From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932236Ab3AJFwI (ORCPT ); Thu, 10 Jan 2013 00:52:08 -0500 Received: from LGEMRELSE1Q.lge.com ([156.147.1.111]:60524 "EHLO LGEMRELSE1Q.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751113Ab3AJFwG (ORCPT ); Thu, 10 Jan 2013 00:52:06 -0500 X-AuditID: 9c93016f-b7b54ae000000e9e-7e-50ee57020b51 From: Namhyung Kim To: Alex Shi Cc: Ingo Molnar , Peter Zijlstra , LKML , Namhyung Kim , Mike Galbraith , Preeti U Murthy , Vincent Guittot Subject: Re: [PATCH] sched: Get rid of unnecessary checks from select_idle_sibling References: <1357714256-24373-1-git-send-email-namhyung@kernel.org> <50ED1D54.70208@intel.com> <876236rdum.fsf@sejong.aot.lge.com> <50ED2B9F.3080800@intel.com> Date: Thu, 10 Jan 2013 14:52:02 +0900 In-Reply-To: <50ED2B9F.3080800@intel.com> (Alex Shi's message of "Wed, 09 Jan 2013 16:34:39 +0800") Message-ID: <87k3rlpou5.fsf@sejong.aot.lge.com> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.1 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain X-Brightmail-Tracker: AAAAAA== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 09 Jan 2013 16:34:39 +0800, Alex Shi wrote: > On 01/09/2013 03:54 PM, Namhyung Kim wrote: >> Hi Alex, >> >> On Wed, 09 Jan 2013 15:33:40 +0800, Alex Shi wrote: >>> On 01/09/2013 02:50 PM, Namhyung Kim wrote: >>>> From: Namhyung Kim >>>> >>>> AFAICS @target cpu of select_idle_sibling() is always either prev_cpu >>>> or this_cpu. So no need to check it again and the conditionals can be >>>> consolidated. >> [snip] >>> Uh, we don't know if the target is this_cpu or previous cpu, If we just >>> check the target idle status, we may miss another idle cpu. So this >>> patch change the logical in this function. >> >> select_idle_sibling() is called only in select_task_rq_fair() if it >> found a suitable affine_sd. The default target is the 'prev_cpu' of the >> task but if wake_affine() returns true it'd be (this) 'cpu'. >> >> I cannot see where the prev_cpu or the cpu is set to another one before >> calling select_idle_sibling. > > The old logical will return directly whenever prev_cpu or this cpu idle, > but your new logical just has one chance. Sorry, I can't get your point. Could you elaborate on it a bit more? Thanks, Namhyung