From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753073AbbC0QXz (ORCPT ); Fri, 27 Mar 2015 12:23:55 -0400 Received: from e34.co.us.ibm.com ([32.97.110.152]:48913 "EHLO e34.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753025AbbC0QXx (ORCPT ); Fri, 27 Mar 2015 12:23:53 -0400 Message-ID: <55158408.60909@linux.vnet.ibm.com> Date: Fri, 27 Mar 2015 21:53:36 +0530 From: Preeti U Murthy User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 MIME-Version: 1.0 To: Jason Low , Wanpeng Li CC: peterz@infradead.org, mingo@kernel.org, riel@redhat.com, daniel.lezcano@linaro.org, vincent.guittot@linaro.org, srikar@linux.vnet.ibm.com, pjt@google.com, benh@kernel.crashing.org, efault@gmx.de, linux-kernel@vger.kernel.org, iamjoonsoo.kim@lge.com, svaidy@linux.vnet.ibm.com, tim.c.chen@linux.intel.com, morten.rasmussen@arm.com, "Gautham R. Shenoy" Subject: Re: [PATCH V2] sched: Improve load balancing in the presence of idle CPUs References: <20150326130014.21532.17158.stgit@preeti.in.ibm.com> <20150327021201.GA4491@kernel> <1427432841.2788.10.camel@j-VirtualBox> In-Reply-To: <1427432841.2788.10.camel@j-VirtualBox> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15032716-0017-0000-0000-000009AF4E3A Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Wanpeng, Jason, On 03/27/2015 10:37 AM, Jason Low wrote: > On Fri, 2015-03-27 at 10:12 +0800, Wanpeng Li wrote: >> Hi Preeti, >> On Thu, Mar 26, 2015 at 06:32:44PM +0530, Preeti U Murthy wrote: >>> >>> 1. An ILB CPU was chosen from the first numa domain to trigger nohz idle >>> load balancing [Given the experiment, upto 6 CPUs per core could be >>> potentially idle in this domain.] >>> >>> 2. However the ILB CPU would call load_balance() on itself before >>> initiating nohz idle load balancing. >>> >>> 3. Given cores are SMT8, the ILB CPU had enough opportunities to pull >>> tasks from its sibling cores to even out load. >>> >>> 4. Now that the ILB CPU was no longer idle, it would abort nohz idle >>> load balancing >> >> I don't see abort nohz idle load balancing when ILB CPU was no longer idle >> in nohz_idle_balance(), could you explain more in details? > > Hi Wanpeng, > > In nohz_idle_balance(), there is a check for need_resched() so if the > cpu has something to run, it should exit nohz_idle_balance(), which may > cause it to not do the idle balancing on the other CPUs. You are right, it is need_resched() causing the issue. I am sorry I overlooked that 'idle' was not a pointer. Thanks a lot for pointing out the issue :) But the patch still does good as you will agree, and the changelog has no specific mention to the 'idle' parameter but describes the issue in general. Hence, we are good. Regards Preeti U Murthy > > >