public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Akihiro Nagai <akihiro.nagai.hw@hitachi.com>
To: David Ahern <dsahern@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>,
	Ingo Molnar <mingo@elte.hu>,
	Peter Zijlstra <peterz@infradead.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	linux-kernel@vger.kernel.org,
	Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>,
	2nddept-manager@sdl.hitachi.co.jp,
	Paul Mackerras <paulus@samba.org>
Subject: Re: [PATCH -tip v3 3/6] perf branch trace: print pid and command
Date: Mon, 28 Mar 2011 19:34:56 +0900	[thread overview]
Message-ID: <4D906450.1040809@hitachi.com> (raw)
In-Reply-To: <4D8CAE74.9080805@gmail.com>

(2011/03/26 0:02), David Ahern wrote:
> On 03/25/11 04:14, Akihiro Nagai wrote:
>>> On 03/24/11 05:32, Akihiro Nagai wrote:
>>>> Provide the function to print pid and command name to
>>>> 'perf branch trace'. Users can select items to print with options.
>>>> For example,
>>>>       'perf branch -p trace' prints only pid,
>>>>       'perf branch -ac trace' prints address and comamnd name.
>>>>       'perf branch trace' prints only address (default)
>>>>
>>>> This is output sample (perf branch -ac trace):
>>>> command      address
>>>> ls           0xffffffff8146fe0e =>   ls           0x0000003806200b20
>>>> ls           0xffffffff8146fe0e =>   ls           0x0000003806200b20
>>>> ls           0x0000003806200b23 =>   ls           0x0000003806204910
>>>> ls           0xffffffff8146fe0e =>   ls           0x0000003806204910
>>>> ls           0xffffffff8146fe0e =>   ls           0x0000003806204936
>>>> ls           0xffffffff8146fe0e =>   ls           0x000000380620493d
>>>> ls           0x0000003806204981 =>   ls           0x00000038062049a3
>>>> ls           0x00000038062049a7 =>   ls           0x0000003806204988
>>>
>>> This can be easily added to perf-script. e.g,
>>>
>>> perf record -e branches:u -c 1 -d -- ls /tmp
>>>
>>> perf script -i /tmp/perf.data -f hw:comm,pid,event,sym,addr
>>>
>>> ...
>>> ls  8150 branches: 0x39d30144d0 ffffffff8146a48e  ()
>>> ls  8150 branches: 0x39d3014507 ffffffff8146a48e  ()
>>> ls  8150 branches: 0x39d3014510            14518 _dl_sysdep_start
>>> (/lib64/ld-2.13.so)
>>> ...
>>> ls  8150 branches: 0x39d3015250             1833 process_envvars
>>> (/lib64/ld-2.13.so)
>>> ls  8150 branches: 0x39d3015260            1526f _dl_next_ld_env_entry
>>> (/lib64/ld-2.13.so)
>>> ls  8150 branches: 0x39d3015260            1526f _dl_next_ld_env_entry
>>> (/lib64/ld-2.13.so)
>> It seems to analyze only 'branch from' address and,
>> print 'branch to' address just in hex.
>> I would like to analyze both of addresses branch from/to.
>
> from is sample->ip? to is sample->addr? In the above example
> 0x39d3015260 is the value from sample->addr, 1526f is sample->ip which
> resolves to _dl_next_ld_env_entry from /lib64/ld-2.13.so.
Yes.
In this example, resolved address is only sample->ip (branch from).
We need the resolved address of sample->addr (branch to) too, because
both of them are addresses of execution code.
For example, we need following output.

...
ls 0x00000038062152a9 _dl_sysdep_start+0x189     /lib64/ld-2.12.90.so             => ls           0x00000038062020e0 dl_main+0x0                /lib64/ld-2.12.90.so
ls 0xffffffff814547d2 irq_return+0x0             /lib/modules/2.6.38-rc8-tip+/build/vmlinux => ls 0x00000038062020e0 dl_main+0x0                /lib64/ld-2.12.90.so
ls 0x0000003806202155 dl_main+0x75               /lib64/ld-2.12.90.so             => ls           0x00000038062017d0 process_envvars+0x0        /lib64/ld-2.12.90.so
ls 0xffffffff814547d2 irq_return+0x0             /lib/modules/2.6.38-rc8-tip+/build/vmlinux => ls 0x00000038062017d0 process_envvars+0x0        /lib64/ld-2.12.90.so
ls 0x0000003806201833 process_envvars+0x63       /lib64/ld-2.12.90.so             => ls           0x0000003806215ec0 _dl_next_ld_env_entry+0x0  /lib64/ld-2.12.90.so
ls 0x0000003806215ed3 _dl_next_ld_env_entry+0x13 /lib64/ld-2.12.90.so             => ls           0x0000003806215ee5 _dl_next_ld_env_entry+0x25 /lib64/ld-2.12.90.so
ls 0x0000003806215ee9 _dl_next_ld_env_entry+0x29 /lib64/ld-2.12.90.so             => ls           0x0000003806215ed5 _dl_next_ld_env_entry+0x15 /lib64/ld-2.12.90.so
...

