From mboxrd@z Thu Jan 1 00:00:00 1970 From: Roger Heflin Subject: Re: Issues with sata_nv and 2 disks under 2.6.16 and 2.6.17-rc2 Date: Wed, 26 Apr 2006 09:42:26 -0500 Message-ID: <444F86D2.7030000@atipa.com> References: <8E8F647D7835334B985D069AE964A4F7011B2606@ECQCMTLMAIL1.quebec.int.ec.gc.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from EXCHG2003.microtech-ks.com ([24.124.14.122]:52730 "EHLO EXCHG2003.microtech-ks.com") by vger.kernel.org with ESMTP id S932456AbWDZOm1 (ORCPT ); Wed, 26 Apr 2006 10:42:27 -0400 In-Reply-To: <8E8F647D7835334B985D069AE964A4F7011B2606@ECQCMTLMAIL1.quebec.int.ec.gc.ca> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: "Fortier,Vincent [Montreal]" Cc: Linux-Kernel , linux-ide@vger.kernel.org Fortier,Vincent [Montreal] wrote: > I think I might be having the "same type of bug" or something related using sata_via? > Bug opened at bugzilla: http://bugzilla.kernel.org/show_bug.cgi?id=6317 > > This started appearing with 2.6.16. It often does it using only one SATA HD. It does not do it at every boot but often starts doing it after a little while (a few hours...) and finally hanging my PC. > > - vin > > I can duplicate my problem everything, and I can make it stop a will. doing "dd if=/dev/sda of=/dev/null bs=64k &" and then "dd if=/dev/sdb of=/dev/null bs=64k &" will cause the problem within a couple of seconds. Doing "kill %1 %2" (assuming the dd's are %1 and %2) will stop the machine from hanging on disk io within 30-60 seconds. Once it hangs it does not appear to do any disk io until the offending processes are killed. Roger