From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760358AbZBYJBM (ORCPT ); Wed, 25 Feb 2009 04:01:12 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1757051AbZBYJA5 (ORCPT ); Wed, 25 Feb 2009 04:00:57 -0500 Received: from mail-bw0-f161.google.com ([209.85.218.161]:62915 "EHLO mail-bw0-f161.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752979AbZBYJA4 convert rfc822-to-8bit (ORCPT ); Wed, 25 Feb 2009 04:00:56 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; b=dpoaj8mFF9Wi24QMK1eRJFIfwWErtjaaThbXzl5u3XWl1KHQ36TDZDsjYoWbrL7xev QsRiklvMP4q8dxIN1wHeNkbWtYAwnRzIKBOdLPz5M1YcaJ47+H7mknIG+1Tatomi0NhU 4N1/4gSa7l+HuxuBSqHlJ4eoB1VKtqNi1/lI8= MIME-Version: 1.0 In-Reply-To: <20090225002852.5ef5b869.akpm@linux-foundation.org> References: <20090225025608.956691460@goodmis.org> <20090225025753.798204550@goodmis.org> <20090224194548.3effb746.akpm@linux-foundation.org> <20090224203308.8d623e0b.akpm@linux-foundation.org> <20090225081118.GC15303@elte.hu> <20090225002852.5ef5b869.akpm@linux-foundation.org> Date: Wed, 25 Feb 2009 11:00:53 +0200 X-Google-Sender-Auth: e15fea1a18c18c52 Message-ID: <84144f020902250100k41e55dd7w8a9c8d2ca96908ea@mail.gmail.com> Subject: Re: [PATCH 2/4] tracing: add event trace infrastructure From: Pekka Enberg To: Andrew Morton Cc: Ingo Molnar , Steven Rostedt , LKML , Thomas Gleixner , Peter Zijlstra , Frederic Weisbecker , Theodore Tso , Arjan van de Ven , Pekka Paalanen , Arnaldo Carvalho de Melo , Jason Baron , Martin Bligh , Mathieu Desnoyers , "Frank Ch. Eigler" , KOSAKI Motohiro , Jens Axboe , Masami Hiramatsu , Steven Rostedt Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Andrew, On Wed, Feb 25, 2009 at 10:28 AM, Andrew Morton wrote: > A better approach would be to design simple, robust kernel interfaces > which make sense and which aren't made all complex by putting the user > interface in kernel space.  And to maintain corresponding userspace > tools which manipulate and present the IO from those kernel interfaces. We did this for kmemtrace and quite frankly, I usually end up spending more time figuring out how to export the data from a virtual machine than actually analyzing the results. What makes ftrace so cool is the fact that it has almost zero-overhead for setup and that the text-based data format plays well with simple scripting tools available everywhere. Pekka