From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932832AbYA2Qv1 (ORCPT ); Tue, 29 Jan 2008 11:51:27 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1760770AbYA2QvK (ORCPT ); Tue, 29 Jan 2008 11:51:10 -0500 Received: from relay2.sgi.com ([192.48.171.30]:50427 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1760441AbYA2QvI (ORCPT ); Tue, 29 Jan 2008 11:51:08 -0500 Date: Tue, 29 Jan 2008 10:51:04 -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: <20080129105104.d70f36ef.pj@sgi.com> In-Reply-To: <479F0507.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> 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: > This is correct. We have the balance policy polymorphically associated > with each sched_class, and the CFS load-balancer and RT "load" (really, > priority) balancer can coexist together at the same time and across > arbitrary #s of cores So ... we have the option of having all sched_classes coexist polymorphically. That I didn't realize until this thread. Now ... do we -want- to ?) That is, what is the easiest kernel-user API to work with and understand? Is it one where we essentially expose sched_class to user space, and let them pick their sched_class, or pick none of the above (don't balance)? Or is it one where, other than the special case my batch schedulers need to not balance at all, we expose nothing more to user space, and provide all sched_class load balancers to all sched_domains (other than those not balanced at all)? -- I won't rest till it's the best ... Programmer, Linux Scalability Paul Jackson 1.940.382.4214