Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S261745AbVEPQrv (ORCPT ); Mon, 16 May 2005 12:47:51 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S261747AbVEPQru (ORCPT ); Mon, 16 May 2005 12:47:50 -0400 Received: from omx3-ext.sgi.com ([192.48.171.20]:61607 "EHLO omx3.sgi.com") by vger.kernel.org with ESMTP id S261745AbVEPQre (ORCPT ); Mon, 16 May 2005 12:47:34 -0400 Date: Mon, 16 May 2005 09:47:08 -0700 (PDT) From: Christoph Lameter To: Dave Hansen cc: Andrew Morton , linux-mm , Linux Kernel Mailing List , shai@scalex86.org, steiner@sgi.com Subject: Re: NUMA aware slab allocator V3 In-Reply-To: <1116251568.1005.29.camel@localhost> Message-ID: References: <20050512000444.641f44a9.akpm@osdl.org> <20050513000648.7d341710.akpm@osdl.org> <20050513043311.7961e694.akpm@osdl.org> <1116251568.1005.29.camel@localhost> 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: 1353 Lines: 30 On Mon, 16 May 2005, Dave Hansen wrote: > There are some broken assumptions in the kernel that > CONFIG_DISCONTIG==CONFIG_NUMA. These usually manifest when code assumes > that one pg_data_t means one NUMA node. > > However, NUMA node ids are actually distinct from "discontigmem nodes". > A "discontigmem node" is just one physically contiguous area of memory, > thus one pg_data_t. Some (non-NUMA) Mac G5's have a gap in their > address space, so they get two discontigmem nodes. I thought the discontigous memory in one node was handled through zones? I.e. ZONE_HIGHMEM in i386? > So, that #error is bogus. It's perfectly valid to have multiple > discontigmem nodes, when the number of NUMA nodes is 1. MAX_NUMNODES > refers to discontigmem nodes, not NUMA nodes. Ok. We looked through the code and saw that the check may be removed without causing problems. However, there is still a feeling of uneasiness about this. To what node does numa_node_id() refer? And it is legit to use numa_node_id() to index cpu maps and stuff? How do the concepts of numa node id relate to discontig node ids? - 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/