From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753642AbbEKTQW (ORCPT ); Mon, 11 May 2015 15:16:22 -0400 Received: from mail.kernel.org ([198.145.29.136]:40338 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752021AbbEKTQS (ORCPT ); Mon, 11 May 2015 15:16:18 -0400 Date: Mon, 11 May 2015 16:16:14 -0300 From: Arnaldo Carvalho de Melo To: Jiri Olsa Cc: Namhyung Kim , David Ahern Subject: perf tools: Event naming inconsistency Message-ID: <20150511191614.GB5456@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline X-Url: http://acmel.wordpress.com User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Jiri, Noticed this while testing the PERF_RECORD_LOST_SAMPLES patchkit: [root@zoo ~]# perf record -e '{cycles,instructions}:p' usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.017 MB perf.data (16 samples) ] [root@zoo ~]# perf record -e '{cycles:p,instructions:p}' usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.017 MB perf.data (16 samples) ] [root@zoo ~]# Thse should be equivalent, right? If I do: [root@zoo ~]# perf evlist -i perf.data.old cycles instructions [root@zoo ~]# perf evlist -i perf.data cycles:p instructions:p [root@zoo ~]# But: [root@zoo ~]# perf evlist -v -i perf.data.old cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 instructions: size: 112, config: 1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|PERIOD, read_format: ID, inherit: 1, freq: 1, precise_ip: 1, sample_id_all: 1, exclude_guest: 1 [root@zoo ~]# [root@zoo ~]# perf evlist -v -i perf.data cycles:p: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 instructions:p: size: 112, config: 1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|PERIOD, read_format: ID, inherit: 1, freq: 1, precise_ip: 1, sample_id_all: 1, exclude_guest: 1 [root@zoo ~]# Both are exactly the same, would be nice that tooling when showing both cases showed the same event name, to avoid confusion... Anyway, not that high prio ;-) - Arnaldo