From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754577AbaGKN5C (ORCPT ); Fri, 11 Jul 2014 09:57:02 -0400 Received: from bombadil.infradead.org ([198.137.202.9]:51624 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753764AbaGKN47 (ORCPT ); Fri, 11 Jul 2014 09:56:59 -0400 Date: Fri, 11 Jul 2014 15:56:53 +0200 From: Peter Zijlstra To: Rik van Riel Cc: mingo@kernel.org, hpa@zytor.com, linux-kernel@vger.kernel.org, torvalds@linux-foundation.org, tglx@linutronix.de Subject: Re: [tip:sched/core] sched/numa: Use effective_load() to balance NUMA loads Message-ID: <20140711135653.GI20603@laptop.programming.kicks-ass.net> References: <1403538378-31571-3-git-send-email-riel@redhat.com> <53BD677B.9050907@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <53BD677B.9050907@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 Wed, Jul 09, 2014 at 12:02:03PM -0400, Rik van Riel wrote: > On 07/05/2014 06:44 AM, tip-bot for Rik van Riel wrote: > > Commit-ID: 6dc1a672ab15604947361dcd02e459effa09bad5 > > Gitweb: http://git.kernel.org/tip/6dc1a672ab15604947361dcd02e459effa09bad5 > > Author: Rik van Riel > > AuthorDate: Mon, 23 Jun 2014 11:46:14 -0400 > > Committer: Ingo Molnar > > CommitDate: Sat, 5 Jul 2014 11:17:35 +0200 > > > > sched/numa: Use effective_load() to balance NUMA loads > > > > When CONFIG_FAIR_GROUP_SCHED is enabled, the load that a task places > > on a CPU is determined by the group the task is in. The active groups > > on the source and destination CPU can be different, resulting in a > > different load contribution by the same task at its source and at its > > destination. As a result, the load needs to be calculated separately > > for each CPU, instead of estimated once with task_h_load(). > > > > Getting this calculation right allows some workloads to converge, > > where previously the last thread could get stuck on another node, > > without being able to migrate to its final destination. > > Self-NAK > > This patch should be reverted. > > It turns out that the tree I am working on was missing > changeset a003a25b227d59ded9197ced109517f037d01c27, > which makes weighted_cpuload and update_numa_stats use > p->se.avg.load_avg_contrib instead of p->se.load.weight. > > This means using effective_load, which operates on the > load.weight is inappropriate. > > Sorry for the noise. n/p I'll take it out. Thanks!