Re: [RFC/PATCH v2] perf data: Add stat subcommand to show sample event stat

[Andi Kleen <andi@firstfloor.org>]

On Wed, May 13, 2015 at 09:05:22PM +0900, Namhyung Kim wrote:
> Hi Andi,
> 
> On Mon, May 11, 2015 at 05:44:05PM +0200, Andi Kleen wrote:
> > > The sampling ratio was useful for me to determine how often the event
> > > was sampled - in this case the cpu cycles event was only sampled at 12%
> > 
> > That's dangerous to determine without a plot. It could be that it was bimodal: 
> > 100% busy and then idle. You may want to add something like the spark
> > plots I submitted for stat some time ago.
> 
> Right, we cannot know the exact situation from a single number.  But
> it was okay for me just to see overall status from the number.  This
> is what we cannot know from the output of 'perf report' easily, so I'd
> like to add this info in some way.
> 
> Anyway, I wrote a script to plot the number of samples and periods
> using python's matplotlib package.  Maybe we can add it to the script
> database.

Looks good. Yes it would be useful to have in the database.

-Andi

> 
> Thanks,
> Namhyung
> 
> 
> /* sample-chart.py */
> import os
> import sys
> import numpy as np
> import matplotlib.pyplot as plt
> 
> sys.path.append(os.environ['PERF_EXEC_PATH'] + \
>         '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
> 
> from perf_trace_context import *
> from EventClass import *
> 
> events = {}
> mode = None  # 'cpu' or 'task'
> nr_events = 0
> first_time = 0
> last_time = 0
> 
> def trace_begin():
>     pass
> 
> def trace_end():
>     xcnt = last_time - first_time + 1
>     xpos = np.arange(xcnt)
>     times = np.arange(first_time, last_time + 1)
> 
>     fig, plt_array = plt.subplots(nrows = nr_events, ncols = 2)
>     fig.suptitle("Event stat", fontsize=20)
> 
>     n = 0
>     for e in events:
>         p1 = plt_array[n][0]
>         p2 = plt_array[n][1]
>         for k in events[e]:  # key = cpu or tid
>             ev_stats = events[e][k]
> 
>             samples = np.zeros(xcnt)
>             periods = np.zeros(xcnt)
>             for t in ev_stats:
>                 samples[t - first_time] = ev_stats[t][0]
>                 periods[t - first_time] = ev_stats[t][1]
> 
>             key = "%s %d" % (mode, k)
> 
>             p1.plot(times, samples, 'o', linewidth=2, label=key)
>             p2.plot(times, periods, '-', linewidth=2, label=key)
> 
>         expect = 400 * np.ones(xcnt)
>         p1.plot(times, expect, '--')
> 
>         p1.set_title("Number of samples in '%s'" % e)
>         p1.legend()
>         p2.set_title("Event values in '%s'" % e)
>         p2.legend()
>         n += 1
> 
>     plt.show()
> 
> def process_event(param_dict):
>     evt  = param_dict["ev_name"]
>     cpu  = param_dict["sample"]["cpu"]
>     tid  = param_dict["sample"]["tid"]
>     time = param_dict["sample"]["time"] / 100000000  # 100 ms
>     val  = param_dict["sample"]["period"]
> 
>     if evt not in events:
>         global nr_events
>         nr_events += 1
>         events[evt] = {}
> 
>     global mode
>     if mode is None:
>         if cpu >= 10000000:
>             mode = 'task'
>         else:
>             mode = 'cpu'
> 
>     key = cpu if mode == 'cpu' else tid
>     if key not in events[evt]:
>         events[evt][key] = {}
> 
>     global first_time, last_time
>     if first_time == 0 or first_time > time:
>         first_time = time
>     if last_time < time:
>         last_time = time
> 
>     ev_stat = events[evt][key]
>     if time not in ev_stat:
>         ev_stat[time] = [0, 0]  # (nr_sample, period)
>     ev_stat[time][0] += 1
>     ev_stat[time][1] += val
> 
> def trace_unhandled(event_name, context, event_fields_dict):
>     pass
> 

-- 
ak@linux.intel.com -- Speaking for myself only.