From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751037AbcFAT53 (ORCPT ); Wed, 1 Jun 2016 15:57:29 -0400 Received: from merlin.infradead.org ([205.233.59.134]:50015 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750742AbcFAT52 (ORCPT ); Wed, 1 Jun 2016 15:57:28 -0400 Date: Wed, 1 Jun 2016 21:57:23 +0200 From: Peter Zijlstra To: Morten Rasmussen Cc: Mike Galbraith , mingo@redhat.com, dietmar.eggemann@arm.com, yuyang.du@intel.com, vincent.guittot@linaro.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 03/16] sched/fair: Disregard idle task wakee_flips in wake_wide Message-ID: <20160601195723.GD28447@twins.programming.kicks-ass.net> References: <1464001138-25063-1-git-send-email-morten.rasmussen@arm.com> <1464001138-25063-4-git-send-email-morten.rasmussen@arm.com> <1464001927.4537.118.camel@suse.de> <20160523120010.GB27946@e105550-lin.cambridge.arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20160523120010.GB27946@e105550-lin.cambridge.arm.com> User-Agent: Mutt/1.5.21 (2012-12-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, May 23, 2016 at 01:00:10PM +0100, Morten Rasmussen wrote: > On Mon, May 23, 2016 at 01:12:07PM +0200, Mike Galbraith wrote: > > On Mon, 2016-05-23 at 11:58 +0100, Morten Rasmussen wrote: > > > wake_wide() is based on task wakee_flips of the waker and the wakee to > > > decide whether an affine wakeup is desirable. On lightly loaded systems > > > the waker is frequently the idle task (pid=0) which can accumulate a lot > > > of wakee_flips in that scenario. It makes little sense to prevent affine > > > wakeups on an idle cpu due to the idle task wakee_flips, so it makes > > > more sense to ignore them in wake_wide(). > > > > You sure? What's the difference between a task flipping enough to > > warrant spreading the load, and an interrupt source doing the same? > > I've both witnessed firsthand, and received user confirmation of this > > very thing improving utilization. > > Right, I didn't consider the interrupt source scenario, my fault. > > The problem then seems to be distinguishing truly idle and busy doing > interrupts. The issue that I observe is that wake_wide() likes pushing > tasks around in lightly scenarios which isn't desirable for power > management. Selecting the same cpu again may potentially let others > reach deeper C-state. > > With that in mind I will if I can do better. Suggestions are welcome :-) Seeing how we always so select_idle_siblings() after affine_sd, the only wake_affine movement that matters is cross-llc. So intra-llc wakeups can avoid the movement, no?