From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arjan van de Ven Subject: Re: [PATCH] PERF(kernel): Cleanup power events V2 Date: Tue, 26 Oct 2010 09:04:19 -0700 Message-ID: <4CC6FC03.708@linux.intel.com> References: <1287488171-25303-3-git-send-email-trenn@suse.de> <1288049630-10947-1-git-send-email-trenn@suse.de> <20101026071020.GC13036@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: Sender: linux-trace-users-owner@vger.kernel.org To: Pierre Tardy Cc: Ingo Molnar , Thomas Renninger , Linus Torvalds , Andrew Morton , Thomas Gleixner , Masami Hiramatsu , Frank Eigler , Steven Rostedt , Kevin Hilman , Peter Zijlstra , linux-omap@vger.kernel.org, rjw@sisk.pl, linux-pm@lists.linux-foundation.org, linux-trace-users@vger.kernel.org, Jean Pihet , Frederic Weisbecker , Tejun Heo , Mathieu Desnoyers List-Id: linux-omap@vger.kernel.org On 10/26/2010 8:32 AM, Pierre Tardy wrote: > On Tue, Oct 26, 2010 at 2:10 AM, Ingo Molnar wrote: > >> How will future PCI (or other device) power saving tracepoints be called? >> >> Might be more consistent to use: >> >> power:cpu_idle >> power:machine_idle >> power:device_idle > Agree with this. > > FYI, I have a runtime_pm tracepoint currently cooking. Here is > preliminary patch. > Can this be a candidate for a "power:device_idle" tracepoint? I would like to see a slightly more advanced tracepoint do the runtime pm framework; specifically I'd like to see the "comm" of the process that's taking a refcount on a device (that way, powertop can track which process keeps a device busy)