From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753321AbZG2JAi (ORCPT ); Wed, 29 Jul 2009 05:00:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751451AbZG2JAh (ORCPT ); Wed, 29 Jul 2009 05:00:37 -0400 Received: from srv5.dvmed.net ([207.36.208.214]:54593 "EHLO mail.dvmed.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751352AbZG2JAg (ORCPT ); Wed, 29 Jul 2009 05:00:36 -0400 Message-ID: <4A700F8A.6000505@garzik.org> Date: Wed, 29 Jul 2009 04:59:54 -0400 From: Jeff Garzik User-Agent: Thunderbird 2.0.0.21 (X11/20090320) MIME-Version: 1.0 To: Peter Zijlstra CC: mingo@redhat.com, hpa@zytor.com, tglx@linutronix.de, mingo@elte.hu, paulus@samba.org, linux-kernel@vger.kernel.org, rostedt@goodmis.org, linux-tip-commits@vger.kernel.org Subject: Re: perf_counter: hook up the tracepoint events References: <20090319194233.744044174@chello.nl> <4A6F9F51.4010107@garzik.org> <1248856508.6987.3041.camel@twins> In-Reply-To: <1248856508.6987.3041.camel@twins> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Score: -4.4 (----) X-Spam-Report: SpamAssassin version 3.2.5 on srv5.dvmed.net summary: Content analysis details: (-4.4 points, 5.0 required) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Peter Zijlstra wrote: > On Tue, 2009-07-28 at 21:01 -0400, Jeff Garzik wrote: >> Peter Zijlstra wrote: >>> diff --git a/init/Kconfig b/init/Kconfig >>> index 8a38443..761129a 100644 >>> --- a/init/Kconfig >>> +++ b/init/Kconfig >>> @@ -945,6 +945,11 @@ config PERF_COUNTERS >>> >>> Say Y if unsure. >>> >>> +config EVENT_PROFILE >>> + bool "Tracepoint profile sources" >>> + depends on PERF_COUNTERS && EVENT_TRACER >>> + default y >>> + >>> endmenu >> Adding help text would be... helpful. :) >> >> The net result in this case was the addition of a completely-unexplained >> Kconfig option late in 2.6.31-rc. >> >> Maybe the x86 maintainers could help see that they don't push >> unexplained Kconfig options upstream -- particularly ones we are asked >> to enable by default? > > You're right. Johannes Berg made the same complaint yesterday. > > Is the below any good? > > --- > Subject: perf_counter: Add help text to CONFIG_EVENT_PROFILE > > Explain what tracepoint profile sources is about. > > Signed-off-by: Peter Zijlstra > --- > init/Kconfig | 6 ++++++ > 1 files changed, 6 insertions(+), 0 deletions(-) > > diff --git a/init/Kconfig b/init/Kconfig > index 13473ac..ffae67c 100644 > --- a/init/Kconfig > +++ b/init/Kconfig > @@ -957,6 +957,12 @@ config EVENT_PROFILE > bool "Tracepoint profile sources" > depends on PERF_COUNTERS && EVENT_TRACING > default y > + help > + Allow the use of tracepoints as software performance counters. > + > + When this is enabled, you can create perf counters based on > + tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID > + found in debugfs://tracing/events/*/*/id. Thanks. Is this feature useful w/out debugfs? If yes, ACK. Jeff