From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S932498AbcCIMqB (ORCPT <rfc822;w@1wt.eu>);
	Wed, 9 Mar 2016 07:46:01 -0500
Received: from mail-pf0-f193.google.com ([209.85.192.193]:34052 "EHLO
	mail-pf0-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S932075AbcCIMpx (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Wed, 9 Mar 2016 07:45:53 -0500
Date: Wed, 9 Mar 2016 21:44:28 +0900
From: Namhyung Kim <namhyung@kernel.org>
To: Jiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>, Ingo Molnar <mingo@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>, Jiri Olsa <jolsa@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>, David Ahern <dsahern@gmail.com>,
        Andi Kleen <andi@firstfloor.org>,
        Stephane Eranian <eranian@google.com>, Wang Nan <wangnan0@huawei.com>
Subject: Re: [PATCH 3/6] perf tools: Fix command line filters in hierarchy
 mode
Message-ID: <20160309124428.GA7678@danjae.kornet>
References: <1457449603-7124-1-git-send-email-namhyung@kernel.org>
 <1457449603-7124-3-git-send-email-namhyung@kernel.org>
 <20160309091356.GA25692@krava.redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <20160309091356.GA25692@krava.redhat.com>
User-Agent: Mutt/1.5.24 (2015-08-30)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Hi Jiri,

On Wed, Mar 09, 2016 at 10:13:56AM +0100, Jiri Olsa wrote:
> On Wed, Mar 09, 2016 at 12:06:40AM +0900, Namhyung Kim wrote:
> > When a command-line filter was applied in hierarchy mode, output was
> > broken especially when filtering on lower level.  The higher level
> > entries didn't show up so it's hard to see the result.
> > 
> > Also it needs to handle multi sort keys in a single level of hierarchy.
> > 
> > Before:
> > 
> >   $ perf report --hierarchy -s 'cpu,{dso,comm}' --comms swapper --stdio
> >   ...
> >   #    Overhead  CPU / Shared Object+Command
> >   # ...........  ...........................
> >   #
> >          13.79%     [kernel.vmlinux]  swapper
> >       31.71%     000
> >          13.80%     [kernel.vmlinux]  swapper
> >           0.43%     [e1000e]          swapper
> >          11.89%     [kernel.vmlinux]  swapper
> >           9.18%     [kernel.vmlinux]  swapper
> > 
> > After:
> > 
> >   #    Overhead  CPU / Shared Object+Command
> >   # ...........  ...............................
> >   #
> >       33.09%     003
> >          13.79%     [kernel.vmlinux]  swapper
> >       31.71%     000
> >          13.80%     [kernel.vmlinux]  swapper
> >           0.43%     [e1000e]          swapper
> >       21.90%     002
> >          11.89%     [kernel.vmlinux]  swapper
> >       13.30%     001
> >           9.18%     [kernel.vmlinux]  swapper
> 
> I'm getting funny numbers when using 'F' toggle in tui mode 
> 
> [jolsa@krava perf]$ ./perf report --hierarchy -s 'cpu,{dso,comm}' --comms swapper 
> 
> Samples: 254  of event 'cycles:pp', Event count (approx.): 132263887
>  Overhead     CPU / Shared Object+Command                                                                                                                     ◆
> + 69.85%      001                                                                                                                                             ▒
> + 44.28%      000                                                                                                                                             ▒
> + 41.62%      002                                                                                                                                             ▒
> + 36.80%      003                                                                                                                                             
> 
> 
> [jolsa@krava perf]$ sudo ./perf top --hierarchy -s 'cpu,{dso,comm}' --comms swapper 
> 
>  Overhead     CPU / Shared O+Command
> + 320.64%     000
> + 179.91%     002
> + 137.05%     003
> + 88.37%      001

Hmm.. I think it's because that the total period is a sum of periods
of leaf nodes.  But if a filter is applied, sum of periods of upper
level entries can be different than sum of the lower level entries.
So it should use top-level entries periods instead IMHO.

I will send a fix.

Thanks,
Namhyung