From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: Ability for classifying of measurements\ Date: Wed, 04 May 2016 16:50:14 -0700 Message-ID: <87inytpemh.fsf@tassilo.jf.intel.com> References: <1461099117-21401-1-git-send-email-leonardo.boquillon@tallertechnologies.com> <87ega0whpq.fsf@tassilo.jf.intel.com> <20160420174724.GP9407@two.firstfloor.org> <87mvo5pklu.fsf@tassilo.jf.intel.com> Mime-Version: 1.0 Content-Type: text/plain Return-path: Received: from mga11.intel.com ([192.55.52.93]:19186 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753952AbcEDXuU (ORCPT ); Wed, 4 May 2016 19:50:20 -0400 In-Reply-To: (Daniel Gutson's message of "Wed, 4 May 2016 18:56:02 -0300") Sender: linux-perf-users-owner@vger.kernel.org List-ID: To: Daniel Gutson Cc: Leonardo Boquillon , linux-perf-users@vger.kernel.org, eranian@google.com Daniel Gutson writes: >> >> For non self monitoring there were perf patches at some point, but they >> were rejected because it wasn't clear if a process should be able >> to opt out of monitoring on its own. > > Any link? Here's an older variant from Jiri https://lwn.net/Articles/568602/ I think there was another newer from Stephane to enable/disable perf through an prctl, but I can't find it right now. > (separately, of course): timing is of no help there. > What I would like to know, is what happened (in terms of performance > metrics) on each state. I would simply > call perf_label("state name") on each transition. Ok. It could be done using the uprobes. But would still need to write the tools to filter by it. -Andi