Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S266316AbUIIQsm (ORCPT ); Thu, 9 Sep 2004 12:48:42 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S266391AbUIIQqf (ORCPT ); Thu, 9 Sep 2004 12:46:35 -0400 Received: from pD9517510.dip.t-dialin.net ([217.81.117.16]:59525 "EHLO undata.org") by vger.kernel.org with ESMTP id S266349AbUIIQpF (ORCPT ); Thu, 9 Sep 2004 12:45:05 -0400 Subject: Re: [patch] voluntary-preempt-2.6.9-rc1-bk4-R1 From: Thomas Charbonnel To: Alan Cox Cc: Mark_H_Johnson@raytheon.com, Ingo Molnar , Lee Revell , Free Ekanayaka , Eric St-Laurent , Linux Kernel Mailing List , "K.R. Foley" , Felipe Alfaro Solana , Daniel Schmitt , "P.O. Gaillard" , nando@ccrma.stanford.edu, luke@audioslack.com, free78@tin.it In-Reply-To: <1094682656.12371.28.camel@localhost.localdomain> References: <1094682656.12371.28.camel@localhost.localdomain> Content-Type: text/plain Message-Id: <1094748286.18782.3.camel@localhost> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.6 Date: Thu, 09 Sep 2004 18:44:46 +0200 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1202 Lines: 32 Alan Cox wrote : > On Mer, 2004-09-08 at 21:33, Mark_H_Johnson@raytheon.com wrote: > > >.... Please disable IDE DMA and see > > >what happens (after hiding the PIO IDE codepath via > > >touch_preempt_timing()). > > > > Not quite sure where to add touch_preempt_timing() calls - somewhere in the > > loop in ide_outsl and ide_insl? [so we keep resetting the start /end > > times?] > > If you haven't done hdparm -u1 that may be a reason you want to touch > these. To defend against some very bad old h/w where a stall in the I/O > stream to the disk causes corruption we disable IRQ's across the > transfer in PIO mode by default. > I had the exact same problem showing in the output of latencytest, and enabling unmaskirq on the drive being stressed solved it, thanks ! See this for the problem : http://www.undata.org/~thomas/unmaskirq_0/index.html and this for the (impressive) results : http://www.undata.org/~thomas/unmaskirq_1/index.html Thomas - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/