From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755692AbZHKXdB (ORCPT ); Tue, 11 Aug 2009 19:33:01 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755678AbZHKXdA (ORCPT ); Tue, 11 Aug 2009 19:33:00 -0400 Received: from smtp1.linux-foundation.org ([140.211.169.13]:33214 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755666AbZHKXc7 (ORCPT ); Tue, 11 Aug 2009 19:32:59 -0400 Date: Tue, 11 Aug 2009 16:31:59 -0700 From: Andrew Morton To: balbir@linux.vnet.ibm.com Cc: kamezawa.hiroyu@jp.fujitsu.com, nishimura@mxp.nes.nec.co.jp, kosaki.motohiro@jp.fujitsu.com, menage@google.com, prarit@redhat.com, andi.kleen@intel.com, xemul@openvz.org, lizf@cn.fujitsu.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: Help Resource Counters Scale better (v4) Message-Id: <20090811163159.ddc5f5fd.akpm@linux-foundation.org> In-Reply-To: <20090811144405.GW7176@balbir.in.ibm.com> References: <20090811144405.GW7176@balbir.in.ibm.com> X-Mailer: Sylpheed version 2.2.4 (GTK+ 2.8.20; i486-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 11 Aug 2009 20:14:05 +0530 Balbir Singh wrote: > Enhancement: Remove the overhead of root based resource counter accounting > > From: Balbir Singh > > This patch reduces the resource counter overhead (mostly spinlock) > associated with the root cgroup. This is a part of the several > patches to reduce mem cgroup overhead. I had posted other > approaches earlier (including using percpu counters). Those > patches will be a natural addition and will be added iteratively > on top of these. > > The patch stops resource counter accounting for the root cgroup. > The data for display is derived from the statisitcs we maintain > via mem_cgroup_charge_statistics (which is more scalable). > > The tests results I see on a 24 way show that > > 1. The lock contention disappears from /proc/lock_stats > 2. The results of the test are comparable to running with > cgroup_disable=memory. > > Please test/review. I don't get it. The patch apepars to skip accounting altogether for the root memcgroup and then adds some accounting back in for swap. Or something like that. How come? Do we actually not need the root memcgroup accounting? IOW, the changelog sucks ;) Is this an alternative approach to using percpu_counters, or do we do both or do we choose one or the other? res_counter_charge() really is quite sucky. The patch didn't have a signoff. It would be nice to finalise those performance testing results and include them in the new, improved patch description.