From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752658Ab2HUNLt (ORCPT ); Tue, 21 Aug 2012 09:11:49 -0400 Received: from mail.x86-64.org ([217.9.48.20]:58748 "EHLO mail.x86-64.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751470Ab2HUNLq (ORCPT ); Tue, 21 Aug 2012 09:11:46 -0400 Date: Tue, 21 Aug 2012 15:11:36 +0200 From: Borislav Petkov To: Peter Zijlstra Cc: Ingo Molnar , Steven Rostedt , Frederic Weisbecker , LKML Subject: Re: [RFC PATCH -v2 0/4] Persistent events Message-ID: <20120821131136.GC21432@aftab.osrc.amd.com> References: <1345139123-15212-1-git-send-email-bp@amd64.org> <1345545050.23018.95.camel@twins> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1345545050.23018.95.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 Tue, Aug 21, 2012 at 12:30:50PM +0200, Peter Zijlstra wrote: > Good progress there, there's still a few things though: > > - the point also raised by Steven, I'm pretty sure that the placing of > the debugfs files unfortunate. I would much rather see something > like /debug/perf/persistent/$foo, also dropping your > perf_event_desc::dir_name. Ok, how do we want to do the per-CPU layout there? Like this: /debug/perf/persistent/mce_record0 /debug/perf/persistent/mce_record1 ... or rather /debug/perf/persistent/cpu0/mce_record /debug/perf/persistent/cpu1/mce_record ? The thing is, I'm not sure we want to make persistent events per-CPU implicitly. If yes, then the second layout would fit better. Hmm. > - I would make perf_add_persistent_on_cpu() static and create > something like perf_add_persistent() which iterates all CPUs and > creates: "%s-%04d", perf_event_desc::fname, cpu. Ok. > This needs a little extra for cpu-hotplug, not sure what to do there. get/put_online_cpus()? and then maybe check whether some of the CPUs are offline and warn if so? > - related to the first point, by not tying them to actual events > you can create a persistent 'event' that contains multiple events. > Its quite possible to create multiple kernel events and use the > equivalent of PERF_EVENT_IOC_SET_OUTPUT on them to the exposed FD. Hm, interesting. So, in that case, the persistent thing would have a per-CPU buffer and a file descriptor connected to it and one would be able to add events which would log into the per-CPU buffer. Ok. > - It might be good to provide means of changing the persistent > event's buffer size, or maybe even 'destroy' persistent buffers. ioctl? Or something else? Thanks. -- Regards/Gruss, Boris. Advanced Micro Devices GmbH Einsteinring 24, 85609 Dornach GM: Alberto Bozzo Reg: Dornach, Landkreis Muenchen HRB Nr. 43632 WEEE Registernr: 129 19551