From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751467AbaETVje (ORCPT ); Tue, 20 May 2014 17:39:34 -0400 Received: from mga02.intel.com ([134.134.136.20]:62483 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750735AbaETVjb (ORCPT ); Tue, 20 May 2014 17:39:31 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.98,876,1392192000"; d="scan'208";a="543852342" Subject: Re: [PATCH] sched: Reduce the rate of needless idle load balancing From: Tim Chen To: Jason Low Cc: Ingo Molnar , Peter Zijlstra , Andrew Morton , Len Brown , Russ Anderson , Dimitri Sivanich , Hedi Berriche , Andi Kleen , Michel Lespinasse , Rik van Riel , Peter Hurley , Linux Kernel Mailing List In-Reply-To: References: <1400617046.2970.270.camel@schen9-DESK> <1400619550.2970.274.camel@schen9-DESK> Content-Type: text/plain; charset="UTF-8" Date: Tue, 20 May 2014 14:39:27 -0700 Message-ID: <1400621967.2970.280.camel@schen9-DESK> Mime-Version: 1.0 X-Mailer: Evolution 2.32.3 (2.32.3-1.fc14) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2014-05-20 at 14:09 -0700, Jason Low wrote: > Hi Tim, Rik > > Yes, that makes sense that we want to balance if they are equal. We > may also consider using "if (time_after_eq(jiffies, > rq->next_balance)". > > Reviewed-by: Jason Low Jason & Rik, Thanks for reviewing the patch. I've updated the patch below as suggested. Tim --- From: Tim Chen Subject: [PATCH v2] sched: Reduce the rate of needless idle load balancing The current no_hz idle load balancer do load balancing for *all* idle cpus, even though the time due to load balance for a particular idle cpu could be still a while in the future. This introduces a much higher load balancing rate than what is necessary. The patch changes the behavior by only doing idle load balancing on behalf of an idle cpu only when it is due for load balancing. On SGI's systems with over 3000 cores, the cpu responsible for idle balancing got overwhelmed with idle balancing, and introduces a lot of OS noise to workloads. This patch fixes the issue. Acked-by: Russ Anderson Reviewed-by: Rik van Riel Reviewed-by: Jason Low Signed-off-by: Tim Chen --- kernel/sched/fair.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9b4c4f3..b826c3a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6764,12 +6764,17 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) rq = cpu_rq(balance_cpu); - raw_spin_lock_irq(&rq->lock); - update_rq_clock(rq); - update_idle_cpu_load(rq); - raw_spin_unlock_irq(&rq->lock); - - rebalance_domains(rq, CPU_IDLE); + /* + * If time for next balance is due, + * do the balance. + */ + if (time_after_eq(jiffies, rq->next_balance)) { + raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); + update_idle_cpu_load(rq); + raw_spin_unlock_irq(&rq->lock); + rebalance_domains(rq, CPU_IDLE); + } if (time_after(this_rq->next_balance, rq->next_balance)) this_rq->next_balance = rq->next_balance; -- 1.7.11.7