From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757276Ab1EZKzm (ORCPT ); Thu, 26 May 2011 06:55:42 -0400 Received: from arkanian.console-pimps.org ([212.110.184.194]:54343 "EHLO arkanian.console-pimps.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756173Ab1EZKzl (ORCPT ); Thu, 26 May 2011 06:55:41 -0400 Date: Thu, 26 May 2011 11:55:39 +0100 From: Matt Fleming To: Peter Zijlstra , Zhang Rui Cc: LKML , linux-pm , mingo@elte.hu, acme@redhat.com, ming.m.lin@intel.com, "Brown, Len" Subject: Re: [PATCH 2/3] introduce intel_rapl driver Message-ID: <20110526105527.GA27748@console-pimps.org> References: <1306398857.2207.157.camel@rui> <1306403003.1200.41.camel@twins> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1306403003.1200.41.camel@twins> 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 On Thu, May 26, 2011 at 11:43:23AM +0200, Peter Zijlstra wrote: > > That's just wrong.. the reason you're wanting to have this timer is to > avoid the RAPL MSRs from overflowing and you loosing offsets, right? > > But the above is actually forcing the event to create samples on a > totally unrelated time base. > > RAPL should fail to create a sampling event since it doesn't have the > capability to trigger overflow interrupts based on its events. > > If you want a timer, add one, but don't do this. > > If you expect you actually want to sample, use this event as part of a > group and add a sampling event in there and use PERF_FORMAT_GROUP, Matt > was working on patches to make perf-record capable of this. Yep, I have some unfinished patches around here somewhere... *rummage* OK, they're in this repository on the perf/group-events branch, git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/sh-2.6.git Obviously since I last touched them in November of last year they're more than likely not going to apply cleanly to tip, and perhaps more importantly, I don't think I ever submitted them to LKML for review. Rui, I'll try to look at your patch series over the weekend and get my sampling patches into a state where they can be submitted for review and used by the intel_rapl driver. Does that sound OK? Or if you want to take a more proactive approach, you're welcome to finish and submit them ;-) -- Matt Fleming, Intel Open Source Technology Center