From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1161314AbXBHIYl (ORCPT ); Thu, 8 Feb 2007 03:24:41 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1161488AbXBHIYl (ORCPT ); Thu, 8 Feb 2007 03:24:41 -0500 Received: from smtp.osdl.org ([65.172.181.24]:33060 "EHLO smtp.osdl.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1161314AbXBHIYk (ORCPT ); Thu, 8 Feb 2007 03:24:40 -0500 Date: Thu, 8 Feb 2007 00:24:28 -0800 From: Andrew Morton To: Andi Kleen Cc: KAMEZAWA Hiroyuki , LKML , clameter@sgi.com, GOTO Subject: Re: [BUG][PATCH] fix mempolcy's check on a system with memory-less-node take2 Message-Id: <20070208002428.1b7aa485.akpm@linux-foundation.org> In-Reply-To: <200702080919.16879.ak@suse.de> References: <20070208110606.ebf668d3.kamezawa.hiroyu@jp.fujitsu.com> <200702080903.46242.ak@suse.de> <20070208000857.7296b94b.akpm@linux-foundation.org> <200702080919.16879.ak@suse.de> X-Mailer: Sylpheed version 2.2.7 (GTK+ 2.8.17; x86_64-unknown-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 On Thu, 8 Feb 2007 09:19:16 +0100 Andi Kleen wrote: > The reason we present nodes to user space is that we can tell the user > where the memory is. You seem to try to promote it to some abstract entity > beyond that, but that doesn't seem particularly fruitful to me. I think > I prefer "down to earth" memory nodes. Who said a node is all about memory? A node is (often) a circuit board, with an edge connector, containing some, all or even none of a) CPUs, b) memory and c) IO devices. That is how a kernel should model and treat it, surely? That's reality.