This example's left hand side which is separated by "=>" is a result of resolving sample->ip and,
right hand side is sample->addr's.

>
>>
>> Can perf-script do it by writing scripts?
>
> If you are pulling the data from a perf sample then you can accomplish
> the same goal within perf-script.
It seems that perf-script doesn't have the interface of converting
sample->addr to symbol, pid, comm and others. Of course, we can add
the interface to perf-script, and it could be another way to implement
this function using perf-script.
However, since BTS output usually becomes huge, it would be very slow
to convert all the data by python/perl.

>
>
> David

  reply	other threads:[~2011-03-28 10:35 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-24 11:31 [PATCH -tip v3 0/6] perf: Introduce branch sub commands Akihiro Nagai
2011-03-24 11:31 ` [PATCH -tip v3 1/6] perf: new subcommand perf branch record Akihiro Nagai
2011-03-24 11:32 ` [PATCH -tip v3 2/6] perf branch: Introduce new sub command 'perf branch trace' Akihiro Nagai
2011-03-24 11:32 ` [PATCH -tip v3 3/6] perf branch trace: print pid and command Akihiro Nagai
2011-03-24 17:05   ` David Ahern
2011-03-25 10:14     ` Akihiro Nagai
2011-03-25 15:02       ` David Ahern
2011-03-28 10:34         ` Akihiro Nagai [this message]
2011-03-28 14:31           ` David Ahern
2011-04-01 15:13             ` Frederic Weisbecker
2011-04-01 15:15               ` Peter Zijlstra
2011-04-01 15:24                 ` Arnaldo Carvalho de Melo
2011-04-01 17:11               ` David Ahern
2011-04-01 20:20                 ` Peter Zijlstra
2011-04-06 12:15                 ` Frederic Weisbecker
2011-04-06 14:09                   ` Arnaldo Carvalho de Melo
2011-04-06 14:15                     ` Peter Zijlstra
2011-04-06 14:30                       ` Frederic Weisbecker
2011-04-06 14:34                         ` David Ahern
2011-04-06 14:43                           ` Frederic Weisbecker
2011-04-06 14:42                       ` Frederic Weisbecker
2011-04-06 14:55                     ` Frederic Weisbecker
2011-04-06 17:18                       ` Arnaldo Carvalho de Melo
2011-04-04 10:00               ` Akihiro Nagai
2011-04-06 12:52                 ` Frederic Weisbecker
2011-04-11  4:54                   ` Akihiro Nagai
2011-03-24 11:32 ` [PATCH -tip v3 4/6] perf branch trace: print file path of the executed elf Akihiro Nagai
2011-03-24 11:32 ` [PATCH -tip v3 5/6] perf branch trace: print function+offset Akihiro Nagai
2011-03-24 11:32 ` [PATCH -tip v3 6/6] perf branch trace: add print all option Akihiro Nagai
2011-03-30 14:46 ` [PATCH -tip v3 0/6] perf: Introduce branch sub commands Frederic Weisbecker
2011-04-01 10:57   ` Akihiro Nagai
2011-04-01 12:51     ` Frederic Weisbecker
2011-04-01 14:43 ` Frederic Weisbecker
2011-04-04 10:06   ` Akihiro Nagai

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=4D906450.1040809@hitachi.com \
    --to=akihiro.nagai.hw@hitachi.com \
    --cc=2nddept-manager@sdl.hitachi.co.jp \
    --cc=acme@infradead.org \
    --cc=dsahern@gmail.com \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=masami.hiramatsu.pt@hitachi.com \
    --cc=mingo@elte.hu \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.org \
    /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