From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754421AbZGCIBM (ORCPT ); Fri, 3 Jul 2009 04:01:12 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751535AbZGCIA7 (ORCPT ); Fri, 3 Jul 2009 04:00:59 -0400 Received: from mail.gmx.net ([213.165.64.20]:54658 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751118AbZGCIA6 (ORCPT ); Fri, 3 Jul 2009 04:00:58 -0400 X-Authenticated: #14349625 X-Provags-ID: V01U2FsdGVkX1/nKlw2yz7ncjtCA5g9zeCl97gUF+sl+PbXan5G6X 8WVtFYpoze5AvX 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: <20090703072941.GC7943@elte.hu> References: <1246514639.13293.40.camel@marge.simson.net> <20090702064712.GA26690@elte.hu> <1246519076.6384.22.camel@marge.simson.net> <1246524170.7113.20.camel@marge.simson.net> <20090703072941.GC7943@elte.hu> Content-Type: text/plain Date: Fri, 03 Jul 2009 10:00:58 +0200 Message-Id: <1246608058.6257.25.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: 0.63 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2009-07-03 at 09:29 +0200, Ingo Molnar wrote: > * Mike Galbraith wrote: > > > On Thu, 2009-07-02 at 09:17 +0200, Mike Galbraith wrote: > > > > > After I resurrect (well, try) live annotation in top... > > > > Random thought wrt live top annotation: instead of resurrecting in > > the previous form, which could be a bit intrusive display space > > wise, what do you think of this idea? > > > > Provide a kbd input snapshot trigger which builds a perf record > > (hard?) compatible file for the symbols being displayed. Start a > > background task to annotate the lot, stuffing annotate output into > > an output file. > > > > Better ideas highly welcome. > > Hm, is there really a performance problem? Sort of.. > We need to calculate and cache the objdump annotation output once, > but after that it should be pretty fast as we just display updated > counts with the same lines over and over again. No repeated objdump > runs are needed. But active files follow symbols, which change on the fly. Besides, as mentioned previously, while displayed annotation was very cool, it took a lot of display space. For me, top with the ability to emit bic-disposable mini-reports would be my primary perf tools usage. I'd only use big brothers when I needed their power/detail. -Mike