From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tejun Heo Subject: Re: ICH6-M libata disk timeouts 2.6.18 -> 2.6.19 Date: Sat, 13 Jan 2007 11:23:19 +0900 Message-ID: <45A84297.3020408@gmail.com> References: <17923.1168404967@mdt.dhcp.pit.laurelnetworks.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: Received: from an-out-0708.google.com ([209.85.132.241]:34715 "EHLO an-out-0708.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1161197AbXAMCX0 (ORCPT ); Fri, 12 Jan 2007 21:23:26 -0500 Received: by an-out-0708.google.com with SMTP id b33so621478ana for ; Fri, 12 Jan 2007 18:23:25 -0800 (PST) In-Reply-To: <17923.1168404967@mdt.dhcp.pit.laurelnetworks.com> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Mike Accetta Cc: linux-ide@vger.kernel.org Mike Accetta wrote: > Here's a bit more information on these timeouts. I noticed a mention > of changing the command queue depth in a recent lkml post and decided > to give that a whirl. > > This problem seems to be related to the depth of the queue. When I > set the value for /sys/block/sdb/device/queue_depth to 4 the raid1 > re-sync completes without incident. When set to 5 it eventually gives > the timeout error message (although at well past 50% of the re-sync). > The problem was originally observed with the default setting (31). Please post the result of 'hdparm -I /dev/sdb'. Thanks. -- tejun