From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2992962AbXDDPgy (ORCPT ); Wed, 4 Apr 2007 11:36:54 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S2992963AbXDDPgy (ORCPT ); Wed, 4 Apr 2007 11:36:54 -0400 Received: from ottawa-hs-64-26-128-89.s-ip.magma.ca ([64.26.128.89]:3894 "EHLO mail.rtr.ca" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2992962AbXDDPgx (ORCPT ); Wed, 4 Apr 2007 11:36:53 -0400 Message-ID: <4613C612.5040600@rtr.ca> Date: Wed, 04 Apr 2007 11:36:50 -0400 From: Mark Lord User-Agent: Thunderbird 1.5.0.10 (X11/20070221) MIME-Version: 1.0 To: Phillip Susi Cc: Chris Snook , Paa Paa , linux-kernel@vger.kernel.org Subject: Re: Lower HD transfer rate with NCQ enabled? References: <46128175.2090506@redhat.com> <4612852C.2030801@rtr.ca> <4612A854.1070702@cfl.rr.com> In-Reply-To: <4612A854.1070702@cfl.rr.com> 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 Phillip Susi wrote: > Mark Lord wrote: >> But WD drives, in particular the Raptor series, have a firmware "feature" >> that disables "drive readahead" whenever NCQ is in use. > > Why is this an issue? Shouldn't the kernel be sending down its own > readahead requests to keep the disk busy? The drive firmware readahead is inherently *way* more effective than other forms, and without it, sequential read performance really suffers. Regardless of how software tries to compensate. This is mostly a problem with the WD Raptor drive, and some other WD drives. I have not yet encountered/noticed the problem with other brands. -ml