[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <597B3C92.7020607@versatic.net>
Date: Fri, 28 Jul 2017 09:30:58 -0400
From: Genevieve Bastien <gbastien@...satic.net>
To: Jiri Olsa <jolsa@...hat.com>
CC: linux-kernel@...r.kernel.org,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Julien Desfossez <jdesfossez@...icios.com>,
Francis Deslauriers <francis.deslauriers@...icios.com>,
Jiri Olsa <jolsa@...nel.org>
Subject: Re: [PATCH 1/3] perf tools: Add callchain to ctf conversion
On 07/28/2017 05:25 AM, Jiri Olsa wrote:
> On Thu, Jul 27, 2017 at 02:12:03PM -0400, Geneviève Bastien wrote:
>> The field perf_callchain, if available, is added to the sampling
>> events during the CTF conversion. It is an array of u64 values.
>> The perf_callchain_size field contains the size of the array.
>>
>> It will allow the analysis of sampling data in trace visualization tools
>> like Trace Compass. Possible analyses with those data: dynamic
>> flamegraphs, correlation with other tracing data like a userspace trace.
>>
>> Here follows a babeltrace CTF output of a trace with callchain:
>>
>> $ babeltrace ./myctftrace
>> [17:38:45.672760285] (+?.?????????) cycles:ppp: { cpu_id = 0 }, { perf_ip = 0xFFFFFFFF81063EE4, perf_tid = 25841, perf_pid = 25774, perf_period = 1, perf_callchain_size = 7, perf_callchain = [ [0] = 0xFFFFFFFFFFFFFF80, [1] = 0xFFFFFFFF81063EE4, [2] = 0xFFFFFFFF8100C770, [3] = 0xFFFFFFFF81006EC6, [4] = 0xFFFFFFFF8118245E, [5] = 0xFFFFFFFF810A9224, [6] = 0xFFFFFFFF8164A4C6 ] }
>> [17:38:45.672777672] (+0.000017387) cycles:ppp: { cpu_id = 0 }, { perf_ip = 0xFFFFFFFF81063EE4, perf_tid = 25841, perf_pid = 25774, perf_period = 1, perf_callchain_size = 8, perf_callchain = [ [0] = 0xFFFFFFFFFFFFFF80, [1] = 0xFFFFFFFF81063EE4, [2] = 0xFFFFFFFF8100C770, [3] = 0xFFFFFFFF81006EC6, [4] = 0xFFFFFFFF8118245E, [5] = 0xFFFFFFFF810A9224, [6] = 0xFFFFFFFF8164A4C6, [7] = 0xFFFFFFFF8164ABAD ] }
>> [17:38:45.672786700] (+0.000009028) cycles:ppp: { cpu_id = 0 }, { perf_ip = 0xFFFFFFFF81063EE4, perf_tid = 25841, perf_pid = 25774, perf_period = 70, perf_callchain_size = 3, perf_callchain = [ [0] = 0xFFFFFFFFFFFFFF80, [1] = 0xFFFFFFFF81063EE4, [2] = 0xFFFFFFFF8100C770 ] }
> missing one more hunk (attached) ;-)
>
> I guess there's no need to resend, Arnaldo could remove it,
> anyway for patchset:
>
> Acked-by: Jiri Olsa <jolsa@...nel.org>
Thanks Jiri,
> Is there already tracecompas change to display callchains and mmaps?
Almost, it is still a patch on gerrit [1] and missing a few features,
like symbol resolution, but we plan to have it released in the coming weeks.
Regards,
Geneviève
[1] https://git.eclipse.org/r/#/c/102015/
>
> thanks,
> jirka
>
>
> ---
> diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
> index c47b0943ef88..2346cecb8ea2 100644
> --- a/tools/perf/util/data-convert-bt.c
> +++ b/tools/perf/util/data-convert-bt.c
> @@ -596,7 +596,6 @@ static int add_generic_values(struct ctf_writer *cw,
> * PERF_SAMPLE_TIME - not needed as we have it in
> * ctf event header
> * PERF_SAMPLE_READ - TODO
> - * PERF_SAMPLE_CALLCHAIN - TODO
> * PERF_SAMPLE_RAW - tracepoint fields are handled separately
> * PERF_SAMPLE_BRANCH_STACK - TODO
> * PERF_SAMPLE_REGS_USER - TODO
Powered by blists - more mailing lists