linux-kernel - scheduling failure on armel with 2.6.32-rc8

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>] [day] [month] [year] [list]

Message-ID: <4B0C66D4.1010402@fifthhorseman.net>
Date:	Tue, 24 Nov 2009 18:05:56 -0500
From:	Daniel Kahn Gillmor <dkg@...thhorseman.net>
To:	linux-kernel@...r.kernel.org
Subject: scheduling failure on armel with 2.6.32-rc8

Hi folks--

I'm running 2.6.32-rc8 from debian packages made by Martin Michlmayr [0]
on a LinkSys NSLU2 (266Mhz arm processor, ixp4xx flavor, armel).  It's
currently hanging with blocked I/O.  Martin suggested i send this info
here to the lkml [1].

Background:

During an I/O-heavy operation (mpd rebuilding its index to a filesystem
stored on a 2GB USB flash drive), the machine became unresponsive.  i'm
hooked into the serial console, and i see messages about blocked tasks
for more than 120 seconds.

I used the magic SysRq to dump blocked processes to the console.

The attached log shows two warnings about blocked processes for 120
seconds, followed by the output of my SysRq call.  I hope it's not too long.

Let me know if there's other debugging i should try.  The machine is
still in this state, and i've got the console attached.  I'm not a
kernel hacker, but i can get you more info if you tell me what you want
and how to get it.

Please CC me on replies, as i'm not currently subscribed to the list.

Regards,

	--dkg

[0] http://people.debian.org/~tbm/armel/kernel/r14655/
[1] http://lists.debian.org/debian-arm/2009/11/msg00105.html

View attachment "blocked.console" of type "text/plain" (30493 bytes)

Download attachment "signature.asc" of type "application/pgp-signature" (892 bytes)