From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752943Ab1LTUgR (ORCPT ); Tue, 20 Dec 2011 15:36:17 -0500 Received: from forward15.mail.yandex.net ([95.108.130.119]:35097 "EHLO forward15.mail.yandex.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751067Ab1LTUgL (ORCPT ); Tue, 20 Dec 2011 15:36:11 -0500 X-Greylist: delayed 451 seconds by postgrey-1.27 at vger.kernel.org; Tue, 20 Dec 2011 15:36:11 EST X-Yandex-Spam: 1 From: Tkhai Kirill To: Oleg Nesterov Cc: linux-kernel@vger.kernel.org, Ingo Molnar , Peter Zijlstra , Gregory Haskins In-Reply-To: <20111220174433.GA2018@redhat.com> References: <1322774765.8386.2.camel@hp> <20111220174433.GA2018@redhat.com> Subject: Re: [PATCH]sched_rt.c: Avoid unnecessary dequeue and enqueue of pushable tasks in set_cpus_allowed_rt() MIME-Version: 1.0 Message-Id: <203221324412916@web157.yandex.ru> Date: Wed, 21 Dec 2011 00:28:36 +0400 X-Mailer: Yamail [ http://yandex.ru ] 5.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=koi8-r Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 20.12.2011, 21:44, "Oleg Nesterov" : > On 12/02, Kirill Tkhai wrote: > >> šMigration status depends on a difference of weight from 0 and 1. If >> šweight > 1 (<= 1) and old weight <= 1 (> 1) then task becomes pushable >> š(not pushable). We are not insterested in exact values of it, is it 3 or >> š4, for example. >> >> šNow if we are changing affinity from a set of 3 cpus to a set of 4, the >> štask will be dequeued and enqueued sequentially without important >> šdifference in comparison with initial state. The only difference is in >> šinternal representation of plist queue of pushable tasks and the fact >> šthat the task may won't be the first in a sequence of the same priority >> štasks. But it seems to me it gives nothing. > > Looks reasonable, although I can't say I really understand this code. > Add Gregory. > >> šSigned-off-by: Tkhai Kirill >> >> š--- kernel/sched_rt.c.orig 2011-12-02 00:29:11.970243145 +0400 >> š+++ kernel/sched_rt.c 2011-12-02 00:37:43.622846606 +0400 > > please use -p1 > Sorry, this time I'm sending "git diffed" output. >> š@@ -1572,43 +1572,37 @@ static void set_cpus_allowed_rt(struct t >> ššššššššššššššššššššššššššššššššššconst struct cpumask *new_mask) >> šš{ >> ššššššššššint weight = cpumask_weight(new_mask); >> š+ struct rq *rq; >> >> ššššššššššBUG_ON(!rt_task(p)); >> >> šššššššššš/* >> š- * Update the migration status of the RQ if we have an RT task >> š- * which is running AND changing its weight value. >> š+ * Just exit if it's not necessary to change migration status >> ššššššššššš*/ >> š- if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) { >> š- struct rq *rq = task_rq(p); >> š+ if ((p->rt.nr_cpus_allowed <= 1 && weight <= 1) >> š+ || (p->rt.nr_cpus_allowed > 1 && weight > 1)) >> š+ return; > > Subjective, but may be > > ššššššššif ((p->rt.nr_cpus_allowed > 1) != (weight > 1)) > ššššššššššššššššreturn; > > looks more understandable? Yes, thanks. --- diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 3640ebb..4467f4d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1774,43 +1774,36 @@ static void set_cpus_allowed_rt(struct task_struct *p, const struct cpumask *new_mask) { int weight = cpumask_weight(new_mask); + struct rq *rq; BUG_ON(!rt_task(p)); /* - * Update the migration status of the RQ if we have an RT task - * which is running AND changing its weight value. + * Just exit if it's not necessary to change migration status */ - if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) { - struct rq *rq = task_rq(p); - - if (!task_current(rq, p)) { - /* - * Make sure we dequeue this task from the pushable list - * before going further. It will either remain off of - * the list because we are no longer pushable, or it - * will be requeued. - */ - if (p->rt.nr_cpus_allowed > 1) - dequeue_pushable_task(rq, p); - - /* - * Requeue if our weight is changing and still > 1 - */ - if (weight > 1) - enqueue_pushable_task(rq, p); + if ((p->rt.nr_cpus_allowed > 1) != (weight > 1)) + return; - } + if (!p->on_rq) + return; - if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) { - rq->rt.rt_nr_migratory++; - } else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) { - BUG_ON(!rq->rt.rt_nr_migratory); - rq->rt.rt_nr_migratory--; - } + rq = task_rq(p); - update_rt_migration(&rq->rt); + /* + * Several cpus were allowed but now it's not so OR vice versa + */ + if (weight <= 1) { + if (!task_current(rq, p)) + dequeue_pushable_task(rq, p); + BUG_ON(!rq->rt.rt_nr_migratory); + rq->rt.rt_nr_migratory--; + } else { + if (!task_current(rq, p)) + enqueue_pushable_task(rq, p); + rq->rt.rt_nr_migratory++; } + + update_rt_migration(&rq->rt); } /* Assumes rq->lock is held */