From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755352AbXJASPl (ORCPT ); Mon, 1 Oct 2007 14:15:41 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752017AbXJASPe (ORCPT ); Mon, 1 Oct 2007 14:15:34 -0400 Received: from netops-testserver-3-out.sgi.com ([192.48.171.28]:49351 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751817AbXJASPd (ORCPT ); Mon, 1 Oct 2007 14:15:33 -0400 Date: Mon, 1 Oct 2007 11:15:28 -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: <20071001111528.5487b4f4.pj@sgi.com> In-Reply-To: <200709301335.00441.nickpiggin@yahoo.com.au> References: <20070930104403.24828.48263.sendpatchset@jackhammer.engr.sgi.com> <200709300521.03356.nickpiggin@yahoo.com.au> <20070930110753.19b03388.pj@sgi.com> <200709301335.00441.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: > which you could equally achieve by adding > a second set of sched domains (and the global domains could keep > globally balancing). Hmmm ... this could be the key to this discussion. Nick - can two sched domains overlap? And if they do, what does that mean on any user or application behaviour. >>From the cpuset side - this patch handles overlap by joining the 'cpus' into one sched domain. If two cpusets with overlapping 'cpus' are both marked 'sched_load_balance', then this patch forms a single, combined sched domain. As best as I can tell, you and I are actually in agreement in the case that there is no overlap. If the several cpusets which have 'sched_load_balance' enabled have mutually disjoint 'cpus' (no overlap), then my patch forms exactly one sched domain for each such cpuset, having the same 'cpus'. The issue is the overlapping cases - are overlapping sched domains allowed, and if so, how do they affect user space? -- I won't rest till it's the best ... Programmer, Linux Scalability Paul Jackson 1.925.600.0401