From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933152AbXCVPPG (ORCPT ); Thu, 22 Mar 2007 11:15:06 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S933131AbXCVPPG (ORCPT ); Thu, 22 Mar 2007 11:15:06 -0400 Received: from mx12.bbn.com ([128.33.0.81]:37278 "EHLO mx12.bbn.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933142AbXCVPPF (ORCPT ); Thu, 22 Mar 2007 11:15:05 -0400 X-Greylist: delayed 1570 seconds by postgrey-1.27 at vger.kernel.org; Thu, 22 Mar 2007 11:15:05 EDT Message-ID: <46029755.3080107@bbn.com> Date: Thu, 22 Mar 2007 10:48:53 -0400 From: Dan Halbert User-Agent: Thunderbird 1.5.0.9 (Windows/20061207) MIME-Version: 1.0 To: linux-kernel@vger.kernel.org Subject: Re: data corruption with nvidia chipsets and IDE/SATA drives // memory hole mapping related bug?! Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org I'd like to mention what might be a new twist on this problem. We are seeing the same kind of 4k-block data corruption on multiple Tyan dual-Opteron boards (S3870) with a ServerWorks chipset, not Nvidia. I wonder if it really an Nvidia-specific issue. The Nvidia boards are a lot more popular, so maybe it's just more likely to be seen with Nvidia. I added a more detailed comment about this to the kernel bug report: http://bugzilla.kernel.org/show_bug.cgi?id=7768#c15.