From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932405AbcE0Dl6 (ORCPT ); Thu, 26 May 2016 23:41:58 -0400 Received: from mga09.intel.com ([134.134.136.24]:27665 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932194AbcE0Dl5 (ORCPT ); Thu, 26 May 2016 23:41:57 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.26,371,1459839600"; d="scan'208";a="111362489" Date: Fri, 27 May 2016 03:44:25 +0800 From: Yuyang Du To: Vincent Guittot Cc: Peter Zijlstra , Ingo Molnar , linux-kernel , Benjamin Segall , Paul Turner , Morten Rasmussen , Dietmar Eggemann , byungchul.park@lge.com Subject: Re: [PATCH 2/2] sched/fair: Skip detach and attach load avgs for new group task Message-ID: <20160526194425.GK18670@intel.com> References: <1464225264-32760-1-git-send-email-yuyang.du@intel.com> <1464225264-32760-3-git-send-email-yuyang.du@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Vincent, On Thu, May 26, 2016 at 01:50:56PM +0200, Vincent Guittot wrote: > On 26 May 2016 at 03:14, Yuyang Du wrote: > > Vincent reported that the first task to a new task group's cfs_rq will > > be attached in attach_task_cfs_rq() and once more when it is enqueued > > (see https://lkml.org/lkml/2016/5/25/388). > > > > Actually, it is worse, attach_task_cfs_rq() is called for new task even > > way before init_entity_runnable_average(). > > > > Solve this by avoiding attach as well as detach new task's sched avgs > > in task_move_group_fair(). To do it, we need to know whether the task > > is forked or not, so we pass this info all the way from sched_move_task() > > to attach_task_cfs_rq(). > > Not sure that this is the right way to solve this problem because you > continue to attach the task twice without detaching it in the mean > time: > - once during the copy of the process in cpu_cgroup_fork (you skip the > attach of load average but the task is still attached to the local > cpu) Sorry, the task's what is still attached, and how? You mean the vruntime thingy? But the load/util avgs are not. > In the mean time, sched_entity is initialized and the last_update_time is reset last_update_time is set to 0 in initialization, and this is the first time it is touched, no? > - one more time when the task is enqueued because the last_update_time > has been reset (this time you don't skip the attache of load_avg This is expected/wanted. We don't skip this because this will be the first-time attach. > Should you better detach the sched_entity with a copy of its parent > metrics before initializing it and attaching it to the new cpu ? Thanks, Yuyang