From: Andrew Vasquez Subject: Re: ext4: (2.6.34-rc4): This should not happen!! Data will be lost Date: Fri, 16 Apr 2010 08:52:21 -0700 Message-ID: <20100416155221.GA57840@plapa.qlogic.org> References: <20100416123526.GW21495@skl-net.de> <4BC87BF6.2040104@redhat.com> <20100416153024.GY25507@skl-net.de> <4BC885B9.2000902@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Andre Noll , "linux-ext4@vger.kernel.org" , Linux Driver , Thomas Helle To: Eric Sandeen Return-path: Received: from vpn.pathscale.com ([198.186.3.75]:37138 "HELO mx.mv.qlogic.com" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with SMTP id S1758229Ab0DPPwW (ORCPT ); Fri, 16 Apr 2010 11:52:22 -0400 Content-Disposition: inline In-Reply-To: <4BC885B9.2000902@redhat.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Fri, 16 Apr 2010, Eric Sandeen wrote: > On 04/16/2010 10:30 AM, Andre Noll wrote: > > On 10:02, Eric Sandeen wrote: > > > >>> I'm seeing the following errors when writing to an ext4 file system: > >>> > >>> qla2xxx 0000:06:09.0: scsi(0:0:0): Abort command issued -- 1 fa6a73 2002. > >>> end_request: I/O error, dev sda, sector 7812771880 > >> > >> Sounds like a hardware failure > > > > Yes, or a problem with the qla2xxx driver. However, it's a bit > > surprising that the hardware survived the stress test for more than > > one day and went south just at the moment the fs was completely filled. > > Hm, that's true. > > Well, the error was on sector 7812771880 of the device ... > > can you reliably write directly to that sector w/o the filesystem in > between? The driver here is simply reporting that the a command's timeout value had been exceeded and the mid-layer began error-recovery with a request to 'abort' the command. The abort-request completed successfully: qla2xxx 0000:06:09.0: scsi(0:0:0): Abort command issued -- 1 fa6a73 2002. I can't explain why the storage did not complete the request in the allotted time. -- av