linux-kernel - Re: [PATCH v5 3/7] perf/sdt: Directly record SDT events with 'perf record'

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 15 Mar 2017 19:19:11 +0530
From:   Ravi Bangoria <ravi.bangoria@...ux.vnet.ibm.com>
To:     Arnaldo Carvalho de Melo <acme@...nel.org>,
        Jiri Olsa <jolsa@...hat.com>
Cc:     mingo@...hat.com, mhiramat@...nel.org, brendan.d.gregg@...il.com,
        peterz@...radead.org, alexander.shishkin@...ux.intel.com,
        wangnan0@...wei.com, jolsa@...nel.org, ak@...ux.intel.com,
        treeze.taeung@...il.com, mathieu.poirier@...aro.org,
        hekuang@...wei.com, sukadev@...ux.vnet.ibm.com, ananth@...ibm.com,
        naveen.n.rao@...ux.vnet.ibm.com, adrian.hunter@...el.com,
        linux-kernel@...r.kernel.org, hemant@...ux.vnet.ibm.com,
        Ravi Bangoria <ravi.bangoria@...ux.vnet.ibm.com>
Subject: Re: [PATCH v5 3/7] perf/sdt: Directly record SDT events with 'perf
 record'



On Wednesday 15 March 2017 06:46 PM, Arnaldo Carvalho de Melo wrote:
> Em Wed, Mar 15, 2017 at 01:03:31PM +0100, Jiri Olsa escreveu:
>> On Tue, Mar 14, 2017 at 08:36:54PM +0530, Ravi Bangoria wrote:
>>> +++ b/tools/perf/builtin-record.c
>>> +static int record__parse_events_option(const struct option *opt,
>>> +				       const char *str,
>>> +				       int unset)
>>> +{
>>> +	if (is_sdt_event((char *) str))
>>> +		return parse_sdt_events_option(opt, str, unset);
>>> +	else
>>> +		return parse_events_option(opt, str, unset);
>> so what happens if there're more than one event in 'str' like:
>>   -e cycles,std_...
>>
>> would it be better to plug this directly into parse-events.y
>> parser.. and handle it like any other event type?
> Yeah, I went to bed thinking about this :-) 
>
> Ravi,
>
> 	Please test something like:
>
>    perf record -e cycles,sdt_glib:mem__alloc,sched:*switch -a sleep 5s

Thanks Jiri, Arnaldo,

Yeah, this is failing :)

  $ sudo ./perf record -a -e sdt_libpthread:mutex_release,sced:*switch
    Error: sdt_libpthread:mutex_release,sched:*switch not found in the cache
    invalid or unsupported event: 'sdt_libpthread:mutex_release,sched:*switch'

Actually I tested with 'perf record -e ev1 -e ev2', but in this case
record__parse_events_option will get called separately for each
individual event.

Anyway, I'll fix this in next version.

Thanks for the review,
Ravi