From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755984Ab2GEQJW (ORCPT ); Thu, 5 Jul 2012 12:09:22 -0400 Received: from mail-lb0-f174.google.com ([209.85.217.174]:57449 "EHLO mail-lb0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751335Ab2GEQJU convert rfc822-to-8bit (ORCPT ); Thu, 5 Jul 2012 12:09:20 -0400 MIME-Version: 1.0 In-Reply-To: <1341234662.1476.13.camel@leonhard> References: <1340960907-3725-1-git-send-email-jolsa@redhat.com> <87fw9blyhj.fsf@sejong.aot.lge.com> <20120702101518.GC967@krava.redhat.com> <1341234662.1476.13.camel@leonhard> Date: Thu, 5 Jul 2012 18:09:18 +0200 Message-ID: Subject: Re: [PATCHv3 0/3] perf tool: Add new event group management From: Stephane Eranian To: Namhyung Kim Cc: Jiri Olsa , acme@redhat.com, a.p.zijlstra@chello.nl, mingo@elte.hu, paulus@samba.org, cjashfor@linux.vnet.ibm.com, fweisbec@gmail.com, linux-kernel@vger.kernel.org, tglx@linutronix.de, andi@firstfloor.org, drepper@gmail.com Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8BIT X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jul 2, 2012 at 3:11 PM, Namhyung Kim wrote: > 2012-07-02 (월), 12:15 +0200, Jiri Olsa: >> On Mon, Jul 02, 2012 at 10:53:44AM +0900, Namhyung Kim wrote: >> > Just a question, is there a way to know about the grouping at perf >> > report time? >> >> nope, AFAIK only ID and perf_event_attr is stored for event >> grouping is known only for record time >> > > I heard that Arnaldo (or Stephane) wanted to make perf report > group-aware or such so that it can show related events together. But to > do that, it seems we need to change the data file format first, right? > Yes, you'd like something like that. The idea is to use an event to sample and the others to compute event deltas. For instance, how many loads/stores instructions retired for every 100k instructions retired. For that you need grouping. The kernel supports this already, the perf tool does not. I don't think you need to change the file format. Everything is there already in the headers. OF course, you perf report needs to detect this mode and adjust the output. IF not, then it should only display samples coming from the first event. Not clear how you'd display the information in perf report or perf annotate at this point yet. > Any idea? > > > -- > Regards, > Namhyung Kim > >