Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761580AbXKMUq3 (ORCPT ); Tue, 13 Nov 2007 15:46:29 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1761144AbXKMUqL (ORCPT ); Tue, 13 Nov 2007 15:46:11 -0500 Received: from lazybastard.de ([212.112.238.170]:35005 "EHLO longford.lazybastard.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1763098AbXKMUqJ (ORCPT ); Tue, 13 Nov 2007 15:46:09 -0500 Date: Tue, 13 Nov 2007 21:41:00 +0100 From: =?utf-8?B?SsO2cm4=?= Engel To: Christoph Lameter Cc: Ray Lee , akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, Mel Gorman , Andi Kleen , Andy Whitcroft Subject: Re: x86_64: Make sparsemem/vmemmap the default memory model Message-ID: <20071113204100.GB20167@lazybastard.org> References: <200711130059.34346.ak@suse.de> <200711130149.54852.ak@suse.de> <2c0942db0711122027m5b11502cveded5705c0bc4f64@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: User-Agent: Mutt/1.5.9i Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1474 Lines: 44 On Mon, 12 November 2007 20:41:10 -0800, Christoph Lameter wrote: > On Mon, 12 Nov 2007, Ray Lee wrote: > > > 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 > > IMHO Order 0 currently matters most and the difference is negligible > there. Is it? I am a bit concerned about the non-monotonic distribution. Difference starts a near-0, grows to 4.4, drops to near-0, grows to 4.9, drops to near-0. 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 Is there an explanation for this behaviour? More to the point, could repeated runs also return 4% difference for order-0? Jörn -- It does not require a majority to prevail, but rather an irate, tireless minority keen to set brush fires in people's minds. -- Samuel Adams - 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/