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 S1752641AbcFFTcx (ORCPT <rfc822;w@1wt.eu>);
	Mon, 6 Jun 2016 15:32:53 -0400
Received: from foss.arm.com ([217.140.101.70]:39157 "EHLO foss.arm.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1751085AbcFFTcw (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Mon, 6 Jun 2016 15:32:52 -0400
Subject: Re: [PATCH v3] sched: fix first task of a task group is attached
 twice
To: Vincent Guittot <vincent.guittot@linaro.org>
References: <CAKfTPtB_yb0P2FEZ4AKR6+Hjad_7dOxiC_w702RGOV6FnDWR8g@mail.gmail.com>
 <1464623541-25429-1-git-send-email-vincent.guittot@linaro.org>
 <574EFFBD.5060803@arm.com>
 <CAKfTPtD401C5_DTPPCMDmV87y2r5sG_066drJQtaFN5-G+9bsA@mail.gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@kernel.org>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Yuyang Du <yuyang.du@intel.com>
From: Dietmar Eggemann <dietmar.eggemann@arm.com>
Message-ID: <5755CFE1.4020005@arm.com>
Date: Mon, 6 Jun 2016 20:32:49 +0100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101
 Thunderbird/38.8.0
MIME-Version: 1.0
In-Reply-To: <CAKfTPtD401C5_DTPPCMDmV87y2r5sG_066drJQtaFN5-G+9bsA@mail.gmail.com>
Content-Type: text/plain; charset=utf-8
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 01/06/16 16:54, Vincent Guittot wrote:
> On 1 June 2016 at 17:31, Dietmar Eggemann <dietmar.eggemann@arm.com> wrote:
>> On 30/05/16 16:52, Vincent Guittot wrote:
>>> The cfs_rq->avg.last_update_time is initialize to 0 with the main effect
>>> that the 1st sched_entity that will be attached, will keep its
>>
>> attached in .task_move_group ?
>>
>> I'm not sure if we can have a .switched_to() directly followed by a
>> .enqueue_task() into a cfs_rq with avg.last_update_time = 0.
> 
> I think it can happen as well if the task is not queued during the
> change of scheduling class because when we attach the task in
> switched_to, the task->se.avg.last_update_time will stay to 0. So when
> the task will be enqueued, it will be attached one more time

You're right. 

So I started msc_test as an rt task in task group tg_1 (css.id=2) (1) and when it slept 
I changed it to become a cfs task (2).


(1) # chrt -r 99 ./cg.sh /tg_1 ./msc_test

(2) # chrt -o -p 0 2093

...
---> busy
[   84.336570] dequeue_task_rt: cpu=2 comm=msc_test pid=2093 tg_css_id=2
[   84.342948] enqueue_task_rt: cpu=1 comm=msc_test pid=2093 tg_css_id=2
---> sleep
[   86.548655] dequeue_task_rt: cpu=1 comm=msc_test pid=2093 tg_css_id=2
[   91.008457] switched_from_rt: cpu=1 comm=msc_test pid=2093
[   91.013896] switched_to_fair: cpu=1 comm=msc_test pid=2093
[   91.019336] attach_entity_load_avg: cpu=1 comm=msc_test pid=2093 last_update_time=0 tg->css.id=2
[   91.028499] do_sched_setscheduler comm=msc_test pid=2093 policy=0 rv=0
[   91.548807] enqueue_task_fair: cpu=1 comm=msc_test pid=2093 tg_css_id=2
[   91.555363] attach_entity_load_avg: cpu=1 comm=msc_test pid=2093 last_update_time=91548795220 tg->css.id=2
---> busy
...