From: Badari Pulavarty Subject: Re: ext3 fsx failures on 2.6.19-rc1 Date: Tue, 10 Oct 2006 09:41:27 -0700 Message-ID: <1160498487.17103.30.camel@dyn9047017100.beaverton.ibm.com> References: <1160436605.17103.27.camel@dyn9047017100.beaverton.ibm.com> <20061010123059.GJ23622@atrey.karlin.mff.cuni.cz> Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: akpm@osdl.org, esandeen@redhat.com, ext4 , lkml , Dave Jones Return-path: Received: from e32.co.us.ibm.com ([32.97.110.150]:54926 "EHLO e32.co.us.ibm.com") by vger.kernel.org with ESMTP id S1030194AbWJJQlu (ORCPT ); Tue, 10 Oct 2006 12:41:50 -0400 To: Jan Kara In-Reply-To: <20061010123059.GJ23622@atrey.karlin.mff.cuni.cz> Sender: linux-ext4-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On Tue, 2006-10-10 at 14:30 +0200, Jan Kara wrote: > Hi, > > > I am having fsx failures on 2.6.19-rc1. > :( > > > I don't have any useful information at this time to track it down. > > I am running 4 copies of fsx (+ fsstress) on a 1k filesystem and > > one copy of fsx dies. > How long does it take? Random. It happens any where from 1 hours to 6 hours. > > > fsx-linux[20667]: segfault at 00000000ffffffff rip 00002af0fe031690 rsp > > 00007fffacc03b88 error 4 > > > > READ BAD DATA: offset = 0xa352, size = 0x5fef > > OFFSET GOOD BAD RANGE > > 0x df90 0x48e4 0x0000 0x 70 > > operation# (mod 256) for the bad data unknown, check HOLE and EXTEND ops > Hmm, so fsx-linux wrote something and read back zeros. Strange. Do you > know what that 'segfault' message means? I cannot find it in my copy of > fsx-linux... > > fsx got a segmentation fault and died. These are the messages in the dmesg. Thanks, Badari