From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from e34.co.us.ibm.com (e34.co.us.ibm.com [32.97.110.152]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id B553E1A0145 for ; Fri, 10 Apr 2015 08:37:15 +1000 (AEST) Received: from /spool/local by e34.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Thu, 9 Apr 2015 16:37:13 -0600 Received: from b03cxnp07029.gho.boulder.ibm.com (b03cxnp07029.gho.boulder.ibm.com [9.17.130.16]) by d03dlp01.boulder.ibm.com (Postfix) with ESMTP id 2898D1FF0025 for ; Thu, 9 Apr 2015 16:28:22 -0600 (MDT) Received: from d03av05.boulder.ibm.com (d03av05.boulder.ibm.com [9.17.195.85]) by b03cxnp07029.gho.boulder.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id t39MbBlc53018670 for ; Thu, 9 Apr 2015 15:37:11 -0700 Received: from d03av05.boulder.ibm.com (localhost [127.0.0.1]) by d03av05.boulder.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id t39MbAh2015491 for ; Thu, 9 Apr 2015 16:37:10 -0600 Date: Thu, 9 Apr 2015 15:37:09 -0700 From: Nishanth Aravamudan To: Brice Goglin Subject: Re: Topology updates and NUMA-level sched domains Message-ID: <20150409223709.GF53918@linux.vnet.ibm.com> References: <20150406214558.GA38501@linux.vnet.ibm.com> <20150407102147.GJ23123@twins.programming.kicks-ass.net> <20150407171410.GA62529@linux.vnet.ibm.com> <20150407194129.GT23123@twins.programming.kicks-ass.net> <552503A1.3050502@inria.fr> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 In-Reply-To: <552503A1.3050502@inria.fr> Cc: Boqun Feng , Srikar Dronamraju , Peter Zijlstra , linux-kernel@vger.kernel.org, Ingo Molnar , Anton Blanchard , linuxppc-dev@lists.ozlabs.org, Anshuman Khandual List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On 08.04.2015 [12:32:01 +0200], Brice Goglin wrote: > Le 07/04/2015 21:41, Peter Zijlstra a écrit : > > No, that's very much not the same. Even if it were dealing with hotplug > > it would still assume the cpu to return to the same node. > > > > But mostly people do not even bother to handle hotplug. > > > > You said userspace assumes the cpu<->node relation is a boot-time fixed > one, and hotplug breaks this. How do you expect userspace to handle > hotplug? Is there a convenient way to be notified when a CPU (or memory) > is unplugged? There is some mention of "User Space Notification" in cpu-hotplug.txt, but no idea if it's current. -Nish From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754522AbbDIWhR (ORCPT ); Thu, 9 Apr 2015 18:37:17 -0400 Received: from e36.co.us.ibm.com ([32.97.110.154]:42982 "EHLO e36.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753284AbbDIWhO (ORCPT ); Thu, 9 Apr 2015 18:37:14 -0400 Date: Thu, 9 Apr 2015 15:37:09 -0700 From: Nishanth Aravamudan To: Brice Goglin Cc: Peter Zijlstra , Ingo Molnar , linux-kernel@vger.kernel.org, Srikar Dronamraju , Boqun Feng , Anshuman Khandual , linuxppc-dev@lists.ozlabs.org, Benjamin Herrenschmidt , Anton Blanchard Subject: Re: Topology updates and NUMA-level sched domains Message-ID: <20150409223709.GF53918@linux.vnet.ibm.com> References: <20150406214558.GA38501@linux.vnet.ibm.com> <20150407102147.GJ23123@twins.programming.kicks-ass.net> <20150407171410.GA62529@linux.vnet.ibm.com> <20150407194129.GT23123@twins.programming.kicks-ass.net> <552503A1.3050502@inria.fr> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <552503A1.3050502@inria.fr> X-Operating-System: Linux 3.13.0-40-generic (x86_64) User-Agent: Mutt/1.5.21 (2010-09-15) X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15040922-0021-0000-0000-000009B9CD42 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 08.04.2015 [12:32:01 +0200], Brice Goglin wrote: > Le 07/04/2015 21:41, Peter Zijlstra a écrit : > > No, that's very much not the same. Even if it were dealing with hotplug > > it would still assume the cpu to return to the same node. > > > > But mostly people do not even bother to handle hotplug. > > > > You said userspace assumes the cpu<->node relation is a boot-time fixed > one, and hotplug breaks this. How do you expect userspace to handle > hotplug? Is there a convenient way to be notified when a CPU (or memory) > is unplugged? There is some mention of "User Space Notification" in cpu-hotplug.txt, but no idea if it's current. -Nish