From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756042AbaKTGSr (ORCPT ); Thu, 20 Nov 2014 01:18:47 -0500 Received: from lgeamrelo01.lge.com ([156.147.1.125]:60487 "EHLO lgeamrelo01.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750792AbaKTGSp (ORCPT ); Thu, 20 Nov 2014 01:18:45 -0500 X-Original-SENDERIP: 10.177.222.235 X-Original-MAILFROM: namhyung@gmail.com From: Namhyung Kim To: Arnaldo Carvalho de Melo Cc: kan.liang@intel.com, jolsa@redhat.com, linux-kernel@vger.kernel.org, ak@linux.intel.com Subject: Re: [PATCH V4 3/3] perf tool: Add sort key symoff for perf diff References: <1416328700-1836-1-git-send-email-kan.liang@intel.com> <1416328700-1836-4-git-send-email-kan.liang@intel.com> <20141118211319.GD3790@kernel.org> Date: Thu, 20 Nov 2014 15:18:44 +0900 In-Reply-To: <20141118211319.GD3790@kernel.org> (Arnaldo Carvalho de Melo's message of "Tue, 18 Nov 2014 18:13:19 -0300") Message-ID: <87a93mpf7f.fsf@sejong.aot.lge.com> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.1 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 18 Nov 2014 18:13:19 -0300, Arnaldo Carvalho de Melo wrote: > Em Tue, Nov 18, 2014 at 11:38:20AM -0500, kan.liang@intel.com escreveu: >> From: Kan Liang >> >> Sometime, especially debugging scaling issue, the function level diff >> may be high granularity. The user may want to do deeper diff analysis >> for some cache or lock issue. The "symoff" key can let the user sort >> differential profile by ips. This feature should only work when the >> perf.data comes from same binary. > > So, to avoid having people scratching heads, and since we have the > build-id for both perf.data files, hence for both binaries being > compared, can we check the build ids and either refuse to do the diff or > print a big warning about different binaries being compared? Why do you think so? I think it's fine to use symoff for different binaries for same reason as the symbol sort key. Even if some functions were changed, other DSOs and/or functions still have same offset and thus have meaningful diff result IMHO. Thanks, Namhyung