Per-thread aggregation doesn't use the CPU numbers but the logic should
be the same. Initialize cpu_aggr_map separately for AGGR_THREAD and use
thread map idx to aggregate counter values.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/builtin-stat.c | 31 +++++++++++++++++++++++++++++++
tools/perf/util/stat.c | 19 +++++++++++++++++++
2 files changed, 50 insertions(+)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 139e35ed68d3..c76240cfc635 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1468,6 +1468,21 @@ static int perf_stat_init_aggr_mode(void)
stat_config.aggr_get_id = aggr_mode__get_id(stat_config.aggr_mode);
}
+ if (stat_config.aggr_mode == AGGR_THREAD) {
+ nr = perf_thread_map__nr(evsel_list->core.threads);
+ stat_config.aggr_map = cpu_aggr_map__empty_new(nr);
+ if (stat_config.aggr_map == NULL)
+ return -ENOMEM;
+
+ for (int s = 0; s < nr; s++) {
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
+
+ id.thread_idx = s;
+ stat_config.aggr_map->map[s] = id;
+ }
+ return 0;
+ }
+
/*
* The evsel_list->cpus is the base we operate on,
* taking the highest cpu number to be the size of
@@ -1677,6 +1692,22 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode);
bool needs_sort = stat_config.aggr_mode != AGGR_NONE;
+ if (stat_config.aggr_mode == AGGR_THREAD) {
+ int nr = perf_thread_map__nr(evsel_list->core.threads);
+
+ stat_config.aggr_map = cpu_aggr_map__empty_new(nr);
+ if (stat_config.aggr_map == NULL)
+ return -ENOMEM;
+
+ for (int s = 0; s < nr; s++) {
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
+
+ id.thread_idx = s;
+ stat_config.aggr_map->map[s] = id;
+ }
+ return 0;
+ }
+
if (!get_id)
return 0;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 99874254809d..013dbe1c5d28 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -403,6 +403,24 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
+ if (config->aggr_mode == AGGR_THREAD) {
+ struct perf_counts_values *aggr_counts = &ps->aggr[thread].counts;
+
+ /*
+ * Skip value 0 when enabling --per-thread globally,
+ * otherwise too many 0 output.
+ */
+ if (count->val == 0 && config->system_wide)
+ return 0;
+
+ ps->aggr[thread].nr++;
+
+ aggr_counts->val += count->val;
+ aggr_counts->ena += count->ena;
+ aggr_counts->run += count->run;
+ goto update;
+ }
+
if (ps->aggr) {
struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx);
struct aggr_cpu_id aggr_id = config->aggr_get_id(config, cpu);
@@ -437,6 +455,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
}
}
+update:
switch (config->aggr_mode) {
case AGGR_THREAD:
case AGGR_CORE:
--
2.38.0.rc1.362.ged0d419d3c-googOn Sun, Oct 9, 2022 at 10:36 PM Namhyung Kim <namhyung@kernel.org> wrote:
>
> Per-thread aggregation doesn't use the CPU numbers but the logic should
> be the same. Initialize cpu_aggr_map separately for AGGR_THREAD and use
> thread map idx to aggregate counter values.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> tools/perf/builtin-stat.c | 31 +++++++++++++++++++++++++++++++
> tools/perf/util/stat.c | 19 +++++++++++++++++++
> 2 files changed, 50 insertions(+)
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 139e35ed68d3..c76240cfc635 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -1468,6 +1468,21 @@ static int perf_stat_init_aggr_mode(void)
> stat_config.aggr_get_id = aggr_mode__get_id(stat_config.aggr_mode);
> }
>
> + if (stat_config.aggr_mode == AGGR_THREAD) {
> + nr = perf_thread_map__nr(evsel_list->core.threads);
> + stat_config.aggr_map = cpu_aggr_map__empty_new(nr);
> + if (stat_config.aggr_map == NULL)
> + return -ENOMEM;
> +
> + for (int s = 0; s < nr; s++) {
> + struct aggr_cpu_id id = aggr_cpu_id__empty();
> +
> + id.thread_idx = s;
> + stat_config.aggr_map->map[s] = id;
> + }
> + return 0;
> + }
> +
> /*
> * The evsel_list->cpus is the base we operate on,
> * taking the highest cpu number to be the size of
> @@ -1677,6 +1692,22 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
> aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode);
> bool needs_sort = stat_config.aggr_mode != AGGR_NONE;
>
> + if (stat_config.aggr_mode == AGGR_THREAD) {
> + int nr = perf_thread_map__nr(evsel_list->core.threads);
> +
> + stat_config.aggr_map = cpu_aggr_map__empty_new(nr);
> + if (stat_config.aggr_map == NULL)
> + return -ENOMEM;
> +
> + for (int s = 0; s < nr; s++) {
> + struct aggr_cpu_id id = aggr_cpu_id__empty();
> +
> + id.thread_idx = s;
> + stat_config.aggr_map->map[s] = id;
> + }
> + return 0;
> + }
> +
> if (!get_id)
> return 0;
>
> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> index 99874254809d..013dbe1c5d28 100644
> --- a/tools/perf/util/stat.c
> +++ b/tools/perf/util/stat.c
> @@ -403,6 +403,24 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
> perf_counts_values__scale(count, config->scale, NULL);
>
> + if (config->aggr_mode == AGGR_THREAD) {
> + struct perf_counts_values *aggr_counts = &ps->aggr[thread].counts;
> +
> + /*
> + * Skip value 0 when enabling --per-thread globally,
> + * otherwise too many 0 output.
