From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756592AbcDDVe4 (ORCPT ); Mon, 4 Apr 2016 17:34:56 -0400 Received: from casper.infradead.org ([85.118.1.10]:47314 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756556AbcDDVez (ORCPT ); Mon, 4 Apr 2016 17:34:55 -0400 Date: Mon, 4 Apr 2016 23:34:50 +0200 From: Peter Zijlstra To: Rik van Riel Cc: Ingo Molnar , Jiri Olsa , James Hartsock , Srivatsa Vaddagiri , Kirill Tkhai , linux-kernel@vger.kernel.org Subject: Re: [RFC] sched: unused cpu in affine workload Message-ID: <20160404213450.GE3448@twins.programming.kicks-ass.net> References: <20160404082302.GB2137@krava.local> <20160404085944.GA3030@gmail.com> <20160404091951.GA10360@gmail.com> <20160404093844.GA16017@gmail.com> <20160404132321.GZ3448@twins.programming.kicks-ass.net> <1459799116.6219.24.camel@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1459799116.6219.24.camel@redhat.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, Apr 04, 2016 at 03:45:16PM -0400, Rik van Riel wrote: > An optimal solution is NP hard. > > Heuristics that "move tasks with pressure" may be > much more doable, and lead to perfectly satisfactory > results, especially if most migrations happen within > a socket (and the same shared L3 cache). Right; trick will be finding something that mostly works without making the regular balance paths increase in complexity. As per the argument in kernel/sched/fair.c:5694 the current load-balancing averages out to O(n), and I would very much like to keep it that way.