From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758106AbXJCRop (ORCPT ); Wed, 3 Oct 2007 13:44:45 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754879AbXJCRoh (ORCPT ); Wed, 3 Oct 2007 13:44:37 -0400 Received: from netops-testserver-3-out.sgi.com ([192.48.171.28]:51205 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754811AbXJCRog (ORCPT ); Wed, 3 Oct 2007 13:44:36 -0400 Date: Wed, 3 Oct 2007 10:44:33 -0700 From: Paul Jackson To: Nick Piggin Cc: akpm@linux-foundation.org, menage@google.com, linux-kernel@vger.kernel.org, dino@in.ibm.com, cpw@sgi.com, mingo@elte.hu Subject: Re: [PATCH] cpuset and sched domains: sched_load_balance flag Message-Id: <20071003104433.083337ea.pj@sgi.com> In-Reply-To: <200710030632.00062.nickpiggin@yahoo.com.au> References: <20070930104403.24828.48263.sendpatchset@jackhammer.engr.sgi.com> <200710030356.18090.nickpiggin@yahoo.com.au> <20071003051729.df3d8ab9.pj@sgi.com> <200710030632.00062.nickpiggin@yahoo.com.au> Organization: SGI X-Mailer: Sylpheed version 2.2.4 (GTK+ 2.8.3; i686-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Nick wrote: > There won't be any CPU cycles used, if the tasks are paused (surely > they're not spin waiting). Consider the case when there are two, smaller, non-overlapping cpusets with active jobs, and one larger cpuset, covering both those smaller ones, with only paused tasks. If we realize we don't need to balance the larger cpuset, then we can have two smaller sched domains rather than one larger one. Since the CPU cycle cost of load balancing increases more than linearly with the size of the sched domain, therefore it will save CPU cycles to have the two smaller ones, rather than the one larger one. If user space can just tell us that the larger cpuset doesn't need balancing, then the kernel has enough information to perform this optimization. -- I won't rest till it's the best ... Programmer, Linux Scalability Paul Jackson 1.925.600.0401