From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752042AbZLRG6L (ORCPT ); Fri, 18 Dec 2009 01:58:11 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751530AbZLRG6K (ORCPT ); Fri, 18 Dec 2009 01:58:10 -0500 Received: from mx2.mail.elte.hu ([157.181.151.9]:36134 "EHLO mx2.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750990AbZLRG6I (ORCPT ); Fri, 18 Dec 2009 01:58:08 -0500 Date: Fri, 18 Dec 2009 07:57:55 +0100 From: Ingo Molnar To: Peter Zijlstra Cc: Mike Galbraith , LKML Subject: Re: [PATCH 0/6] Some load-balancer cleanups Message-ID: <20091218065755.GA23808@elte.hu> References: <20091217185021.684424629@chello.nl> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20091217185021.684424629@chello.nl> User-Agent: Mutt/1.5.20 (2009-08-17) X-ELTE-SpamScore: 0.0 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=0.0 required=5.9 tests=none autolearn=no SpamAssassin version=3.2.5 _SUMMARY_ Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Peter Zijlstra wrote: > Since RT has since grown its own load-balancer which is totally independent > from CFS, we can remove some of the left-overs from back when. > > Gets rid of the ->load_balance and ->move_one_task sched_class calls and > removed the rq_iterator stuff. > > Also carries a lock-break recently found wanted by -rt. > > Compile tested with CGROUP/SMP/UP and booted on x86_64-SMP. > > include/linux/sched.h | 8 - > kernel/sched.c | 1945 ++--------------------------------------------- > kernel/sched_fair.c | 1778 +++++++++++++++++++++++++++++++++++++++++-- > kernel/sched_idletask.c | 21 - > kernel/sched_rt.c | 20 - > 5 files changed, 1805 insertions(+), 1967 deletions(-) Nice cleanups! I think we want to delay its application to the scheduler tree for a week or two, to not interact with any urgent fixes for the .33 code. Thanks, Ingo