> + */
> + if (count->val == 0 && config->system_wide)
> + return 0;
> +
> + ps->aggr[thread].nr++;
> +
> + aggr_counts->val += count->val;
> + aggr_counts->ena += count->ena;
> + aggr_counts->run += count->run;
> + goto update;
nit: perhaps there is a more intention revealing name than update here.
Acked-by: Ian Rogers <irogers@google.com>
Thanks,
Ian
> + }
> +
> if (ps->aggr) {
> struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx);
> struct aggr_cpu_id aggr_id = config->aggr_get_id(config, cpu);
> @@ -437,6 +455,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> }
> }
>
> +update:
> switch (config->aggr_mode) {
> case AGGR_THREAD:
> case AGGR_CORE:
> --
> 2.38.0.rc1.362.ged0d419d3c-goog
>
On Mon, Oct 10, 2022 at 4:17 PM Ian Rogers <irogers@google.com> wrote:
>
> On Sun, Oct 9, 2022 at 10:36 PM Namhyung Kim <namhyung@kernel.org> wrote:
> >
> > Per-thread aggregation doesn't use the CPU numbers but the logic should
> > be the same. Initialize cpu_aggr_map separately for AGGR_THREAD and use
> > thread map idx to aggregate counter values.
> >
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> > tools/perf/builtin-stat.c | 31 +++++++++++++++++++++++++++++++
> > tools/perf/util/stat.c | 19 +++++++++++++++++++
> > 2 files changed, 50 insertions(+)
> >
> > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> > index 139e35ed68d3..c76240cfc635 100644
> > --- a/tools/perf/builtin-stat.c
> > +++ b/tools/perf/builtin-stat.c
> > @@ -1468,6 +1468,21 @@ static int perf_stat_init_aggr_mode(void)
> > stat_config.aggr_get_id = aggr_mode__get_id(stat_config.aggr_mode);
> > }
> >
> > + if (stat_config.aggr_mode == AGGR_THREAD) {
> > + nr = perf_thread_map__nr(evsel_list->core.threads);
> > + stat_config.aggr_map = cpu_aggr_map__empty_new(nr);
> > + if (stat_config.aggr_map == NULL)
> > + return -ENOMEM;
> > +
> > + for (int s = 0; s < nr; s++) {
> > + struct aggr_cpu_id id = aggr_cpu_id__empty();
> > +
> > + id.thread_idx = s;
> > + stat_config.aggr_map->map[s] = id;
> > + }
> > + return 0;
> > + }
> > +
> > /*
> > * The evsel_list->cpus is the base we operate on,
> > * taking the highest cpu number to be the size of
> > @@ -1677,6 +1692,22 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
> > aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode);
> > bool needs_sort = stat_config.aggr_mode != AGGR_NONE;
> >
> > + if (stat_config.aggr_mode == AGGR_THREAD) {
> > + int nr = perf_thread_map__nr(evsel_list->core.threads);
> > +
> > + stat_config.aggr_map = cpu_aggr_map__empty_new(nr);
> > + if (stat_config.aggr_map == NULL)
> > + return -ENOMEM;
> > +
> > + for (int s = 0; s < nr; s++) {
> > + struct aggr_cpu_id id = aggr_cpu_id__empty();
> > +
> > + id.thread_idx = s;
> > + stat_config.aggr_map->map[s] = id;
> > + }
> > + return 0;
> > + }
> > +
> > if (!get_id)
> > return 0;
> >
> > diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> > index 99874254809d..013dbe1c5d28 100644
> > --- a/tools/perf/util/stat.c
> > +++ b/tools/perf/util/stat.c
> > @@ -403,6 +403,24 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> > evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
> > perf_counts_values__scale(count, config->scale, NULL);
> >
> > + if (config->aggr_mode == AGGR_THREAD) {
> > + struct perf_counts_values *aggr_counts = &ps->aggr[thread].counts;
> > +
> > + /*
> > + * Skip value 0 when enabling --per-thread globally,
> > + * otherwise too many 0 output.
> > + */
> > + if (count->val == 0 && config->system_wide)
> > + return 0;
> > +
> > + ps->aggr[thread].nr++;
> > +
> > + aggr_counts->val += count->val;
> > + aggr_counts->ena += count->ena;
> > + aggr_counts->run += count->run;
> > + goto update;
>
> nit: perhaps there is a more intention revealing name than update here.
thread_map_idx ? ;-) I think we need to rename it separately.
>
> Acked-by: Ian Rogers <irogers@google.com>
Thanks,
Namhyung
>
> > + }
> > +
> > if (ps->aggr) {
> > struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx);
> > struct aggr_cpu_id aggr_id = config->aggr_get_id(config, cpu);
> > @@ -437,6 +455,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> > }
> > }
> >
> > +update:
> > switch (config->aggr_mode) {
> > case AGGR_THREAD:
> > case AGGR_CORE:
> > --
> > 2.38.0.rc1.362.ged0d419d3c-goog
> >
© 2016 - 2026 Red Hat, Inc.