From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751267AbXC0Jzq (ORCPT ); Tue, 27 Mar 2007 05:55:46 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753528AbXC0Jzq (ORCPT ); Tue, 27 Mar 2007 05:55:46 -0400 Received: from lucidpixels.com ([75.144.35.66]:52122 "EHLO lucidpixels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751267AbXC0Jzp (ORCPT ); Tue, 27 Mar 2007 05:55:45 -0400 Date: Tue, 27 Mar 2007 05:55:44 -0400 (EDT) From: Justin Piszcz X-X-Sender: jpiszcz@p34.internal.lan To: Alan Cox cc: linux-kernel@vger.kernel.org Subject: Re: Why is NCQ enabled by default by libata? (2.6.20) In-Reply-To: <20070324184300.3250fab0@the-village.bc.nu> Message-ID: References: <20070324184300.3250fab0@the-village.bc.nu> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 24 Mar 2007, Alan Cox wrote: > On Sat, 24 Mar 2007 12:38:02 -0400 (EDT) > Justin Piszcz wrote: > >> Without NCQ, performance is MUCH better on almost every operation, with >> the exception of 2-3 items. > > It depends on the drive. Generally NCQ is better but some drive firmware > isn't too bright and there are probably still cases where we get bad > interactions in the kernel code that want tuning too > Checking the benchmarks on various hardware websites, anandtech, hothardware and others, they generally all come to the same conclusion if there is only 1 thread using I/O (single user system) then NCQ off is the best. I see 30-50MB/s faster speeds with NCQ turned off on two different SW RAID5s. Justin.