From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753397AbZGCHgc (ORCPT ); Fri, 3 Jul 2009 03:36:32 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751425AbZGCHgZ (ORCPT ); Fri, 3 Jul 2009 03:36:25 -0400 Received: from mail.gmx.net ([213.165.64.20]:48819 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751401AbZGCHgY (ORCPT ); Fri, 3 Jul 2009 03:36:24 -0400 X-Authenticated: #14349625 X-Provags-ID: V01U2FsdGVkX1/uNms5obTunn+KqXTnNgm+VNlWsJK6bOYIi5Hfnu lWkcV4zSImNbqA Subject: Re: [patch 0/4] perf_counter tools: support annotation of live kernel modules From: Mike Galbraith To: Ingo Molnar Cc: Arnaldo Carvalho de Melo , Paul Mackerras , =?ISO-8859-1?Q?Fr=E9d=E9ric?= Weisbecker , LKML , Peter Zijlstra In-Reply-To: <20090703072717.GB7943@elte.hu> References: <1246514639.13293.40.camel@marge.simson.net> <20090702064712.GA26690@elte.hu> <1246519076.6384.22.camel@marge.simson.net> <20090702074214.GA19187@elte.hu> <1246521342.8681.5.camel@marge.simson.net> <20090703072717.GB7943@elte.hu> Content-Type: text/plain Date: Fri, 03 Jul 2009 09:36:25 +0200 Message-Id: <1246606585.6257.2.camel@marge.simson.net> Mime-Version: 1.0 X-Mailer: Evolution 2.24.1.1 Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 X-FuHaFi: 0.55 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2009-07-03 at 09:27 +0200, Ingo Molnar wrote: > * Mike Galbraith wrote: > > > On Thu, 2009-07-02 at 09:42 +0200, Ingo Molnar wrote: > > > > (squirrels suggestions away for later reference) > > > > > Btw, another thing: we are thinking about making -F 1000 (1 KHz > > > auto-freq sampling) the default for perf top and perf record. This > > > way we'd always gather enough data (and never too much or too little > > > data), regardless of the intensity of the workload. Have you played > > > with -F before, what's your general experience about it? It's > > > particularly useful for 'rare' and highly fluctuating events like > > > cache-misses. > > > > > > Maybe 1KHz is a bit too low - Oprofile defaults to 100000 cycles > > > interval by default which is about 10 KHz on a 1GHz box and 30 > > > KHz on a 3GHz box. Perhaps 10 KHz is a better default? > > > > My default usage is 1000Hz to keep overhead low. Works fine for > > me. > > ah, so you use -F by default? Yes. > I still think 10 KHz would be better - especially for really short > runs like 'perf record -f -g ./git gc'. Since Oprofile samples at 26 > KHz by default, we must not go to a too low frequency, otherwise > people might get a 'hm, the perf profiles are worse than the > Oprofile ones' first impression ... > > We could perhaps add a freq=1000 switch to .perfconfig - we have > Git's util/config.c facility - it's just unused right now ;-) > > [ Look at the Git sources about how config.c is used. ] Yeah, that's a good idea.. everyone can roll their own defaults. For me, it doesn't matter what the default is, I always specify. -Mike