From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1762578AbXJYXhj (ORCPT ); Thu, 25 Oct 2007 19:37:39 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755300AbXJYXhc (ORCPT ); Thu, 25 Oct 2007 19:37:32 -0400 Received: from netops-testserver-3-out.sgi.com ([192.48.171.28]:34042 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754036AbXJYXhb (ORCPT ); Thu, 25 Oct 2007 19:37:31 -0400 Date: Thu, 25 Oct 2007 16:37:30 -0700 (PDT) From: Christoph Lameter X-X-Sender: clameter@schroedinger.engr.sgi.com To: David Rientjes cc: Andrew Morton , Andi Kleen , Paul Jackson , Lee Schermerhorn , linux-kernel@vger.kernel.org Subject: Re: [patch 2/2] cpusets: add interleave_over_allowed option In-Reply-To: Message-ID: References: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 25 Oct 2007, David Rientjes wrote: > Adds a new 'interleave_over_allowed' option to cpusets. > > When a task with an MPOL_INTERLEAVE memory policy is attached to a cpuset > with this option set, the interleaved nodemask becomes the cpuset's > mems_allowed. When the cpuset's mems_allowed changes, the interleaved > nodemask for all tasks with MPOL_INTERLEAVE memory policies is also > updated to be the new mems_allowed nodemask. > > This allows applications to specify that they want to interleave over all > nodes that they are allowed to access. This set of nodes can be changed > at any time via the cpuset interface and each individual memory policy is > updated to reflect the changes for all attached tasks when this option is > set. More interactions between cpusets and memory policies. We have to be careful here to keep clean semantics. Isnt it a bit surprising for an application that has set up a custom MPOL_INTERLEAVE policy if the nodes suddenly change because of a cpuset or mems_allowed change?