From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755720AbXGGVks (ORCPT ); Sat, 7 Jul 2007 17:40:48 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753102AbXGGVkl (ORCPT ); Sat, 7 Jul 2007 17:40:41 -0400 Received: from smtpq1.tilbu1.nb.home.nl ([213.51.146.200]:54682 "EHLO smtpq1.tilbu1.nb.home.nl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752140AbXGGVkk (ORCPT ); Sat, 7 Jul 2007 17:40:40 -0400 Message-ID: <46900851.4060403@gmail.com> Date: Sat, 07 Jul 2007 23:40:33 +0200 From: Rene Herman User-Agent: Thunderbird 1.5.0.12 (X11/20070509) MIME-Version: 1.0 To: Christoph Pleger CC: linux-kernel@vger.kernel.org Subject: Re: PATA-disk named sda References: <20070706102132.14fbc600.Christoph.Pleger@cs.uni-dortmund.de> <20070706111848.43551f33@the-village.bc.nu> <20070706143055.01aa9ef6.Christoph.Pleger@cs.uni-dortmund.de> In-Reply-To: <20070706143055.01aa9ef6.Christoph.Pleger@cs.uni-dortmund.de> Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit X-AtHome-MailScanner-Information: Please contact support@home.nl for more information X-AtHome-MailScanner: Found to be clean Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On 07/06/2007 02:30 PM, Christoph Pleger wrote: > And what about hdparm (setting 32bit I/O and multi-sector mode)? Suren > wrote that 32bit I/O makes no sense when using DMA. Maybe that's right, > but it does not correspond with my experiences. At least, I have the > "feeling" that my IDE disks work much faster since I enabled 32bit > support (DMA already was on before). hdparm -t /dev/hda (or /dev/sda -- it works for the SD interface as well) is a quick test of a drive's sequential read speed. I have, at the time, noticed at least on older controllers/drives (Intel 430 generation chipsets with things like 8G UDMA33 disks) that I could reliably increase the result with something like 1MB/s (to a total of 6 to 8, so it wasn't insignificant) by enabling 32-bit I/O. Had also understood that it shouldn't make a difference with DMA, but just went "oh well" and stuck a "hdparm -c1" in my bootup scripts. (if anyone tries; note that hdparm -a can have a large effect on that result as well on some setups -- on machines where it does, -a 1024 usually gives me best results) Rene.