Add a logic to aggregate counter values to the new evsel->stats->aggr.
This is not used yet so shadow stats are not updated. But later patch
will convert the existing code to use it.
With that, we don't need to handle AGGR_GLOBAL specially anymore. It
can use the same logic with counts, prev_counts and aggr_counts.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/builtin-stat.c | 3 --
tools/perf/util/evsel.c | 9 +---
.../scripting-engines/trace-event-python.c | 6 ---
tools/perf/util/stat.c | 46 ++++++++++++++++---
4 files changed, 41 insertions(+), 23 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index eaddafbd7ff2..139e35ed68d3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -963,9 +963,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
init_stats(&walltime_nsecs_stats);
update_stats(&walltime_nsecs_stats, t1 - t0);
- if (stat_config.aggr_mode == AGGR_GLOBAL)
- evlist__save_aggr_prev_raw_counts(evsel_list);
-
evlist__copy_prev_raw_counts(evsel_list);
evlist__reset_prev_raw_counts(evsel_list);
perf_stat__reset_shadow_per_stat(&rt_stat);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a6ea91c72659..a1fcb3166149 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1526,13 +1526,8 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread,
if (!evsel->prev_raw_counts)
return;
- if (cpu_map_idx == -1) {
- tmp = evsel->prev_raw_counts->aggr;
- evsel->prev_raw_counts->aggr = *count;
- } else {
- tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
- *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
- }
+ tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
+ *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
count->val = count->val - tmp.val;
count->ena = count->ena - tmp.ena;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 1f2040f36d4e..7bc8559dce6a 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1653,12 +1653,6 @@ static void python_process_stat(struct perf_stat_config *config,
struct perf_cpu_map *cpus = counter->core.cpus;
int cpu, thread;
- if (config->aggr_mode == AGGR_GLOBAL) {
- process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp,
- &counter->counts->aggr);
- return;
- }
-
for (thread = 0; thread < threads->nr; thread++) {
for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
process_stat(counter, perf_cpu_map__cpu(cpus, cpu),
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 374149628507..99874254809d 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -387,6 +387,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
struct perf_counts_values *count)
{
struct perf_counts_values *aggr = &evsel->counts->aggr;
+ struct perf_stat_evsel *ps = evsel->stats;
static struct perf_counts_values zero;
bool skip = false;
@@ -398,6 +399,44 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
if (skip)
count = &zero;
+ if (!evsel->snapshot)
+ evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
+ perf_counts_values__scale(count, config->scale, NULL);
+
+ 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);
+ struct perf_stat_aggr *ps_aggr;
+ int i;
+
+ for (i = 0; i < ps->nr_aggr; i++) {
+ if (!aggr_cpu_id__equal(&aggr_id, &config->aggr_map->map[i]))
+ continue;
+
+ ps_aggr = &ps->aggr[i];
+ ps_aggr->nr++;
+
+ /*
+ * When any result is bad, make them all to give
+ * consistent output in interval mode.
+ */
+ if (count->ena == 0 || count->run == 0 ||
+ evsel->counts->scaled == -1) {
+ ps_aggr->counts.val = 0;
+ ps_aggr->counts.ena = 0;
+ ps_aggr->counts.run = 0;
+ ps_aggr->failed = true;
+ }
+
+ if (!ps_aggr->failed) {
+ ps_aggr->counts.val += count->val;
+ ps_aggr->counts.ena += count->ena;
+ ps_aggr->counts.run += count->run;
+ }
+ break;
+ }
+ }
+
switch (config->aggr_mode) {
case AGGR_THREAD:
case AGGR_CORE:
@@ -405,9 +444,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
case AGGR_SOCKET:
case AGGR_NODE:
case AGGR_NONE:
- if (!evsel->snapshot)
- evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
- perf_counts_values__scale(count, config->scale, NULL);
if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
perf_stat__update_shadow_stats(evsel, count->val,
cpu_map_idx, &rt_stat);
@@ -469,10 +505,6 @@ int perf_stat_process_counter(struct perf_stat_config *config,
if (config->aggr_mode != AGGR_GLOBAL)
return 0;
- if (!counter->snapshot)
- evsel__compute_deltas(counter, -1, -1, aggr);
- perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
-
update_stats(&ps->res_stats, *count);
if (verbose > 0) {
--
2.38.0.rc1.362.ged0d419d3c-googOn Sun, Oct 9, 2022 at 10:36 PM Namhyung Kim <namhyung@kernel.org> wrote:
>
> Add a logic to aggregate counter values to the new evsel->stats->aggr.
> This is not used yet so shadow stats are not updated. But later patch
> will convert the existing code to use it.
