From:	Thomas Gleixner <tglx@...utronix.de>
To:	Justin Piszcz <jpiszcz@...idpixels.com>
cc:	LKML <linux-kernel@...r.kernel.org>,
	Alan Piszcz <ap@...arrain.com>, Ingo Molnar <mingo@...e.hu>,
	Peter Zijlstra <peterz@...radead.org>
Subject: Re: 2.6.39: crash w/threadirqs option enabled

On Fri, 20 May 2011, Justin Piszcz wrote:
> On Fri, 20 May 2011, Thomas Gleixner wrote:
> 
> > On Fri, 20 May 2011, Justin Piszcz wrote:
> > > On Fri, 20 May 2011, Thomas Gleixner wrote:
> > > > Does it crash right away or just when doing something particular?
> > > It crashed at 2100, this is when I run a few I/O intensive processes:
> > > - backup (dump ext4 filesystem -> to a separate raid device)
> > > - backup (dump ext4 on remote host -> to separate raid device)
> > > - backup (dump xfs on remote host -> to separate raid device)
> > > 
> > > This looks like it is what caused it to crash.
> > 
> > That narrows it down somewhat, but does not give us a clue at all :(
> > 
> > > > Is the box fully dead after the crash ?
> > > The host was online and I went away for awhile, when I came back the
> > > system
> > > had rebooted on its own (as I lost all of my X windows/etc).
> > 
> > Hmm. Did you have panic_timeout set ?
> 
> Hi,
> 
> No, I do not use panic_timeout or any type of watchdog that would reboot
> the system upon a lockup/crash.

Yuck, that means it ran into a triple fault. Nasty. I have no idea how
to debug that at the moment and I was not able to reproduce on one of
my test systems. Maybe I need to try harder.

Thanks,

	tglx




--
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/