Re: [PATCH 1/4] perf, tools: Output running time and run/enabled ratio in CSV mode
From: Jiri Olsa
Date: Mon Mar 09 2015 - 03:50:22 EST
On Sun, Mar 08, 2015 at 04:55:21PM -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@xxxxxxxxxxxxxxx>
>
> The information how much a counter ran in perf stat can be quite
> interesting for other tools to judge how trustworthy a measurement is.
>
> Currently it is only output in non CSV mode.
>
> This patches make perf stat always output the running time and the
> enabled/running ratio in CSV mode.
>
> This adds two new fields at the end for each line. I assume that existing
> tools ignore new fields at the end, so it's on by default.
>
> Only CSV mode is affected, no difference otherwise.
hum, so people using CSV mode will now see extra 2 numbers
at the end of the line:
$ ./perf.old stat -x, -e cycles ls > /dev/null
2679161,,cycles
$ ./perf stat -x, -e cycles ls > /dev/null
2574169,,cycles,1295544,100.00
we could be breaking existing scripts..
you recently added 'running-time' option for record,
could you please add same option for stat?
plus 2 nits below
thanks,
jirka
>
> v2: Add extra print_running function
> v3: Avoid printing nan
> Reviewed-by: Jiri Olsa <jolsa@xxxxxxxxxx>
> Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
> ---
> tools/perf/builtin-stat.c | 36 ++++++++++++++++++++++++------------
> 1 file changed, 24 insertions(+), 12 deletions(-)
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index d28949d..5d0c6ea 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -769,6 +769,16 @@ static int run_perf_stat(int argc, const char **argv)
> return ret;
> }
>
> +static void print_running(u64 run, u64 ena)
> +{
> + if (csv_output)
> + fprintf(output, "%s%" PRIu64 "%s%.2f",
> + csv_sep,
> + run,
> + csv_sep,
> + ena ? 100.0 * run / ena : 100.0);
nit - need { } for multiplne lines 'if' leg
> +}
> +
> static void print_noise_pct(double total, double avg)
> {
> double pct = rel_stddev_stats(total, avg);
> @@ -1252,6 +1262,7 @@ static void print_aggr(char *prefix)
> fprintf(output, "%s%s",
> csv_sep, counter->cgrp->name);
>
> + print_running(run, ena);
> fputc('\n', output);
> continue;
> }
> @@ -1268,6 +1279,8 @@ static void print_aggr(char *prefix)
> if (run != ena)
> fprintf(output, " (%.2f%%)",
> 100.0 * run / ena);
> + } else {
> + print_running(run, ena);
> }
we already have 'csv_output' check in print_running
> fputc('\n', output);
> }
> @@ -1284,6 +1297,10 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
> double avg = avg_stats(&ps->res_stats[0]);
> int scaled = counter->counts->scaled;
> double uval;
> + double avg_enabled, avg_running;
> +
> + avg_enabled = avg_stats(&ps->res_stats[1]);
> + avg_running = avg_stats(&ps->res_stats[2]);
>
> if (prefix)
> fprintf(output, "%s", prefix);
> @@ -1303,6 +1320,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
> if (counter->cgrp)
> fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
>
> + print_running(avg_running, avg_enabled);
> fputc('\n', output);
> return;
> }
> @@ -1316,19 +1334,9 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
>
> print_noise(counter, avg);
>
> - if (csv_output) {
> - fputc('\n', output);
> - return;
> - }
> -
> - if (scaled) {
> - double avg_enabled, avg_running;
> -
> - avg_enabled = avg_stats(&ps->res_stats[1]);
> - avg_running = avg_stats(&ps->res_stats[2]);
> -
> + print_running(avg_running, avg_enabled);
> + if (!csv_output)
> fprintf(output, " [%5.2f%%]", 100 * avg_running / avg_enabled);
> - }
> fprintf(output, "\n");
> }
>
> @@ -1370,6 +1378,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
> fprintf(output, "%s%s",
> csv_sep, counter->cgrp->name);
>
> + print_running(run, ena);
> fputc('\n', output);
> continue;
> }
> @@ -1387,7 +1396,10 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
> if (run != ena)
> fprintf(output, " (%.2f%%)",
> 100.0 * run / ena);
> + } else {
> + print_running(run, ena);
> }
same here
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/