From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758103AbZGIEyg (ORCPT ); Thu, 9 Jul 2009 00:54:36 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1757296AbZGIEyT (ORCPT ); Thu, 9 Jul 2009 00:54:19 -0400 Received: from mailout3.samsung.com ([203.254.224.33]:64407 "EHLO mailout3.samsung.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752597AbZGIEyR (ORCPT ); Thu, 9 Jul 2009 00:54:17 -0400 Content-return: prohibited Date: Thu, 09 Jul 2009 04:54:10 +0000 (GMT) From: NARAYANAN GOPALAKRISHNAN Subject: Re: Re: Performance degradation seen after using one list for hot/cold pages. To: Andrew Morton , Mel Gorman Cc: "kamezawa.hiroyu@jp.fujitsu.com" , "linux-mm@kvack.org" , "cl@linux-foundation.org" , "kosaki.motohiro@jp.fujitsu.com" , "stable@kernel.org" , "linux-kernel@vger.kernel.org" , "linux-scsi@vger.kernel.org" Reply-to: narayanan.g@samsung.com Message-id: <23853191.513591247115250186.JavaMail.weblogic@epml10> MIME-version: 1.0 MIME-version: 1.0 Content-type: text/plain; charset=windows-1252 X-Priority: 3 Msgkey: 20090709044753090@narayanan.g X-MTR: 20090709044753090@narayanan.g X-EPLocale: en_US.windows-1252 X-EPWebmail-Msg-Type: personal X-EPWebmail-Reply-Demand: 0 X-EPApproval-Locale: X-EPHeader: ML X-EPTrCode: X-EPTrName: X-MLAttribute: X-RootMTR: X-ParentMTR: Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from base64 to 8bit by alpha.home.local id n694t1Xx000977 > I'll add the rather important text: > > Fix a post-2.6.24 performance regression caused by > 3dfa5721f12c3d5a441448086bee156887daa961 ("page-allocator: preserve PFN > ordering when __GFP_COLD is set"). > > This was a pretty major screwup. > > This is why changing core MM is so worrisome - there's so much secret and > subtle history to it, and performance dependencies are unobvious and quite > indirect and the lag time to discover regressions is long. > > Narayanan, are you able to quantify the regression more clearly? All I > have is "2 MBps lower" which isn't very useful. What is this as a > percentage, and with what sort of disk controller? Thanks. It is around 15%. There is no disk controller as our setup is based on Samsung OneNAND used as a memory mapped device on a OMAP2430 based board. Narayanan {.n++%ݶw{.n+{G{ayʇڙ,jfhz_(階ݢj"mG?&~iOzv^m ?I