From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932747AbYDOVid (ORCPT ); Tue, 15 Apr 2008 17:38:33 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1757711AbYDOViY (ORCPT ); Tue, 15 Apr 2008 17:38:24 -0400 Received: from saeurebad.de ([85.214.36.134]:41961 "EHLO saeurebad.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754388AbYDOViX (ORCPT ); Tue, 15 Apr 2008 17:38:23 -0400 From: Johannes Weiner To: "Yinghai Lu" Cc: suresh.b.siddha@intel.com, "Ingo Molnar" , akpm@linux-foundation.org, mm-commits@vger.kernel.org, andi@firstfloor.org, clameter@sgi.com, kamezawa.hiroyu@jp.fujitsu.com, y-goto@jp.fujitsu.com, linux-kernel@vger.kernel.org Subject: Re: + bootmem-node-setup-agnostic-free_bootmem.patch added to -mm tree References: <200804150623.m3F6NInZ014509@imap1.linux-foundation.org> <20080415071120.GB15499@elte.hu> <87hce3i8mq.fsf@saeurebad.de> <86802c440804151157m5baab2efla7f35a8f98ac76b7@mail.gmail.com> <87mynuhp0o.fsf@saeurebad.de> <86802c440804151303k29295e9bp70c1046b8c9dca76@mail.gmail.com> <87ej96hlc1.fsf@saeurebad.de> <86802c440804151419i42f6a4caj3bb23b6c21d9238d@mail.gmail.com> Date: Tue, 15 Apr 2008 23:38:03 +0200 In-Reply-To: <86802c440804151419i42f6a4caj3bb23b6c21d9238d@mail.gmail.com> (Yinghai Lu's message of "Tue, 15 Apr 2008 14:19:20 -0700") Message-ID: <87abjuhk90.fsf@saeurebad.de> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.0.60 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.1.3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, "Yinghai Lu" writes: > On Tue, Apr 15, 2008 at 2:14 PM, Johannes Weiner wrote: >> Hi, >> >> "Yinghai Lu" writes: >> >> >> >> > 2. intel cross node box: node0: 0g-2g, 4g-6g, node1: 2g-4g, 6g-8g. i >> >> > don't think they have two bdata struct for every node. >> >> >> >> How do the bdata structures represent this setup right now? Are you >> >> sure that there is not a node descriptor for every contiguous region? >> > >> > http://lkml.org/lkml/2008/3/25/233 >> > >> > Subject [patch] srat, x86_64: Add support for nodes spanning other nodes >> > >> > For example, If the physical address layout on a two node system with 8 GB >> > memory is something like: >> > node 0: 0-2GB, 4-6GB >> > node 1: 2-4GB, 6-8GB >> > >> > Current kernels fail to boot/detect this NUMA topology. >> > >> > ACPI SRAT tables can expose such a topology which needs to be supported. >> > >> > Signed-off-by: Suresh Siddha >> >> As I understood the code (more guessing than understanding), it breaks >> down these physical nodes into contiguous logical memory blocks which >> then get represented by having a node descriptor for each of them. Can >> you confirm that? > > Not sure, on x86_64 one node should have one bdata only. > execpt suresh update that to make one node have two bdata. We are just guessing around here. My understanding is that right now we have contigous physical nodes represented by a node descriptor each and with Suresh's patch we have each contigous block represented by its own node descriptor. So in this setup node 0: 0-2GB, 4-6GB node 1: 2-4GB, 6-8GB we have 4 node descriptors [0-2], [2-4], [4-6], [6-8]? Can someone please ack/nak this? Hannes