From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tejun Heo Subject: Re: [PATCH] blacklist NCQ on Seagate Barracuda ST380817AS Date: Sun, 30 Sep 2007 10:29:09 -0700 Message-ID: <46FFDCE5.4060900@gmail.com> References: <20070930160548.235be972@localhost> <20070930152908.1f58d39d@the-village.bc.nu> <20070930164610.20818867@localhost> <46FFBB2D.6060004@garzik.org> <46FFDC5A.7070509@rtr.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: Received: from nz-out-0506.google.com ([64.233.162.235]:61944 "EHLO nz-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755650AbXI3Raq (ORCPT ); Sun, 30 Sep 2007 13:30:46 -0400 Received: by nz-out-0506.google.com with SMTP id s18so2343572nze for ; Sun, 30 Sep 2007 10:30:45 -0700 (PDT) In-Reply-To: <46FFDC5A.7070509@rtr.ca> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Mark Lord Cc: Jeff Garzik , Paolo Ornati , Alan Cox , Linux Kernel Mailing List , linux-ide@vger.kernel.org Mark Lord wrote: > Jeff Garzik wrote: >> Paolo Ornati wrote: >>> I have this problem only with XFS, and even with XFS it goes away >>> mounting with "nobarrier"... >> >> This last is an interesting datapoint. >> >> I wonder if libata has a generic problem with NCQ + FLUSH CACHE. > > Yeah, that's pretty suspicious. Prior to issuing a FLUSH_CACHE op, > one must first drain all outstanding NCQ commands (and not issue new ones). > > I'm sure the code must *try* to do that, but perhaps there's a bug in > there? > Or just another drive bug? If there was such a bug, the aborted commands list should contain both FPDMA commands and FLUSH commands. I don't think command filtering itself is broken. Possibly another quirky firmware but it's strange that this is the only Seagate drive showing this problem. Thanks. -- tejun