From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id p2U1esYV000512 for ; Tue, 29 Mar 2011 20:40:54 -0500 Received: from ipmail07.adl2.internode.on.net (localhost [127.0.0.1]) by cuda.sgi.com (Spam Firewall) with ESMTP id 8373615A40EB for ; Tue, 29 Mar 2011 18:44:03 -0700 (PDT) Received: from ipmail07.adl2.internode.on.net (ipmail07.adl2.internode.on.net [150.101.137.131]) by cuda.sgi.com with ESMTP id 5AcGzo45H2fILcbi for ; Tue, 29 Mar 2011 18:44:03 -0700 (PDT) Date: Wed, 30 Mar 2011 12:44:00 +1100 From: Dave Chinner Subject: Re: XFS memory allocation deadlock in 2.6.38 Message-ID: <20110330014400.GK3008@dastard> References: <20110324174311.GA31576@infradead.org> <081DDE43F61F3D43929A181B477DCA95639B5349@MSXAOA6.twosigma.com> <081DDE43F61F3D43929A181B477DCA95639B534E@MSXAOA6.twosigma.com> <081DDE43F61F3D43929A181B477DCA95639B5359@MSXAOA6.twosigma.com> <20110329192434.GA10536@infradead.org> <081DDE43F61F3D43929A181B477DCA95639B535D@MSXAOA6.twosigma.com> <20110330000942.GI3008@dastard> <081DDE43F61F3D43929A181B477DCA95639B5364@MSXAOA6.twosigma.com> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <081DDE43F61F3D43929A181B477DCA95639B5364@MSXAOA6.twosigma.com> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: Sean Noonan Cc: Trammell Hudson , Christos Zoulas , Martin Bligh , "'linux-kernel@vger.kernel.org'" , Stephen Degler , 'Christoph Hellwig' , "'linux-mm@kvack.org'" , "'linux-xfs@oss.sgi.com'" , 'Michel Lespinasse' On Tue, Mar 29, 2011 at 09:32:06PM -0400, Sean Noonan wrote: > > Ok, so that looks like root cause of the problem. can you try the > > patch below to see if it fixes the problem (without any other > > patches applied or reverted). > > It looks like this does fix the deadlock problem. However, it > appears to come at the price of significantly higher mmap startup > costs. It shouldn't make any difference to startup costs with the current code uses read faults to populate the region and that doesn't cause any allocation to occur and hence this code is not executed during the populate phase. Is this repeatable or is it just a one-off result? Cheers, Dave. -- Dave Chinner david@fromorbit.com _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755375Ab1C3BoG (ORCPT ); Tue, 29 Mar 2011 21:44:06 -0400 Received: from ipmail07.adl2.internode.on.net ([150.101.137.131]:33147 "EHLO ipmail07.adl2.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753785Ab1C3BoF (ORCPT ); Tue, 29 Mar 2011 21:44:05 -0400 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AjoFAHeHkk15LK5JTmdsb2JhbAClUAsBASADIyW/cw2FXQQ Date: Wed, 30 Mar 2011 12:44:00 +1100 From: Dave Chinner To: Sean Noonan Cc: "'Christoph Hellwig'" , "'Michel Lespinasse'" , "'linux-kernel@vger.kernel.org'" , Martin Bligh , Trammell Hudson , Christos Zoulas , "'linux-xfs@oss.sgi.com'" , Stephen Degler , "'linux-mm@kvack.org'" Subject: Re: XFS memory allocation deadlock in 2.6.38 Message-ID: <20110330014400.GK3008@dastard> References: <20110324174311.GA31576@infradead.org> <081DDE43F61F3D43929A181B477DCA95639B5349@MSXAOA6.twosigma.com> <081DDE43F61F3D43929A181B477DCA95639B534E@MSXAOA6.twosigma.com> <081DDE43F61F3D43929A181B477DCA95639B5359@MSXAOA6.twosigma.com> <20110329192434.GA10536@infradead.org> <081DDE43F61F3D43929A181B477DCA95639B535D@MSXAOA6.twosigma.com> <20110330000942.GI3008@dastard> <081DDE43F61F3D43929A181B477DCA95639B5364@MSXAOA6.twosigma.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <081DDE43F61F3D43929A181B477DCA95639B5364@MSXAOA6.twosigma.com> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Mar 29, 2011 at 09:32:06PM -0400, Sean Noonan wrote: > > Ok, so that looks like root cause of the problem. can you try the > > patch below to see if it fixes the problem (without any other > > patches applied or reverted). > > It looks like this does fix the deadlock problem. However, it > appears to come at the price of significantly higher mmap startup > costs. It shouldn't make any difference to startup costs with the current code uses read faults to populate the region and that doesn't cause any allocation to occur and hence this code is not executed during the populate phase. Is this repeatable or is it just a one-off result? Cheers, Dave. -- Dave Chinner david@fromorbit.com From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail203.messagelabs.com (mail203.messagelabs.com [216.82.254.243]) by kanga.kvack.org (Postfix) with SMTP id B1C978D0040 for ; Tue, 29 Mar 2011 21:44:10 -0400 (EDT) Date: Wed, 30 Mar 2011 12:44:00 +1100 From: Dave Chinner Subject: Re: XFS memory allocation deadlock in 2.6.38 Message-ID: <20110330014400.GK3008@dastard> References: <20110324174311.GA31576@infradead.org> <081DDE43F61F3D43929A181B477DCA95639B5349@MSXAOA6.twosigma.com> <081DDE43F61F3D43929A181B477DCA95639B534E@MSXAOA6.twosigma.com> <081DDE43F61F3D43929A181B477DCA95639B5359@MSXAOA6.twosigma.com> <20110329192434.GA10536@infradead.org> <081DDE43F61F3D43929A181B477DCA95639B535D@MSXAOA6.twosigma.com> <20110330000942.GI3008@dastard> <081DDE43F61F3D43929A181B477DCA95639B5364@MSXAOA6.twosigma.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <081DDE43F61F3D43929A181B477DCA95639B5364@MSXAOA6.twosigma.com> Sender: owner-linux-mm@kvack.org List-ID: To: Sean Noonan Cc: 'Christoph Hellwig' , 'Michel Lespinasse' , "'linux-kernel@vger.kernel.org'" , Martin Bligh , Trammell Hudson , Christos Zoulas , "'linux-xfs@oss.sgi.com'" , Stephen Degler , "'linux-mm@kvack.org'" On Tue, Mar 29, 2011 at 09:32:06PM -0400, Sean Noonan wrote: > > Ok, so that looks like root cause of the problem. can you try the > > patch below to see if it fixes the problem (without any other > > patches applied or reverted). > > It looks like this does fix the deadlock problem. However, it > appears to come at the price of significantly higher mmap startup > costs. It shouldn't make any difference to startup costs with the current code uses read faults to populate the region and that doesn't cause any allocation to occur and hence this code is not executed during the populate phase. Is this repeatable or is it just a one-off result? Cheers, Dave. -- Dave Chinner david@fromorbit.com -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: email@kvack.org