Re: [PATCH v4 15/25] perf stat: Filter out unmatched aggregation for hybrid event

From: Jiri Olsa
Date: Thu Apr 22 2021 - 06:26:42 EST


On Thu, Apr 22, 2021 at 11:10:54AM +0800, Jin, Yao wrote:
> Hi Jiri,
>
> On 4/22/2021 2:29 AM, Jiri Olsa wrote:
> > On Fri, Apr 16, 2021 at 10:05:07PM +0800, Jin Yao wrote:
> >
> > SNIP
> >
> > > diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
> > > index 5255d78b1c30..15eafd249e46 100644
> > > --- a/tools/perf/util/stat-display.c
> > > +++ b/tools/perf/util/stat-display.c
> > > @@ -643,6 +643,20 @@ static void aggr_cb(struct perf_stat_config *config,
> > > }
> > > }
> > > +static bool aggr_id_hybrid_matched(struct perf_stat_config *config,
> > > + struct evsel *counter, struct aggr_cpu_id id)
> > > +{
> > > + struct aggr_cpu_id s;
> > > +
> > > + for (int i = 0; i < evsel__nr_cpus(counter); i++) {
> > > + s = config->aggr_get_id(config, evsel__cpus(counter), i);
> > > + if (cpu_map__compare_aggr_cpu_id(s, id))
> > > + return true;
> > > + }
> > > +
> > > + return false;
> > > +}
> > > +
> > > static void print_counter_aggrdata(struct perf_stat_config *config,
> > > struct evsel *counter, int s,
> > > char *prefix, bool metric_only,
> > > @@ -656,6 +670,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
> > > double uval;
> > > ad.id = id = config->aggr_map->map[s];
> > > +
> > > + if (perf_pmu__has_hybrid() &&
> > > + !aggr_id_hybrid_matched(config, counter, id)) {
> > > + return;
> > > + }
> > > +
> > > ad.val = ad.ena = ad.run = 0;
> > > ad.nr = 0;
> > > if (!collect_data(config, counter, aggr_cb, &ad))
> >
> > there's same check in aggr_cb, so it seems like we could just make check in here:
> >
> > if (perf_pmu__has_hybrid() && ad.ena == 0)
> > return;
> >
> > without another extra loop
> >
> > jirka
> >
>
> I guess you recommended the patch like this:
>
> static void print_counter_aggrdata(struct perf_stat_config *config,
> struct evsel *counter, int s,
> char *prefix, bool metric_only,
> @@ -670,17 +656,14 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
> double uval;
>
> ad.id = id = config->aggr_map->map[s];
> ad.val = ad.ena = ad.run = 0;
> ad.nr = 0;
> if (!collect_data(config, counter, aggr_cb, &ad))
> return;
>
> + if (perf_pmu__has_hybrid() && ad.ena == 0)
> + return;
> +
> nr = ad.nr;
> ena = ad.ena;
> run = ad.run;
>
> Yes, it works. The test log is,

ok, great

thanks,
jirka

>
> # perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1
>
> Performance counter stats for 'system wide':
>
> S0-D0-C0 2 2,341,923 cpu_core/cycles/
> S0-D0-C4 2 1,707,933 cpu_core/cycles/
> S0-D0-C8 2 845,805 cpu_core/cycles/
> S0-D0-C12 2 1,001,961 cpu_core/cycles/
> S0-D0-C16 2 932,004 cpu_core/cycles/
> S0-D0-C20 2 1,778,603 cpu_core/cycles/
> S0-D0-C24 2 804,448 cpu_core/cycles/
> S0-D0-C28 2 178,360 cpu_core/cycles/
>
> 1.002264168 seconds time elapsed
>
> Thanks
> Jin Yao
>