From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756226AbYA2VCu (ORCPT ); Tue, 29 Jan 2008 16:02:50 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752502AbYA2VCl (ORCPT ); Tue, 29 Jan 2008 16:02:41 -0500 Received: from netops-testserver-3-out.sgi.com ([192.48.171.28]:39176 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751727AbYA2VCk (ORCPT ); Tue, 29 Jan 2008 16:02:40 -0500 Date: Tue, 29 Jan 2008 15:02:34 -0600 From: Paul Jackson To: "Gregory Haskins" Cc: a.p.zijlstra@chello.nl, mingo@elte.hu, dmitry.adamushko@gmail.com, rostedt@goodmis.org, menage@google.com, rientjes@google.com, tong.n.li@intel.com, tglx@linutronix.de, akpm@linux-foundation.org, dhaval@linux.vnet.ibm.com, vatsa@linux.vnet.ibm.com, sgrubb@redhat.com, linux-kernel@vger.kernel.org, ebiederm@xmission.com, nickpiggin@yahoo.com.au Subject: Re: scheduler scalability - cgroups, cpusets and load-balancing Message-Id: <20080129150234.b57ce988.pj@sgi.com> In-Reply-To: <479F4812.BA47.005A.0@novell.com> References: <1201600428.28547.87.camel@lappy> <1201604243.28547.101.camel@lappy> <20080129053005.bc7a11d7.pj@sgi.com> <1201607401.28547.124.camel@lappy> <479F0507.BA47.005A.0@novell.com> <20080129105104.d70f36ef.pj@sgi.com> <479F1A4F.BA47.005A.0@novell.com> <20080129130403.92d0a1fe.pj@sgi.com> <479F4812.BA47.005A.0@novell.com> Organization: SGI X-Mailer: Sylpheed version 2.2.4 (GTK+ 2.12.0; 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 List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Gregory wrote: > > ... (1) turning off > > sched_load_balance in any overlapping cpusets, including all > > encompassing parent cpusets, (2) leaving sched_load_balance on in the > > RT cpuset itself, and ... > > Technically you only need (2). I run my 4-8 core development systems > in the single default global cpuset, normally. Well, if you're running in the default cpuset, then you automatically get (1), because sched_load_balance is turned off in all overlapping cpusets (there aren't any overlapping cpusets!) So, yes, you -do- need both (1) and (2). In your normal system, you just happen to get (1) effortlessly. -- I won't rest till it's the best ... Programmer, Linux Scalability Paul Jackson 1.940.382.4214