From patchwork Sun May 11 18:16:58 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yuyang Du X-Patchwork-Id: 4155051 Return-Path: X-Original-To: patchwork-linux-pm@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.19.201]) by patchwork1.web.kernel.org (Postfix) with ESMTP id AF7569F170 for ; Mon, 12 May 2014 02:24:50 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id E63682018A for ; Mon, 12 May 2014 02:24:49 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 16C9F2017D for ; Mon, 12 May 2014 02:24:49 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753330AbaELCX4 (ORCPT ); Sun, 11 May 2014 22:23:56 -0400 Received: from mga01.intel.com ([192.55.52.88]:8861 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758525AbaELCW7 (ORCPT ); Sun, 11 May 2014 22:22:59 -0400 Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by fmsmga101.fm.intel.com with ESMTP; 11 May 2014 19:22:58 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.97,1032,1389772800"; d="scan'208";a="530200863" Received: from dalvikqa005-desktop.bj.intel.com ([10.238.151.105]) by fmsmga001.fm.intel.com with ESMTP; 11 May 2014 19:22:36 -0700 From: Yuyang Du To: mingo@redhat.com, peterz@infradead.org, rafael.j.wysocki@intel.com, linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org Cc: arjan.van.de.ven@intel.com, len.brown@intel.com, alan.cox@intel.com, mark.gross@intel.com, morten.rasmussen@arm.com, vincent.guittot@linaro.org, rajeev.d.muralidhar@intel.com, vishwesh.m.rudramuni@intel.com, nicole.chalhoub@intel.com, ajaya.durg@intel.com, harinarayanan.seshadri@intel.com, jacob.jun.pan@linux.intel.com, fengguang.wu@intel.com, yuyang.du@intel.com Subject: [RFC PATCH 09/12 v2] Intercept idle balancing Date: Mon, 12 May 2014 02:16:58 +0800 Message-Id: <1399832221-8314-10-git-send-email-yuyang.du@intel.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1399832221-8314-1-git-send-email-yuyang.du@intel.com> References: <1399832221-8314-1-git-send-email-yuyang.du@intel.com> Sender: linux-pm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org X-Spam-Status: No, score=-6.0 required=5.0 tests=BAYES_00, DATE_IN_PAST_06_12, RCVD_IN_DNSWL_HI, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP We intercept load balancing to contain the load and load balancing in the consolidated CPUs according to our consolidating mechanism. In idle balancing, we do two things: 1) Skip pulling task to the idle non-consolidated CPUs. 2) In addition, for consolidated Idle CPU, we aggressively pull tasks from non-consolidated CPUs. Signed-off-by: Yuyang Du --- kernel/sched/fair.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c7a6347..94c7a6a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6655,6 +6655,10 @@ out: return ld_moved; } +#ifdef CONFIG_WORKLOAD_CONSOLIDATION +static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); +#endif + /* * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. @@ -6666,6 +6670,9 @@ static int idle_balance(struct rq *this_rq) unsigned long next_balance = jiffies + HZ; u64 curr_cost = 0; int this_cpu = this_rq->cpu; +#ifdef CONFIG_WORKLOAD_CONSOLIDATION + struct cpumask *nonshielded = __get_cpu_var(local_cpu_mask); +#endif idle_enter_fair(this_rq); /* @@ -6684,6 +6691,19 @@ static int idle_balance(struct rq *this_rq) update_blocked_averages(this_cpu); rcu_read_lock(); + +#ifdef CONFIG_WORKLOAD_CONSOLIDATION + cpumask_copy(nonshielded, cpu_active_mask); + + /* + * if we encounter shielded cpus here, don't do balance on them + */ + workload_consolidation_nonshielded_mask(this_cpu, nonshielded); + if (!cpumask_test_cpu(this_cpu, nonshielded)) + goto unlock; + workload_consolidation_unload(nonshielded); +#endif + for_each_domain(this_cpu, sd) { unsigned long interval; int continue_balancing = 1; @@ -6716,6 +6736,9 @@ static int idle_balance(struct rq *this_rq) if (pulled_task) break; } +#ifdef CONFIG_WORKLOAD_CONSOLIDATION +unlock: +#endif rcu_read_unlock(); raw_spin_lock(&this_rq->lock); @@ -7709,6 +7732,14 @@ void print_cfs_stats(struct seq_file *m, int cpu) __init void init_sched_fair_class(void) { #ifdef CONFIG_SMP +#ifdef CONFIG_WORKLOAD_CONSOLIDATION + unsigned int i; + for_each_possible_cpu(i) { + zalloc_cpumask_var_node(&per_cpu(local_cpu_mask, i), + GFP_KERNEL, cpu_to_node(i)); + } +#endif + open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); #ifdef CONFIG_NO_HZ_COMMON