From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: Re: [git patches] IDE update Date: Fri, 8 Jul 2005 13:45:07 +0200 Message-ID: <20050708114503.GG7050@suse.de> References: <42CA84DB.2050506@rainbow-software.org> <1120569095.12942.11.camel@linux> <42CAAC7D.2050604@rainbow-software.org> <20050705142122.GY1444@suse.de> <6m8mc1lhug5d345uqikru1vpsqi6hciv41@4ax.com> <20050708084817.GB7050@suse.de> <20050708102056.GA7172@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from ns.virtualhost.dk ([195.184.98.160]:31206 "EHLO virtualhost.dk") by vger.kernel.org with ESMTP id S262578AbVGHLnk (ORCPT ); Fri, 8 Jul 2005 07:43:40 -0400 Content-Disposition: inline In-Reply-To: <20050708102056.GA7172@elte.hu> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Ingo Molnar Cc: Linus Torvalds , Grant Coady , Ondrej Zary , =?iso-8859-1?Q?Andr=E9?= Tomt , Al Boldi , 'Bartlomiej Zolnierkiewicz' , linux-ide@vger.kernel.org, linux-kernel@vger.kernel.org On Fri, Jul 08 2005, Ingo Molnar wrote: > > * Jens Axboe wrote: > > > But! I used hdparm -t solely, 2.6 was always ~5% faster than 2.4. But > > using -Tt slowed down the hd speed by about 30%. So it looks like some > > scheduler interaction, perhaps the memory timing loops gets it marked > > as batch or something? > > to check whether that could be the case, could you try: > > nice -n -20 hdparm -t /dev/hdc > > does that produce different results? Same result, see my next mail, it turned out to be a read-ahead bug. -- Jens Axboe