Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755566Ab3HAOVP (ORCPT ); Thu, 1 Aug 2013 10:21:15 -0400 Received: from mail-wg0-f53.google.com ([74.125.82.53]:38007 "EHLO mail-wg0-f53.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754803Ab3HAOVO (ORCPT ); Thu, 1 Aug 2013 10:21:14 -0400 Date: Thu, 1 Aug 2013 16:21:11 +0200 From: Frederic Weisbecker To: Peter Zijlstra Cc: Jiri Olsa , LKML , Namhyung Kim , Ingo Molnar , Arnaldo Carvalho de Melo , Stephane Eranian Subject: Re: [PATCH 6/8] perf: Account freq events per cpu Message-ID: <20130801142109.GH431@somewhere> References: <1374539466-4799-1-git-send-email-fweisbec@gmail.com> <1374539466-4799-7-git-send-email-fweisbec@gmail.com> <20130801124658.GC1032@krava.brq.redhat.com> <20130801133155.GB27162@twins.programming.kicks-ass.net> <20130801135525.GE431@somewhere> <20130801140352.GE27162@twins.programming.kicks-ass.net> <20130801140615.GF27162@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20130801140615.GF27162@twins.programming.kicks-ass.net> 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: 1415 Lines: 28 On Thu, Aug 01, 2013 at 04:06:15PM +0200, Peter Zijlstra wrote: > On Thu, Aug 01, 2013 at 04:03:52PM +0200, Peter Zijlstra wrote: > > On Thu, Aug 01, 2013 at 03:55:27PM +0200, Frederic Weisbecker wrote: > > > On Thu, Aug 01, 2013 at 03:31:55PM +0200, Peter Zijlstra wrote: > > > > > > > > Where the freq thing is new and shiney, but we already had the other > > > > two. Of those, cgroup events must be per cpu so that should be good, > > > > the branch_stack thing tests ATTACH_TASK, which should also be good, but > > > > leaves me wonder wth they do for those that are attached to tasks. > > > > > > > > But yes, the frequency thing is borken. > > > > > > Aie, so the freq thing, I can either account to all CPUs (inc to all > > > and send an IPI to all), or when the event scheds in/out. Probably we > > > should do the former to avoid sending an IPI at all context switches. > > > > Yeah, just go with a single global state for now.. > > The perf default is to create inherited counter, which are per cpu > anyway. So we'll not loose much. So you mean that I keep the per cpu state when event->cpu != -1 and also have a global counter for the others. Right? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/