linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@kernel.org>
To: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: "Wangnan (F)" <wangnan0@huawei.com>,
	linux-kernel@vger.kernel.org,
	Adrian Hunter <adrian.hunter@intel.com>,
	Borislav Petkov <bp@suse.de>,
	Chandler Carruth <chandlerc@gmail.com>,
	David Ahern <dsahern@gmail.com>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	Stephane Eranian <eranian@google.com>,
	pi3orama <pi3orama@163.com>
Subject: Re: [PATCH 13/16] perf callchain: Switch default to 'graph,0.5,caller'
Date: Thu, 22 Oct 2015 10:46:55 +0200	[thread overview]
Message-ID: <20151022084655.GA19913@gmail.com> (raw)
In-Reply-To: <20151021134348.GI10639@kernel.org>


* Arnaldo Carvalho de Melo <acme@redhat.com> wrote:

> > 5) --no-children
> > 
> > I agree that 'perf top -g --no-children' looks more intuitive than 'perf top -g'.
> 
> So, what do you propose, to switch back the default to --no-children, for both 
> tools, top and report? Now that I am getting used to it... ;-)

Heh ;-) So I'm only thinking out loud, trying to find the most intuitive initial 
screen to display. Expert users can configure their output any which way they want 
it to be, I'm not worried about them.

It's casual and in particular first-time users we should be worried about most - 
if they try the '-g' option in record, what will they first see in 'perf report' 
output?

I think the best output method would be to include only the 'highest level' parent 
symbols, with all children summed up under the parent's entry. Isn't the new 
'graph,0.5,caller' default very close to that?

But what confuses me about the output is the same that confused Wangnan's users:

  "This is my story: after switching to new version of perf, in a period of time 
   there are plenty of perf users in my company be confused by the first column of 
   'perf report' because the sum of the percentage listed there is much higher than 
   100%. They find me because they think this is a bug in perf which breaks their 
   routinely profiling work."

So this is suboptimal.

The first column is 'Children', which should show the sum of all child overhead - 
but if a child overhead was already included under a parent, it should never show 
up under another parent's entry. I.e. the first column should only contain the 
highest level entries, no sub-entries.

But what we do currently is:

  Children      Self  Command        Shared Object       Symbol
-   70.41%     0.00%  cc1            cc1                 [.] toplev_main
   - toplev_main
      + __libc_start_main
-   70.38%     0.00%  cc1            libc-2.20.so        [.] __libc_start_main
   + __libc_start_main

i.e. even though '__libc_start_main' is a child of 'toplev_main', it's still 
included on the 'overview' page.

Is there an output method that can do what I suggest above?

( Having both 'children' and 'self' columns in itself is intuitive IMHO: it shows
  that an entry that is shown does not directly have overhead at that level, a
  child call of it has that overhead. )

Thanks,

	Ingo

  parent reply	other threads:[~2015-10-22  8:47 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-10-05 21:03 [GIT PULL 00/16] perf/core improvements and fixes Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 01/16] tools lib api fs: No need to use PATH_MAX + 1 Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 02/16] perf evlist: Display DATA_SRC sample type bit Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 03/16] perf annotate: Fix sizeof_sym_hist overflow issue Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 04/16] perf tools: Export perf_event_attr__set_max_precise_ip() Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 05/16] perf tools: Introduce 'P' modifier to request max precision Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 06/16] perf tests: Add parsing test for 'P' modifier Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 07/16] perf tools: Add support for sorting on the iaddr Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 08/16] perf tools: Setup proper width for symbol_iaddr field Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 09/16] perf tools: Handle -h and -v options Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 10/16] perf tests: Add arch tests Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 11/16] perf tests: Move x86 tests into arch directory Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 12/16] perf tests: Add Intel CQM test Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 13/16] perf callchain: Switch default to 'graph,0.5,caller' Arnaldo Carvalho de Melo
2015-10-09 20:34   ` Brendan Gregg
2015-10-09 21:56     ` Arnaldo Carvalho de Melo
2015-10-09 22:10       ` Brendan Gregg
2015-10-09 22:25         ` Arnaldo Carvalho de Melo
2015-10-20  0:16           ` Brendan Gregg
2015-10-20 12:00             ` Arnaldo Carvalho de Melo
2015-10-20 12:19               ` Frederic Weisbecker
2015-10-20 13:06                 ` Arnaldo Carvalho de Melo
2015-10-20 17:21                   ` Frederic Weisbecker
2015-10-20 18:44                     ` Arnaldo Carvalho de Melo
2015-10-21  1:21                       ` Namhyung Kim
2015-10-21 13:24                         ` Arnaldo Carvalho de Melo
2015-10-21  8:09                     ` Namhyung Kim
2015-10-21 11:57                       ` Wangnan (F)
2015-10-21 16:35                       ` Frederic Weisbecker
     [not found]                   ` <CAAwGriEtYeBytGt9x24=uUqSEy5oJ2HigfA2KXnKyrAioKrtNg@mail.gmail.com>
2015-10-21 16:27                     ` Frederic Weisbecker
2015-10-21 18:28                     ` Brendan Gregg
2015-10-21 19:23                       ` Arnaldo Carvalho de Melo
2015-10-22  0:44                         ` Brendan Gregg
2015-10-21  8:06               ` Ingo Molnar
2015-10-21 13:21                 ` Arnaldo Carvalho de Melo
2015-10-21 19:18                 ` Brendan Gregg
2015-10-10  7:09         ` Ingo Molnar
2015-10-10  7:34           ` Brendan Gregg
2015-10-10  9:07             ` Ingo Molnar
2015-10-12 15:27   ` Frederic Weisbecker
2015-10-13  4:26   ` Namhyung Kim
2015-10-19 23:50     ` Brendan Gregg
2015-10-21  7:29       ` Namhyung Kim
2015-10-20 13:23   ` Wangnan (F)
2015-10-20 13:38     ` Arnaldo Carvalho de Melo
2015-10-21  1:44       ` Namhyung Kim
2015-10-21  8:48       ` Ingo Molnar
2015-10-21 13:43         ` Arnaldo Carvalho de Melo
2015-10-21 13:46           ` Arnaldo Carvalho de Melo
2015-10-22  8:46           ` Ingo Molnar [this message]
2015-10-22 12:36             ` Namhyung Kim
2015-10-05 21:03 ` [PATCH 14/16] perf ui browser: Optional horizontal scrolling key binding Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 15/16] perf hists browser: Implement horizontal scrolling Arnaldo Carvalho de Melo
2015-10-05 21:03 ` [PATCH 16/16] perf tools: Fail properly in case pattern matching fails to find tracepoint Arnaldo Carvalho de Melo
2015-10-06  7:09 ` [GIT PULL 00/16] perf/core improvements and fixes Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20151022084655.GA19913@gmail.com \
    --to=mingo@kernel.org \
    --cc=acme@redhat.com \
    --cc=adrian.hunter@intel.com \
    --cc=bp@suse.de \
    --cc=chandlerc@gmail.com \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=namhyung@kernel.org \
    --cc=pi3orama@163.com \
    --cc=wangnan0@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).