From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752275Ab1DUSg4 (ORCPT ); Thu, 21 Apr 2011 14:36:56 -0400 Received: from mx1.fusionio.com ([64.244.102.30]:58849 "EHLO mx1.fusionio.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750988Ab1DUSgz (ORCPT ); Thu, 21 Apr 2011 14:36:55 -0400 X-ASG-Debug-ID: 1303411014-03d6a57329f95f0001-xx1T2L X-Barracuda-Envelope-From: JAxboe@fusionio.com Message-ID: <4DB07942.20209@fusionio.com> Date: Thu, 21 Apr 2011 20:36:50 +0200 From: Jens Axboe MIME-Version: 1.0 To: Christian Kujau CC: Linus Torvalds , Christoph Hellwig , Michael Guntsche , "linux-kernel@vger.kernel.org" Subject: Re: 2.6.39 Block layer regression was [Bug] Boot hangs with 2.6.39-rc[123]] References: <20110415035451@it-loops.com> <20110415042255.GC27928@infradead.org> <4DA7E202.4000307@fusionio.com> <4DB077AF.7020909@nerdbynature.de> X-ASG-Orig-Subj: Re: 2.6.39 Block layer regression was [Bug] Boot hangs with 2.6.39-rc[123]] In-Reply-To: <4DB077AF.7020909@nerdbynature.de> Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit X-Barracuda-Connect: mail1.int.fusionio.com[10.101.1.21] X-Barracuda-Start-Time: 1303411014 X-Barracuda-URL: http://10.101.1.180:8000/cgi-mod/mark.cgi X-Barracuda-Spam-Score: 0.00 X-Barracuda-Spam-Status: No, SCORE=0.00 using per-user scores of TAG_LEVEL=1000.0 QUARANTINE_LEVEL=1000.0 KILL_LEVEL=9.0 tests= X-Barracuda-Spam-Report: Code version 3.2, rules version 3.2.2.61525 Rule breakdown below pts rule name description ---- ---------------------- -------------------------------------------------- Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 2011-04-21 20:30, Christian Kujau wrote: > Linus Torvalds wrote on 2011-04-21 10:59 : >> As of right now, all _known_ block bugs should be fixed in the stuff I >> just pushed out, with the current top-of-tree being the merge of the >> IDE CD endless loop issue and the NULL ptr oops at elevator change >> time: > > OK, thanks. > >> That said, that udevd message of yours would imply a full root >> filesystem, which can cause any amount of issues at boot time.. > > My /dev is mounted as udev and is 10MB in size, which is more than > enough for kernels < 2.6.39. But with 2.6.39 something changed and > /dev/.udev/queue.bin is growing to 7 MB and more, udevd is spinning like > crazy and the OOM is reaping processes. > > I'm currently in the middle of a bisect, with 11 steps to go on this > PowerBook G4 :-\ Please try Linus -git as of now, it could be the excessive udev events for media change that is causing your problem. -- Jens Axboe