Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760694AbXKME1r (ORCPT ); Mon, 12 Nov 2007 23:27:47 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1760475AbXKME1h (ORCPT ); Mon, 12 Nov 2007 23:27:37 -0500 Received: from nf-out-0910.google.com ([64.233.182.187]:57918 "EHLO nf-out-0910.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752258AbXKME1g (ORCPT ); Mon, 12 Nov 2007 23:27:36 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; b=UU7/qCVlptPB2j7lF475BYwTYOCaX8/WPVavKMM09YP064HPECpdCf/8bh7tds/aRPv1aRHjndsWhXW4eRthK8Ik5S3Jbb0W7WiE2RBIjlPeMbvUz4jq1sDPUg8VmCbT756vyDzcVGTZ4QfZPd3DJhnVJGU8SaQmrtVqMwao1Ms= Message-ID: <2c0942db0711122027m5b11502cveded5705c0bc4f64@mail.gmail.com> Date: Mon, 12 Nov 2007 20:27:34 -0800 From: "Ray Lee" To: "Christoph Lameter" Subject: Re: x86_64: Make sparsemem/vmemmap the default memory model Cc: akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, "Mel Gorman" , "Andi Kleen" , "Andy Whitcroft" In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <200711130059.34346.ak@suse.de> <200711130149.54852.ak@suse.de> X-Google-Sender-Auth: a263406121f143e7 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1767 Lines: 50 On Nov 12, 2007 7:42 PM, Christoph Lameter wrote: > Ok here is the patch to remove DISCONTIG and FLATMEM > > x86_64: Make sparsemem/vmemmap the default memory model > > Use sparsemem as the only memory model for UP, SMP and NUMA. > Measurements indicate that DISCONTIGMEM has a higher overhead > than sparsemem. And FLATMEMs benefits are minimal. So I think its > best to simply standardize on sparsemem. > > Results of page allocator tests (test can be had via git from slab git > tree branch tests) > > Measurements in cycle counts. 1000 allocations were performed and then the > average cycle count was calculated. > > Order FlatMem Discontig SparseMem > 0 639 665 641 > 1 567 647 593 > 2 679 774 692 > 3 763 967 781 > 4 961 1501 962 > 5 1356 2344 1392 > 6 2224 3982 2336 > 7 4869 7225 5074 > 8 12500 14048 12732 > 9 27926 28223 28165 > 10 58578 58714 58682 Discontig obviously needs to die. However, FlatMem is consistently faster, averaging about 2.1% better overall for your numbers above. Is the page allocator not, erm, a fast path, where that matters? Order Flat Sparse % diff 0 639 641 0.3 1 567 593 4.4 2 679 692 1.9 3 763 781 2.3 4 961 962 0.1 5 1356 1392 2.6 6 2224 2336 4.8 7 4869 5074 4.0 8 12500 12732 1.8 9 27926 28165 0.8 10 58578 58682 0.2 - 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/