From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751099AbdILBAp (ORCPT ); Mon, 11 Sep 2017 21:00:45 -0400 Received: from LGEAMRELO12.lge.com ([156.147.23.52]:47111 "EHLO lgeamrelo12.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750911AbdILBAo (ORCPT ); Mon, 11 Sep 2017 21:00:44 -0400 X-Original-SENDERIP: 156.147.1.121 X-Original-MAILFROM: byungchul.park@lge.com X-Original-SENDERIP: 10.177.222.33 X-Original-MAILFROM: byungchul.park@lge.com Date: Tue, 12 Sep 2017 10:00:29 +0900 From: Byungchul Park To: peterz@infradead.org, mingo@kernel.org, rostedt@goodmis.org Cc: joel.opensrc@gmail.com, linux-kernel@vger.kernel.org, juri.lelli@gmail.com, kernel-team@lge.com Subject: Re: [PATCH v11 2/2] sched/rt: Add support for SD_PREFER_SIBLING on find_lowest_rq() Message-ID: <20170912010029.GG3240@X58A-UD3R> References: <1503643251-797-1-git-send-email-byungchul.park@lge.com> <1503643251-797-3-git-send-email-byungchul.park@lge.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1503643251-797-3-git-send-email-byungchul.park@lge.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 Fri, Aug 25, 2017 at 03:40:51PM +0900, Byungchul Park wrote: > It would be better to try to check other siblings first if > SD_PREFER_SIBLING is flaged when pushing tasks - migration. Any opinions? > Suggested-by: Peter Zijlstra > Signed-off-by: Byungchul Park > Reviewed-by: Steven Rostedt (VMware) > --- > kernel/sched/rt.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++++--- > 1 file changed, 77 insertions(+), 3 deletions(-) > > diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c > index 979b734..a32e36d 100644 > --- a/kernel/sched/rt.c > +++ b/kernel/sched/rt.c > @@ -1618,12 +1618,35 @@ static struct task_struct *pick_highest_pushable_task(struct rq *rq, int cpu) > > static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); > > +/* > + * Find the first cpu in: mask & sd & ~prefer > + */ > +static int find_cpu(const struct cpumask *mask, > + const struct sched_domain *sd, > + const struct sched_domain *prefer) > +{ > + const struct cpumask *sds = sched_domain_span(sd); > + const struct cpumask *ps = prefer ? sched_domain_span(prefer) : NULL; > + int cpu; > + > + for_each_cpu(cpu, mask) { > + if (!cpumask_test_cpu(cpu, sds)) > + continue; > + if (ps && cpumask_test_cpu(cpu, ps)) > + continue; > + break; > + } > + > + return cpu; > +} > + > static int find_lowest_rq(struct task_struct *task) > { > - struct sched_domain *sd; > + struct sched_domain *sd, *prefer = NULL; > struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask); > int this_cpu = smp_processor_id(); > int cpu = task_cpu(task); > + int fallback_cpu = -1; > > /* Make sure the mask is initialized first */ > if (unlikely(!lowest_mask)) > @@ -1668,9 +1691,37 @@ static int find_lowest_rq(struct task_struct *task) > return this_cpu; > } > > - best_cpu = cpumask_first_and(lowest_mask, > - sched_domain_span(sd)); > + /* > + * If a cpu exists that is in the lowest_mask and > + * the current sd span, but not in the prefer sd > + * span, then that becomes our choice. > + * > + * Of course, the lowest possible cpu is already > + * under consideration through lowest_mask. > + */ > + best_cpu = find_cpu(lowest_mask, sd, prefer); > + > if (best_cpu < nr_cpu_ids) { > + /* > + * If current domain is SD_PREFER_SIBLING > + * flaged, we have to try to check other > + * siblings first. > + */ > + if (sd->flags & SD_PREFER_SIBLING) { > + prefer = sd; > + > + /* > + * fallback_cpu should be one > + * in the closest domain among > + * SD_PREFER_SIBLING domains, > + * in case that more than one > + * SD_PREFER_SIBLING domains > + * exist in the hierachy. > + */ > + if (fallback_cpu == -1) > + fallback_cpu = best_cpu; > + continue; > + } > rcu_read_unlock(); > return best_cpu; > } > @@ -1679,6 +1730,29 @@ static int find_lowest_rq(struct task_struct *task) > rcu_read_unlock(); > > /* > + * If fallback_cpu is valid, all our guesses failed *except* for > + * SD_PREFER_SIBLING domain. Now, we can return the fallback cpu. > + * > + * XXX: Consider the following example, 4 cores SMT2 system: > + * > + * LLC [0 - 7] > + * SMT [0 1][2 3][4 5][6 7] > + * o x o x x x x x > + * > + * where 'o': occupied and 'x': empty. > + * > + * A wakeup on cpu0 will exclude cpu1 and choose cpu3, since > + * cpu1 is in a SD_PREFER_SIBLING sd and cpu3 is not. However, > + * in this case, cpu4 would have been a better choice, since > + * cpu3 is a (SMT) thread of an already loaded core. > + * > + * Doing it 'right' is difficult and expensive. The current > + * solution is an acceptable approximation. > + */ > + if (fallback_cpu != -1) > + return fallback_cpu; > + > + /* > * And finally, if there were no matches within the domains > * just give the caller *something* to work with from the compatible > * locations. > -- > 1.9.1