From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751723Ab3HUOFF (ORCPT ); Wed, 21 Aug 2013 10:05:05 -0400 Received: from mail-qa0-f54.google.com ([209.85.216.54]:46338 "EHLO mail-qa0-f54.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751410Ab3HUOFB (ORCPT ); Wed, 21 Aug 2013 10:05:01 -0400 Date: Wed, 21 Aug 2013 10:04:57 -0400 From: Tejun Heo To: Li Zefan Cc: LKML , Cgroups , Containers Subject: Re: [PATCH 07/11] cpuset: use effective cpumask to build sched domains Message-ID: <20130821140457.GG19286@mtj.dyndns.org> References: <52148F52.0@huawei.com> <52148FA9.806@huawei.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <52148FA9.806@huawei.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Aug 21, 2013 at 06:00:09PM +0800, Li Zefan wrote: > @@ -887,10 +888,17 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpuset *trialcs, > > update_tasks_cpumask(cp, heap); > > + if (!cpumask_empty(cp->cpus_allowed) && > + is_sched_load_balance(cp)) > + need_rebuild_sched_domains = true; > + > rcu_read_lock(); > css_put(&cp->css); > } > rcu_read_unlock(); > + > + if (need_rebuild_sched_domains) > + rebuild_sched_domains_locked(); > } > > /** > @@ -944,9 +952,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, > update_cpumasks_hier(cs, trialcs, &heap); > > heap_free(&heap); > - > - if (is_sched_load_balance(cs)) > - rebuild_sched_domains_locked(); Hmmm... can we please document what's going on with the above call and add some comment explaining what it's doing and why it's where it's at? Thanks. -- tejun