From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751570Ab0LVJEV (ORCPT ); Wed, 22 Dec 2010 04:04:21 -0500 Received: from canuck.infradead.org ([134.117.69.58]:56983 "EHLO canuck.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751185Ab0LVJEQ convert rfc822-to-8bit (ORCPT ); Wed, 22 Dec 2010 04:04:16 -0500 Subject: Re: [RFC PATCH] perf: Add load latency monitoring on Intel Nehalem/Westmere From: Peter Zijlstra To: Lin Ming Cc: Ingo Molnar , Andi Kleen , Stephane Eranian , Frederic Weisbecker , Arjan van de Ven , lkml In-Reply-To: <1293006808.2170.42.camel@laptop> References: <1293005543.2565.156.camel@minggr.sh.intel.com> <1293006808.2170.42.camel@laptop> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8BIT Date: Wed, 22 Dec 2010 10:04:16 +0100 Message-ID: <1293008656.2170.67.camel@laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 2010-12-22 at 09:33 +0100, Peter Zijlstra wrote: > On Wed, 2010-12-22 at 16:12 +0800, Lin Ming wrote: > > It's applied on top of tip/master(3ea1f4f89) and Andi's offcore > > patchsets are needed. > > I still haven't gotten a version of that I'm willing to apply. That is, maybe you could pick up his patches and finish them, Andi doesn't seem interested in getting them sorted. I think the last posting lost the needs_percore logic, which would avoid the percore allocations on platforms that don't need it (if we can detect if HT is enabled that would be nice too). I think he also lost the topology iteration (which can be used for both the percore and the amd northbridge stuff), currently we iterate the full machine looking for a matching nb/core_id, using a smaller topology mask makes sense. Also, after reading your patch, I think we want the MSR names in the lists, not the numbers.