From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757054AbYEQSi3 (ORCPT ); Sat, 17 May 2008 14:38:29 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753179AbYEQSiW (ORCPT ); Sat, 17 May 2008 14:38:22 -0400 Received: from smtp1.linux-foundation.org ([140.211.169.13]:49939 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752570AbYEQSiV (ORCPT ); Sat, 17 May 2008 14:38:21 -0400 Date: Sat, 17 May 2008 11:37:35 -0700 (PDT) From: Linus Torvalds To: Alistair John Strachan cc: Jens Axboe , xfs@oss.sgi.com, Neil Brown , Nick Piggin , linux-kernel@vger.kernel.org Subject: Re: XFS/md/blkdev warning (was Re: Linux 2.6.26-rc2) In-Reply-To: <200805171922.56272.alistair@devzero.co.uk> Message-ID: References: <20080512164920.GE16217@kernel.dk> <200805171922.56272.alistair@devzero.co.uk> User-Agent: Alpine 1.10 (LFD 962 2008-03-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 17 May 2008, Alistair John Strachan wrote: > > My guess is that when the kernel runs out of MemFree and starts reclaiming the > cache, something is deadlocking somewhere. Just doing a: > > cat /dev/zero >/path/to/file Do this on the console (and having a serial console or working netconsole is a wonderful thing to log it, because otherwise it will generally just scroll off the screen), and trigger SysRQ-w. That dumps all blocked tasks to the screen. You may need to do echo 1 > /proc/sys/kernel/sysrq before that to enable it. (Or if you have some things still running because they haevn't hit the lock that causes the deadlock, you can try echo w > /proc/sysrq-trigger rather than the key combination). Linus