Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S261855AbVAYHji (ORCPT ); Tue, 25 Jan 2005 02:39:38 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S261856AbVAYHji (ORCPT ); Tue, 25 Jan 2005 02:39:38 -0500 Received: from one.firstfloor.org ([213.235.205.2]:51676 "EHLO one.firstfloor.org") by vger.kernel.org with ESMTP id S261855AbVAYHjd (ORCPT ); Tue, 25 Jan 2005 02:39:33 -0500 To: Steve Lord Cc: Marcelo Tosatti , Mel Gorman , William Lee Irwin III , Linux Memory Management List , Linux Kernel , Grant Grundler Subject: Re: [PATCH] Avoiding fragmentation through different allocator References: <20050120101300.26FA5E598@skynet.csn.ul.ie> <20050121142854.GH19973@logos.cnet> <20050122215949.GD26391@logos.cnet> <20050124122952.GA5739@logos.cnet> <1106585052.5513.26.camel@mulgrave> <41F55EE1.5090702@xfs.org> From: Andi Kleen Date: Tue, 25 Jan 2005 08:39:31 +0100 In-Reply-To: <41F55EE1.5090702@xfs.org> (Steve Lord's message of "Mon, 24 Jan 2005 14:47:29 -0600") Message-ID: User-Agent: Gnus/5.110002 (No Gnus v0.2) Emacs/21.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1454 Lines: 35 Steve Lord writes: > > I realize this is one data point on one end of the scale, but I > just wanted to make the point that there are cases where it > does matter. Hopefully William's little change from last > year has helped out a lot. There are more datapoints: e.g. performance on megaraid controllers (very popular because a big PC vendor ships them) was always quite bad on Linux. Up to the point that specific IO workloads run half as fast on a megaraid compared to other controllers. I heard they do work better on Windows. Also I did some experiments with coalescing SG lists in the Opteron IOMMU some time ago. With a MPT fusion controller and forcing all SG lists through the IOMMU so that the SCSI controller always only contiguous mappings I saw ~5% improvement on some IO tests. Unfortunately there are some problems that doesn't allow to enable this unconditionally. But it gives strong evidence that MPT Fusion prefers shorter SG lists too. So it seems to be worthwhile to optimize for shorter SG lists. Ideally the Linux IO patterns would look similar to the Windows IO patterns, then we could reuse all the optimizations the controller vendors did for Windows :) -Andi - 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/