From: Masami Hiramatsu <mhiramat@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>,
Masami Hiramatsu <mhiramat@kernel.org>,
bhargavb <bhargavaramudu@gmail.com>,
linux-kernel@vger.kernel.org,
Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>,
linux-rt-users@vger.kernel.org, linux-perf-users@vger.kernel.org
Subject: Re: [PATCH v2 2/5] perf-probe: Cut off the version suffix from event name
Date: Wed, 13 Dec 2017 00:02:55 +0900 [thread overview]
Message-ID: <20171213000255.8cc0e9a698eb97d6f7b0c579@kernel.org> (raw)
In-Reply-To: <20171211182547.GH3958@kernel.org>
On Mon, 11 Dec 2017 15:25:47 -0300
Arnaldo Carvalho de Melo <acme@kernel.org> wrote:
> Em Fri, Dec 08, 2017 at 08:49:46AM -0600, Paul Clarke escreveu:
> >
> >
> > On 12/07/2017 09:01 PM, Masami Hiramatsu wrote:
> > > On Thu, 7 Dec 2017 10:34:51 -0600
> > > Paul Clarke <pc@us.ibm.com> wrote:
> > >> On 12/07/2017 01:20 AM, Masami Hiramatsu wrote:
> > >>> Cut off the version suffix (e.g. @GLIBC_2.2.5 etc.) from
> > >>> automatic generated event name. This fixes wildcard event
> > >>> adding like below case;
> > >>>
> > >>> =====
> > >>> # perf probe -x /lib64/libc-2.25.so malloc*
> > >>> Internal error: "malloc_get_state@GLIBC_2" is wrong event name.
> > >>> Error: Failed to add events.
> > >>> =====
> > >>>
> > >>> This failure was caused by a versioned suffix symbol.
> > >>> With this fix, perf probe automatically cuts the
> > >>> suffix after @ as below.
> > >>>
> > >>> =====
> > >>> # ./perf probe -x /lib64/libc-2.25.so malloc*
> > >>> Added new events:
> > >>> probe_libc:malloc_printerr (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_consolidate (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_check (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_hook_ini (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_trim (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_usable_size (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_stats (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_info (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:mallochook (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_get_state (on malloc* in /usr/lib64/libc-2.25.so)
> > >>> probe_libc:malloc_set_state (on malloc* in /usr/lib64/libc-2.25.so)
> > >>>
> > >>> You can now use it in all perf tools, such as:
> > >>>
> > >>> perf record -e probe_libc:malloc_set_state -aR sleep 1
> > >>>
> > >>> =====
> > >>
> > >> I think this will still fall over for a case where there are multiple versions of the same base symbol, like:
> > >>
> > >> $ nm /lib64/libc.so.6 | egrep ' sched_getaffinity'
> > >> 0000000000134430 T sched_getaffinity@GLIBC_2.3.3
> > >> 00000000000dcf00 T sched_getaffinity@@GLIBC_2.3.4
> > >
> > > No, in that case perf probe adds number suffix (_1, _2...) for new events :)
> > >
> > > This feature (number suffix) is anyway required for the case that inlined
> > > function is spreaded in multiple places. I think this is natural for perf probe.
> >
> > I can live with that.
> >
> > Is the versioning tag retained for display with "perf probe -l" display, so the probe points can be distinguished?
> >
> > In other words, will one see:
> > # perf probe -l
> > probe_libc:sched_getaffinity (on sched_getaffinity@GLIBC_2.3.3 in /usr/lib64/libc-2.17.so)
> > probe_libc:sched_getaffinity_1 (on sched_getaffinity@@GLIBC_2.3.4 in /usr/lib64/libc-2.17.so)
> > or
> > # perf probe -l
> > probe_libc:sched_getaffinity (on sched_getaffinity in /usr/lib64/libc-2.17.so)
> > probe_libc:sched_getaffinity_1 (on sched_getaffinity in /usr/lib64/libc-2.17.so)
>
> [root@jouet ~]# perf probe -x /lib64/libc-2.25.so malloc*
> Added new events:
> probe_libc:malloc_printerr (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_consolidate (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_check (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_hook_ini (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_trim (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_usable_size (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_stats (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_info (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:mallochook (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_get_state (on malloc* in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_set_state (on malloc* in /usr/lib64/libc-2.25.so)
>
> You can now use it in all perf tools, such as:
>
> perf record -e probe_libc:malloc_set_state -aR sleep 1
>
> [root@jouet ~]# perf probe -l
> probe_libc:malloc (on 0xd22a6973 in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_check (on 0x25db6f5a in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_consolidate (on 0x88f7c44a in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_get_state (on 0xdd38eca7 in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_hook_ini (on 0x8de2b533 in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_info (on 0x8b327bde in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_printerr (on 0x8fff087c in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_set_state (on 0x861940e6 in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_stats (on 0x51fa3cdc in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_trim (on 0xa9fa4e43 in /usr/lib64/libc-2.25.so)
> probe_libc:malloc_usable_size (on 0xceb5e090 in /usr/lib64/libc-2.25.so)
> probe_libc:mallochook (on 0x6ebc00f5 in /usr/lib64/libc-2.25.so)
This looks something wrong. perf-probe should try to get symbol
at least. What happened on that ? Could you run perf probe -l with -vv ?
