From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1757394Ab3AIIdc (ORCPT <rfc822;w@1wt.eu>);
	Wed, 9 Jan 2013 03:33:32 -0500
Received: from mga11.intel.com ([192.55.52.93]:51601 "EHLO mga11.intel.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1757273Ab3AIIdb (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Wed, 9 Jan 2013 03:33:31 -0500
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="4.84,436,1355126400"; 
   d="scan'208";a="274650030"
Message-ID: <50ED2B9F.3080800@intel.com>
Date: Wed, 09 Jan 2013 16:34:39 +0800
From: Alex Shi <alex.shi@intel.com>
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:15.0) Gecko/20120912 Thunderbird/15.0.1
MIME-Version: 1.0
To: Namhyung Kim <namhyung@kernel.org>
CC: Ingo Molnar <mingo@kernel.org>, Peter Zijlstra <a.p.zijlstra@chello.nl>,
        LKML <linux-kernel@vger.kernel.org>,
        Namhyung Kim <namhyung.kim@lge.com>, Mike Galbraith <efault@gmx.de>,
        Preeti U Murthy <preeti@linux.vnet.ibm.com>,
        Vincent Guittot <vincent.guittot@linaro.org>
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>
In-Reply-To: <876236rdum.fsf@sejong.aot.lge.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

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 <namhyung.kim@lge.com>
>>>
>>> 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.


> 
> Thanks,
> Namhyung
> 


-- 
Thanks Alex