From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935805AbYGCHN0 (ORCPT ); Thu, 3 Jul 2008 03:13:26 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1750899AbYGCG6f (ORCPT ); Thu, 3 Jul 2008 02:58:35 -0400 Received: from mga11.intel.com ([192.55.52.93]:48902 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755001AbYGCFyQ (ORCPT ); Thu, 3 Jul 2008 01:54:16 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.27,742,1204531200"; d="scan'208";a="348285187" Subject: Re: [problem] raid performance loss with 2.6.26-rc8 on 32-bit x86 (bisected) From: Dan Williams To: Mel Gorman Cc: Linus Torvalds , Andy Whitcroft , linux-mm@kvack.org, linux-kernel@vger.kernel.org, NeilBrown , babydr@baby-dragons.com, cl@linux-foundation.org, lee.schermerhorn@hp.com, a.beregalov@gmail.com, akpm@linux-foundation.org In-Reply-To: <20080703050036.GD14614@csn.ul.ie> References: <1214877439.7885.40.camel@dwillia2-linux.ch.intel.com> <20080701080910.GA10865@csn.ul.ie> <20080701175855.GI32727@shadowen.org> <20080701190741.GB16501@csn.ul.ie> <1214944175.26855.18.camel@dwillia2-linux.ch.intel.com> <20080702051759.GA26338@csn.ul.ie> <1215049766.2840.43.camel@dwillia2-linux.ch.intel.com> <20080703042750.GB14614@csn.ul.ie> <20080703050036.GD14614@csn.ul.ie> Content-Type: text/plain Date: Wed, 02 Jul 2008 22:54:15 -0700 Message-Id: <1215064455.15797.4.camel@dwillia2-linux.ch.intel.com> Mime-Version: 1.0 X-Mailer: Evolution 2.12.3 (2.12.3-5.fc8) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 2008-07-02 at 22:00 -0700, Mel Gorman wrote: > Subject: [PATCH] Do not overwrite nr_zones on !NUMA when initialising zlcache_ptr > > With the two-zonelist patches on !NUMA machines, there really is only one > zonelist as __GFP_THISNODE is meaningless. However, during initialisation, the > assumption is made that two zonelists exist when initialising zlcache_ptr. The > result is that pgdat->nr_zones is always 0. As kswapd uses this value to > determine what reclaim work is necessary, the result is that kswapd never > reclaims. This causes processes to stall frequently in low-memory situations > as they always direct reclaim. This patch initialises zlcache_ptr correctly. > > Signed-off-by: Mel Gorman > --- > page_alloc.c | 1 - > 1 file changed, 1 deletion(-) > > diff -rup -X /usr/src/patchset-0.6/bin//dontdiff linux-2.6.26-rc8-clean/mm/page_alloc.c linux-2.6.26-rc8-fix-kswapd-on-numa/mm/page_alloc.c > --- linux-2.6.26-rc8-clean/mm/page_alloc.c 2008-06-24 18:58:20.000000000 -0700 > +++ linux-2.6.26-rc8-fix-kswapd-on-numa/mm/page_alloc.c 2008-07-02 21:49:09.000000000 -0700 > @@ -2328,7 +2328,6 @@ static void build_zonelists(pg_data_t *p > static void build_zonelist_cache(pg_data_t *pgdat) > { > pgdat->node_zonelists[0].zlcache_ptr = NULL; > - pgdat->node_zonelists[1].zlcache_ptr = NULL; > } > > #endif /* CONFIG_NUMA */ > Bug squished. # for i in `seq 1 5`; do dd if=/dev/zero of=/dev/md0 bs=1024k count=2048; done 2048+0 records in 2048+0 records out 2147483648 bytes (2.1 GB) copied, 7.73352 s, 278 MB/s 2048+0 records in 2048+0 records out 2147483648 bytes (2.1 GB) copied, 7.6845 s, 279 MB/s 2048+0 records in 2048+0 records out 2147483648 bytes (2.1 GB) copied, 7.74428 s, 277 MB/s 2048+0 records in 2048+0 records out 2147483648 bytes (2.1 GB) copied, 7.65959 s, 280 MB/s 2048+0 records in 2048+0 records out 2147483648 bytes (2.1 GB) copied, 7.73107 s, 278 MB/s Tested-by: Dan Williams