From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751989AbcAEXiK (ORCPT ); Tue, 5 Jan 2016 18:38:10 -0500 Received: from LGEAMRELO12.lge.com ([156.147.23.52]:35278 "EHLO lgeamrelo12.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751487AbcAEXiF (ORCPT ); Tue, 5 Jan 2016 18:38:05 -0500 X-Original-SENDERIP: 156.147.1.127 X-Original-MAILFROM: namhyung@kernel.org X-Original-SENDERIP: 165.244.98.76 X-Original-MAILFROM: namhyung@kernel.org X-Original-SENDERIP: 10.177.227.17 X-Original-MAILFROM: namhyung@kernel.org Date: Wed, 6 Jan 2016 08:37:53 +0900 From: Namhyung Kim To: Andi Kleen CC: "Wangnan (F)" , Arnaldo Carvalho de Melo , Ingo Molnar , Peter Zijlstra , Jiri Olsa , LKML , David Ahern , Stephane Eranian , Masami Hiramatsu Subject: Re: [RFC/PATCH] perf report: Show random usage tip on the help line Message-ID: <20160105233753.GB18895@sejong> References: <1451972206-22481-1-git-send-email-namhyung@kernel.org> <568B638F.1030208@huawei.com> <20160105104307.GA13561@danjae.kornet> <20160105205246.GJ15533@two.firstfloor.org> MIME-Version: 1.0 In-Reply-To: <20160105205246.GJ15533@two.firstfloor.org> User-Agent: Mutt/1.5.24 (2015-08-30) X-MIMETrack: Itemize by SMTP Server on LGEKRMHUB06/LGE/LG Group(Release 8.5.3FP6|November 21, 2013) at 2016/01/06 08:38:00, Serialize by Router on LGEKRMHUB06/LGE/LG Group(Release 8.5.3FP6|November 21, 2013) at 2016/01/06 08:38:00, Serialize complete at 2016/01/06 08:38:00 Content-Type: text/plain; charset="utf-8" Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jan 05, 2016 at 09:52:46PM +0100, Andi Kleen wrote: > > Btw, does anyone have some tips to add? :) > > Use perf script to show individual samples > Use perf report --percent-limit 5 to only show entires above 5% > Use perf record -b -g / perf report --branch-history to show branch events > Use perf record -b / perf report to show branch mispredictions > Use perf report -M intel to show Intel style assembler > Use perf report --sort srcfile to sort by source file > Use perf report --sort symbol,srcline to sort by source line > Use perf record -e '{cycles,cache-misses}:S' / perf report --group to associate events We should enable --group by default if recorded data file has groups IMHO. Arnaldo, could you please take this? https://lkml.org/lkml/2015/11/29/76 > Use perf mem record / perf mem report for memory address profiling > Use perf stat -I 1000 to count events in intervals > Use perf stat -I 1000 -x, to count events and output as CSV > Use perf timechart record / report to generate high level time line > Use perf probe --add kfunc / perf record -e kfunc to trace a custom trace point Thanks for sharing! > > You may also want to adapt some of Brendan's one liners: > > http://www.brendangregg.com/perf.html Will take a look. Thanks, Namhyung