From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757550AbbJVN5p (ORCPT ); Thu, 22 Oct 2015 09:57:45 -0400 Received: from mail-pa0-f42.google.com ([209.85.220.42]:33607 "EHLO mail-pa0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752197AbbJVN5n convert rfc822-to-8bit (ORCPT ); Thu, 22 Oct 2015 09:57:43 -0400 Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (Mac OS X Mail 9.0 \(3094\)) Subject: Re: [PATCH 2/3] perf top: Support call-graph display options also From: Taeung Song In-Reply-To: Date: Thu, 22 Oct 2015 22:57:35 +0900 Cc: Ingo Molnar , Arnaldo Carvalho de Melo , Peter Zijlstra , Jiri Olsa , "linux-kernel@vger.kernel.org" , David Ahern , Adrian Hunter , Borislav Petkov , Chandler Carruth , Frederic Weisbecker , Stephane Eranian , Wang Nan , Brendan Gregg Content-Transfer-Encoding: 8BIT Message-Id: References: <1445495330-25416-1-git-send-email-namhyung@kernel.org> <1445495330-25416-2-git-send-email-namhyung@kernel.org> <20151022082301.GB18916@gmail.com> To: Namhyung Kim X-Mailer: Apple Mail (2.3094) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, Namhyung and Ingo > On Oct 22, 2015, at 9:20 PM, Namhyung Kim wrote: > > On Thu, Oct 22, 2015 at 5:23 PM, Ingo Molnar wrote: >> >> * Namhyung Kim wrote: >> >>> Currently 'perf top --call-graph' option is same as 'perf record'. But >>> 'perf top' also need to receive display options in 'perf report'. To do >>> that, change parse_callchain_report_opt() to allow record options too. >>> >>> Now perf top can receive display options like below: >>> >>> $ perf top --call-graph >>> Error: option `call-graph' requires a value >>> >>> Usage: perf top [] >>> >>> --call-graph >>> >>> setup and enables call-graph (stack chain/backtrace) >>> recording: fp dwarf lbr, output_type (graph, flat, >>> fractal, or none), min percent threshold, optional >>> print limit, callchain order, key (function or >>> address), add branches >> >> Yeah, so this fix is nice, and I think we should also do another patch to fix the >> help text output to be the following: >> >> --call-graph >> >> >> Set up and enable call graph (call chain, stack backtrace) recording: >> >> record_mode: call graph recording mode (fp|dwarf|lbr) >> record_size: if rec_mode == dwarf, maximum depth of stack recording (bytes), >> default: 8192 bytes. >> print_style: call graph printing style (graph|flat|fractal|none) >> limit: minimum call graph inclusion threshold (percent) >> print_limit: printing threshold (percent) >> call_order: call graph order (caller|callee) >> sort_key: sorting key (function|address|branch) >> >> Default: fp,graph,0.5,0.0,caller,function >> >> Note that this text evolved a bit over what I sent in my previous mail. > > OK. I'll cook a patch to improve help message like this as well as man page. > > >> >> Also note that I think we should sync up the perf config options to be the same as >> the option name shortcuts used in this help text. > > Ah, good idea. > >> >> Side note: to improve perf config usability, we should probably also recognize >> underscores in perf config entries, i.e. the following variants should both work: >> >> print_percent = 1 >> print-percent = 1 >> >> Right now only the second one will match. > > Taeung, could you consider fixing this in your config patchiest? > Sure, no problem. I thought as below. Even if one use a print_percent variable, it will be handled like print-percent. Also if a user change print_percent variable by perf-config command, print-percent variable will remain in perfconfig file. (Because perf-config command will rewrite perfconfig file.) Is anything wrong ? Thanks, Taeung