From patchwork Wed Aug 31 10:52:16 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Morten Rasmussen X-Patchwork-Id: 75070 Delivered-To: patch@linaro.org Received: by 10.140.29.52 with SMTP id a49csp264984qga; Wed, 31 Aug 2016 03:52:36 -0700 (PDT) X-Received: by 10.98.34.151 with SMTP id p23mr15680281pfj.102.1472640755871; Wed, 31 Aug 2016 03:52:35 -0700 (PDT) Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id cq3si50316738pad.61.2016.08.31.03.52.35; Wed, 31 Aug 2016 03:52:35 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760122AbcHaKwO (ORCPT + 27 others); Wed, 31 Aug 2016 06:52:14 -0400 Received: from foss.arm.com ([217.140.101.70]:57610 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759934AbcHaKwK (ORCPT ); Wed, 31 Aug 2016 06:52:10 -0400 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id C0752C87; Wed, 31 Aug 2016 03:52:09 -0700 (PDT) Received: from e105550-lin.cambridge.arm.com (e105550-lin.cambridge.arm.com [10.1.211.30]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 183F33F220; Wed, 31 Aug 2016 03:52:07 -0700 (PDT) From: Morten Rasmussen To: peterz@infradead.org, mingo@redhat.com Cc: dietmar.eggemann@arm.com, yuyang.du@intel.com, vincent.guittot@linaro.org, mgalbraith@suse.de, sgurrappadi@nvidia.com, freedom.tan@mediatek.com, keita.kobayashi.ym@renesas.com, linux-kernel@vger.kernel.org, Morten Rasmussen Subject: [PATCH v4 2/5] sched/fair: Consider spare capacity in find_idlest_group() Date: Wed, 31 Aug 2016 11:52:16 +0100 Message-Id: <1472640739-8778-3-git-send-email-morten.rasmussen@arm.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1472640739-8778-1-git-send-email-morten.rasmussen@arm.com> References: <1472640739-8778-1-git-send-email-morten.rasmussen@arm.com> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org In low-utilization scenarios comparing relative loads in find_idlest_group() doesn't always lead to the most optimum choice. Systems with groups containing different numbers of cpus and/or cpus of different compute capacity are significantly better off when considering spare capacity rather than relative load in those scenarios. In addition to existing load based search an alternative spare capacity based candidate sched_group is found and selected instead if sufficient spare capacity exists. If not, existing behaviour is preserved. cc: Ingo Molnar cc: Peter Zijlstra Signed-off-by: Morten Rasmussen --- kernel/sched/fair.c | 50 +++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 45 insertions(+), 5 deletions(-) -- 1.9.1 diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index adff97d6c834..ebe8907119b5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5184,6 +5184,14 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, return 1; } +static inline int task_util(struct task_struct *p); +static int cpu_util_wake(int cpu, struct task_struct *p); + +static unsigned long capacity_spare_wake(int cpu, struct task_struct *p) +{ + return capacity_orig_of(cpu) - cpu_util_wake(cpu, p); +} + /* * find_idlest_group finds and returns the least busy CPU group within the * domain. @@ -5193,7 +5201,9 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu, int sd_flag) { struct sched_group *idlest = NULL, *group = sd->groups; + struct sched_group *most_spare_sg = NULL; unsigned long min_load = ULONG_MAX, this_load = 0; + unsigned long most_spare = 0, this_spare = 0; int load_idx = sd->forkexec_idx; int imbalance = 100 + (sd->imbalance_pct-100)/2; @@ -5201,7 +5211,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, load_idx = sd->wake_idx; do { - unsigned long load, avg_load; + unsigned long load, avg_load, spare_cap, max_spare_cap; int local_group; int i; @@ -5213,8 +5223,12 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(group)); - /* Tally up the load of all CPUs in the group */ + /* + * Tally up the load of all CPUs in the group and find + * the group containing the cpu with most spare capacity. + */ avg_load = 0; + max_spare_cap = 0; for_each_cpu(i, sched_group_cpus(group)) { /* Bias balancing toward cpus of our domain */ @@ -5224,6 +5238,11 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, load = target_load(i, load_idx); avg_load += load; + + spare_cap = capacity_spare_wake(i, p); + + if (spare_cap > max_spare_cap) + max_spare_cap = spare_cap; } /* Adjust by relative CPU capacity of the group */ @@ -5231,12 +5250,33 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, if (local_group) { this_load = avg_load; - } else if (avg_load < min_load) { - min_load = avg_load; - idlest = group; + this_spare = max_spare_cap; + } else { + if (avg_load < min_load) { + min_load = avg_load; + idlest = group; + } + + if (most_spare < max_spare_cap) { + most_spare = max_spare_cap; + most_spare_sg = group; + } } } while (group = group->next, group != sd->groups); + /* + * The cross-over point between using spare capacity or least load + * is too conservative for high utilization tasks on partially + * utilized systems if we require spare_capacity > task_util(p), + * so we allow for some task stuffing by using + * spare_capacity > task_util(p)/2. + */ + if (this_spare > task_util(p) / 2 && + imbalance*this_spare > 100*most_spare) + return NULL; + else if (most_spare > task_util(p) / 2) + return most_spare_sg; + if (!idlest || 100*this_load < imbalance*min_load) return NULL; return idlest;