From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753821AbbCEFfY (ORCPT ); Thu, 5 Mar 2015 00:35:24 -0500 Received: from mga01.intel.com ([192.55.52.88]:50212 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752067AbbCEFfX (ORCPT ); Thu, 5 Mar 2015 00:35:23 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,345,1422950400"; d="scan'208";a="687163867" Message-ID: <1425533699.6711.48.camel@intel.com> Subject: Re: [LKP] [mm] 3484b2de949: -46.2% aim7.jobs-per-min From: Huang Ying To: Mel Gorman Cc: LKML , LKP ML Date: Thu, 05 Mar 2015 13:34:59 +0800 In-Reply-To: <1425108604.10337.84.camel@linux.intel.com> References: <1425021696.10337.55.camel@linux.intel.com> <20150228014642.GG3087@suse.de> <1425108604.10337.84.camel@linux.intel.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.12.9-1+b1 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, Mel, On Sat, 2015-02-28 at 15:30 +0800, Huang Ying wrote: > On Sat, 2015-02-28 at 01:46 +0000, Mel Gorman wrote: > > On Fri, Feb 27, 2015 at 03:21:36PM +0800, Huang Ying wrote: > > > FYI, we noticed the below changes on > > > > > > git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master > > > commit 3484b2de9499df23c4604a513b36f96326ae81ad ("mm: rearrange zone fields into read-only, page alloc, statistics and page reclaim lines") > > > > > > The perf cpu-cycles for spinlock (zone->lock) increased a lot. I suspect there are some cache ping-pong or false sharing. > > > > > > > Are you sure about this result? I ran similar tests here and found that > > there was a major regression introduced near there but it was commit > > 05b843012335 ("mm: memcontrol: use root_mem_cgroup res_counter") that > > cause the problem and it was later reverted. On local tests on a 4-node > > machine, commit 3484b2de9499df23c4604a513b36f96326ae81ad was within 1% > > of the previous commit and well within the noise. > > After applying the below debug patch, the performance regression > restored. So I think we can root cause this regression to be cache line > alignment related issue? > > If my understanding were correct, after the 3484b2de94, lock and low > address area free_area are in the same cache line, so that the cache > line of the lock and the low address area of free_area will be switched > between MESI "E" and "S" state because it is written in one CPU (page > allocating with free_area) and frequently read (spinning on lock) in > another CPU. What do you think about this? Best Regards, Huang, Ying > Best Regards, > Huang, Ying > > --- > include/linux/mmzone.h | 2 ++ > 1 file changed, 2 insertions(+) > > --- a/include/linux/mmzone.h > +++ b/include/linux/mmzone.h > @@ -468,6 +468,8 @@ struct zone { > /* Write-intensive fields used from the page allocator */ > spinlock_t lock; > > + ZONE_PADDING(_pad_xx_) > + > /* free areas of different sizes */ > struct free_area free_area[MAX_ORDER]; > >