On my Fedora26,
$ sudo ./perf probe -l
probe_libc:malloc (on __malloc in /usr/lib64/libc-2.25.so)
probe_libc:malloc_check (on malloc_check in /usr/lib64/libc-2.25.so)
probe_libc:malloc_consolidate (on malloc_consolidate.part.1 in /usr/lib64/libc-2.25.so)
probe_libc:malloc_get_state (on malloc_get_state@GLIBC_2.2.5 in /usr/lib64/libc-2.25.so)
probe_libc:malloc_hook_ini (on malloc_hook_ini in /usr/lib64/libc-2.25.so)
probe_libc:malloc_info (on __malloc_info in /usr/lib64/libc-2.25.so)
probe_libc:malloc_printerr (on malloc_printerr in /usr/lib64/libc-2.25.so)
probe_libc:malloc_set_state (on malloc_set_state@GLIBC_2.2.5 in /usr/lib64/libc-2.25.so)
probe_libc:malloc_stats (on __malloc_stats in /usr/lib64/libc-2.25.so)
probe_libc:malloc_trim (on __malloc_trim in /usr/lib64/libc-2.25.so)
probe_libc:malloc_usable_size (on __malloc_usable_size in /usr/lib64/libc-2.25.so)
probe_libc:mallochook (on mallochook in /usr/lib64/libc-2.25.so)
I can see the symbols with version suffixes.
> [root@jouet ~]#
>
> [acme@jouet perf]$ nm /lib64/libc-2.25.so | grep malloc_get_state
> 0000000000151ba0 T malloc_get_state@GLIBC_2.2.5
> [acme@jouet perf]$
>
> For your example it finds two symbols, adds two but I couldn't find a
> simple way of mapping one to the other, would be nice if 'perf probe -l'
> showed them like 'nm' does.
>
> [root@jouet ~]# nm /lib64/libc-2.25.so | grep ' sched_getaffinity'
> 0000000000151cd0 T sched_getaffinity@GLIBC_2.3.3
> 00000000000f3c10 T sched_getaffinity@@GLIBC_2.3.4
> [root@jouet ~]#
>
> [root@jouet ~]# perf probe -x /lib64/libc-2.25.so sched_getaffinity*
> Added new events:
> probe_libc:sched_getaffinity (on sched_getaffinity* in /usr/lib64/libc-2.25.so)
> probe_libc:sched_getaffinity_1 (on sched_getaffinity* in /usr/lib64/libc-2.25.so)
>
> You can now use it in all perf tools, such as:
>
> perf record -e probe_libc:sched_getaffinity_1 -aR sleep 1
>
> [root@jouet ~]# perf probe -l
> probe_libc:sched_getaffinity (on 0x5fd95e7c in /usr/lib64/libc-2.25.so)
> probe_libc:sched_getaffinity_1 (on 0xd8d51601 in /usr/lib64/libc-2.25.so)
> [root@jouet ~]#
This case also shows
$ sudo ./perf probe -l
probe_libc:sched_getaffinity (on __sched_getaffinity_new in /usr/lib64/libc-2.25.so)
probe_libc:sched_getaffinity_1 (on sched_getaffinity@GLIBC_2.3.3 in /usr/lib64/libc-2.25.so)
(but the first one seems a bit different, maybe it is an alias of sched_getaffinity@<some new version>.)
Thank you,
--
Masami Hiramatsu <mhiramat@kernel.org>
next prev parent reply other threads:[~2017-12-12 15:03 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-07 7:19 [PATCH v2 0/5] perf-probe: Improve probing on versioned symbols Masami Hiramatsu
2017-12-07 7:19 ` [PATCH v2 1/5] perf-probe: Add warning message if there is unexpected event name Masami Hiramatsu
2017-12-07 15:53 ` Arnaldo Carvalho de Melo
2017-12-08 2:48 ` Masami Hiramatsu
2017-12-07 7:20 ` [PATCH v2 2/5] perf-probe: Cut off the version suffix from " Masami Hiramatsu
2017-12-07 16:34 ` Paul Clarke
2017-12-08 3:01 ` Masami Hiramatsu
2017-12-08 14:49 ` Paul Clarke
2017-12-08 16:12 ` Masami Hiramatsu
2017-12-11 18:25 ` Arnaldo Carvalho de Melo
2017-12-12 15:02 ` Masami Hiramatsu [this message]
2017-12-07 16:56 ` Arnaldo Carvalho de Melo
2017-12-07 17:24 ` Paul Clarke
2017-12-07 17:55 ` Arnaldo Carvalho de Melo
2017-12-08 3:15 ` Masami Hiramatsu
2017-12-07 7:20 ` [PATCH v2 3/5] perf-probe: Add __return suffix for return events Masami Hiramatsu
2017-12-07 7:21 ` [PATCH v2 4/5] perf-probe: Find versioned symbols from map Masami Hiramatsu
2017-12-08 11:08 ` Thomas-Mich Richter
2017-12-08 14:22 ` Masami Hiramatsu
2017-12-07 7:21 ` [PATCH v2 5/5] perf-probe: Support escaped character in parser Masami Hiramatsu
2017-12-08 11:45 ` Thomas-Mich Richter
2017-12-08 15:54 ` Masami Hiramatsu
2017-12-07 12:47 ` [PATCH v2 0/5] perf-probe: Improve probing on versioned symbols Ravi Bangoria
2017-12-08 16:24 ` Masami Hiramatsu
2017-12-08 17:13 ` Ravi Bangoria
2017-12-08 11:56 ` Thomas-Mich Richter
2017-12-08 16:12 ` Masami Hiramatsu
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=20171213000255.8cc0e9a698eb97d6f7b0c579@kernel.org \
--to=mhiramat@kernel.org \
--cc=acme@kernel.org \
--cc=bhargavaramudu@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=pc@us.ibm.com \
--cc=ravi.bangoria@linux.vnet.ibm.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).