Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S967039Ab3HIKdv (ORCPT ); Fri, 9 Aug 2013 06:33:51 -0400 Received: from mx1.redhat.com ([209.132.183.28]:45506 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S966522Ab3HIKdu (ORCPT ); Fri, 9 Aug 2013 06:33:50 -0400 Date: Fri, 9 Aug 2013 12:33:23 +0200 From: Jiri Olsa To: Frederic Weisbecker Cc: Peter Zijlstra , LKML , Ingo Molnar , Namhyung Kim , Arnaldo Carvalho de Melo , Stephane Eranian Subject: Re: [PATCH 2/3] perf: Account freq events globally Message-ID: <20130809103323.GE1045@krava.brq.redhat.com> References: <1375460996-16329-1-git-send-email-fweisbec@gmail.com> <1375460996-16329-3-git-send-email-fweisbec@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1375460996-16329-3-git-send-email-fweisbec@gmail.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1246 Lines: 29 On Fri, Aug 02, 2013 at 06:29:55PM +0200, Frederic Weisbecker wrote: > Freq events may not always be affine to a particular CPU. As such, > account_event_cpu() may crash if we account per cpu a freq event > that has event->cpu == -1. > > To solve this, lets account freq events globally. In practice > this doesn't change much the picture because perf tools create > per-task perf events with one event per CPU by default. Profiling a > single CPU is usually a corner case so there is no much point in > optimizing things that way. > > Reported-by: Jiri Olsa > Suggested-by: Peter Zijlstra > Signed-off-by: Frederic Weisbecker > Cc: Ingo Molnar > Cc: Peter Zijlstra > Cc: Jiri Olsa > Cc: Namhyung Kim > Cc: Arnaldo Carvalho de Melo > Cc: Stephane Eranian no more OOPSes ;-) Tested-by: Jiri Olsa