From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756276AbdEROcA (ORCPT ); Thu, 18 May 2017 10:32:00 -0400 Received: from smtp.codeaurora.org ([198.145.29.96]:54020 "EHLO smtp.codeaurora.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754107AbdEROb5 (ORCPT ); Thu, 18 May 2017 10:31:57 -0400 DMARC-Filter: OpenDMARC Filter v1.3.2 smtp.codeaurora.org 02A1C60DDD Authentication-Results: pdx-caf-mail.web.codeaurora.org; dmarc=none (p=none dis=none) header.from=codeaurora.org Authentication-Results: pdx-caf-mail.web.codeaurora.org; spf=none smtp.mailfrom=jhugo@codeaurora.org Subject: Re: [RFC 1/2] sched/fair: Fix load_balance() affinity redo path To: Dietmar Eggemann , Peter Zijlstra Cc: Ingo Molnar , linux-kernel@vger.kernel.org, Austin Christ , Tyler Baicar References: <1494608498-4538-1-git-send-email-jhugo@codeaurora.org> <1494608498-4538-2-git-send-email-jhugo@codeaurora.org> <20170512204754.GK4626@worktop.programming.kicks-ass.net> <9580a899-0fdb-7c14-c6e5-397f7d52bcf2@codeaurora.org> <9b97fa6f-2b3d-3e10-fd55-208ef47f3e2a@arm.com> From: Jeffrey Hugo Message-ID: <890e6ad4-ebe7-44dd-7369-9143d53246b1@codeaurora.org> Date: Thu, 18 May 2017 08:31:55 -0600 User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.0.1 MIME-Version: 1.0 In-Reply-To: <9b97fa6f-2b3d-3e10-fd55-208ef47f3e2a@arm.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 5/15/2017 8:56 AM, Dietmar Eggemann wrote: > On 12/05/17 21:57, Jeffrey Hugo wrote: >> On 5/12/2017 2:47 PM, Peter Zijlstra wrote: >>> On Fri, May 12, 2017 at 11:01:37AM -0600, Jeffrey Hugo wrote: >>>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c >>>> index d711093..8f783ba 100644 >>>> --- a/kernel/sched/fair.c >>>> +++ b/kernel/sched/fair.c >>>> @@ -8219,8 +8219,19 @@ static int load_balance(int this_cpu, struct >>>> rq *this_rq, >>>> /* All tasks on this runqueue were pinned by CPU affinity */ >>>> if (unlikely(env.flags & LBF_ALL_PINNED)) { >>>> + struct cpumask tmp; >>> >>> You cannot have cpumask's on stack. >> >> Well, we need a temp variable to store the intermediate values since the >> cpumask_* operations are somewhat limited, and require a "storage" >> parameter. >> >> Do you have any suggestions to meet all of these requirements? > > What about we use env.dst_grpmask and check if cpus is an improper > subset of env.dst_grpmask? In this case we have to get rid of > setting env.dst_grpmask = NULL in case of CPU_NEWLY_IDLE which is > IMHO not an issue since it's idle is passed via env into > can_migrate_task(). > And cpus has to be and'ed with sched_domain_span(env.sd). > > I'm not sure if this will work with 'not fully connected NUMA' (SD_OVERLAP) > though ... Hmm. I follow the idea, but I'm not too confident in the SD_OVERLAP case, and looking at your proposed code, it seems invasive to me - changes are needed in what would otherwise be unrelated sections of code. I'd prefer not to go in that direction. Also, it appears that the dst_cpu is still considered as a source for load. We've got a different idea to address the stack issue, and still keep the change "contained", which I'll roll into a V2 today or tomorrow. -- Jeffrey Hugo Qualcomm Datacenter Technologies as an affiliate of Qualcomm Technologies, Inc. Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.