Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1423510AbXBHTJx (ORCPT ); Thu, 8 Feb 2007 14:09:53 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1423508AbXBHTJx (ORCPT ); Thu, 8 Feb 2007 14:09:53 -0500 Received: from omx2-ext.sgi.com ([192.48.171.19]:45834 "EHLO omx2.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1423510AbXBHTJw (ORCPT ); Thu, 8 Feb 2007 14:09:52 -0500 Date: Thu, 8 Feb 2007 11:09:40 -0800 (PST) From: Christoph Lameter To: Andrew Morton cc: Andi Kleen , KAMEZAWA Hiroyuki , LKML , GOTO , Christoph Lameter Subject: Re: [2.6.20][PATCH] fix mempolicy error check on a system with memory-less-node In-Reply-To: <20070207094344.0efdde10.akpm@linux-foundation.org> Message-ID: References: <20070206202312.4f979bcf.kamezawa.hiroyu@jp.fujitsu.com> <20070207082330.d07525ec.akpm@linux-foundation.org> <200702071750.55283.ak@suse.de> <20070207094344.0efdde10.akpm@linux-foundation.org> 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 Content-Length: 1255 Lines: 35 On Wed, 7 Feb 2007, Andrew Morton wrote: > > > A node which has CPUs and no memory is obviously physically possible and > > > isn't a completely insane thing for a user to do. I'd have thought that > > > the kernel should be able to cleanly and clearly handle it, > > > > It doesn't. > > Fix it? Why? It is a bad idea. > > > and to > > > accurately present the machine's topology to the user without us having to > > > go adding falsehoods like this? > > > > a node is a piece of memory. Without memory it doesn't make sense. > > Who said? I can pick up a piece of circuitry which has four CPUs and no > RAM, wave it about then stick it in a computer. The kernel is just wrong, > surely? Surely your computer has some memory so attach it to that memory (which in a NUMA system would be one or the other node). Cpu only "nodes" would mean that all memory would be off node. Meaning whatever interconnect one has would be heavily used. Operating system and application performance will suffer. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/