>
> With that, we don't need to handle AGGR_GLOBAL specially anymore. It
> can use the same logic with counts, prev_counts and aggr_counts.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> tools/perf/builtin-stat.c | 3 --
> tools/perf/util/evsel.c | 9 +---
> .../scripting-engines/trace-event-python.c | 6 ---
> tools/perf/util/stat.c | 46 ++++++++++++++++---
> 4 files changed, 41 insertions(+), 23 deletions(-)
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index eaddafbd7ff2..139e35ed68d3 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -963,9 +963,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
> init_stats(&walltime_nsecs_stats);
> update_stats(&walltime_nsecs_stats, t1 - t0);
>
> - if (stat_config.aggr_mode == AGGR_GLOBAL)
> - evlist__save_aggr_prev_raw_counts(evsel_list);
> -
> evlist__copy_prev_raw_counts(evsel_list);
> evlist__reset_prev_raw_counts(evsel_list);
> perf_stat__reset_shadow_per_stat(&rt_stat);
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index a6ea91c72659..a1fcb3166149 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1526,13 +1526,8 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread,
> if (!evsel->prev_raw_counts)
> return;
>
> - if (cpu_map_idx == -1) {
> - tmp = evsel->prev_raw_counts->aggr;
> - evsel->prev_raw_counts->aggr = *count;
> - } else {
> - tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
> - *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
> - }
> + tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
> + *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
>
> count->val = count->val - tmp.val;
> count->ena = count->ena - tmp.ena;
> diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
> index 1f2040f36d4e..7bc8559dce6a 100644
> --- a/tools/perf/util/scripting-engines/trace-event-python.c
> +++ b/tools/perf/util/scripting-engines/trace-event-python.c
> @@ -1653,12 +1653,6 @@ static void python_process_stat(struct perf_stat_config *config,
> struct perf_cpu_map *cpus = counter->core.cpus;
> int cpu, thread;
>
> - if (config->aggr_mode == AGGR_GLOBAL) {
> - process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp,
> - &counter->counts->aggr);
> - return;
> - }
> -
> for (thread = 0; thread < threads->nr; thread++) {
> for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
> process_stat(counter, perf_cpu_map__cpu(cpus, cpu),
> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> index 374149628507..99874254809d 100644
> --- a/tools/perf/util/stat.c
> +++ b/tools/perf/util/stat.c
> @@ -387,6 +387,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> struct perf_counts_values *count)
> {
> struct perf_counts_values *aggr = &evsel->counts->aggr;
> + struct perf_stat_evsel *ps = evsel->stats;
> static struct perf_counts_values zero;
> bool skip = false;
>
> @@ -398,6 +399,44 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> if (skip)
> count = &zero;
>
> + if (!evsel->snapshot)
> + evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
> + perf_counts_values__scale(count, config->scale, NULL);
> +
> + 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);
> + struct perf_stat_aggr *ps_aggr;
> + int i;
> +
> + for (i = 0; i < ps->nr_aggr; i++) {
Would it be cleaner to have a helper function here that returns i or
ps_aggr for the first CPU being aggregated into? That would avoid the
continue/break.
> + if (!aggr_cpu_id__equal(&aggr_id, &config->aggr_map->map[i]))
> + continue;
> +
> + ps_aggr = &ps->aggr[i];
> + ps_aggr->nr++;
> +
> + /*
> + * When any result is bad, make them all to give
> + * consistent output in interval mode.
> + */
> + if (count->ena == 0 || count->run == 0 ||
> + evsel->counts->scaled == -1) {
> + ps_aggr->counts.val = 0;
> + ps_aggr->counts.ena = 0;
> + ps_aggr->counts.run = 0;
> + ps_aggr->failed = true;
> + }
> +
> + if (!ps_aggr->failed) {
> + ps_aggr->counts.val += count->val;
> + ps_aggr->counts.ena += count->ena;
> + ps_aggr->counts.run += count->run;
> + }
> + break;
> + }
> + }
> +
> switch (config->aggr_mode) {
> case AGGR_THREAD:
> case AGGR_CORE:
> @@ -405,9 +444,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> case AGGR_SOCKET:
> case AGGR_NODE:
> case AGGR_NONE:
> - if (!evsel->snapshot)
> - evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
> - perf_counts_values__scale(count, config->scale, NULL);
> if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
> perf_stat__update_shadow_stats(evsel, count->val,
> cpu_map_idx, &rt_stat);
> @@ -469,10 +505,6 @@ int perf_stat_process_counter(struct perf_stat_config *config,
> if (config->aggr_mode != AGGR_GLOBAL)
> return 0;
>
> - if (!counter->snapshot)
> - evsel__compute_deltas(counter, -1, -1, aggr);
> - perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
> -
It isn't clear to me how this relates to the patch.
Thanks,
Ian
> update_stats(&ps->res_stats, *count);
>
> if (verbose > 0) {
> --
> 2.38.0.rc1.362.ged0d419d3c-goog
>
On Mon, Oct 10, 2022 at 4:11 PM Ian Rogers <irogers@google.com> wrote:
>
> On Sun, Oct 9, 2022 at 10:36 PM Namhyung Kim <namhyung@kernel.org> wrote:
> >
> > Add a logic to aggregate counter values to the new evsel->stats->aggr.
> > This is not used yet so shadow stats are not updated. But later patch
> > will convert the existing code to use it.
> >
> > With that, we don't need to handle AGGR_GLOBAL specially anymore. It
> > can use the same logic with counts, prev_counts and aggr_counts.
> >
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> > tools/perf/builtin-stat.c | 3 --
> > tools/perf/util/evsel.c | 9 +---
> > .../scripting-engines/trace-event-python.c | 6 ---
> > tools/perf/util/stat.c | 46 ++++++++++++++++---
> > 4 files changed, 41 insertions(+), 23 deletions(-)
> >
> > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> > index eaddafbd7ff2..139e35ed68d3 100644
> > --- a/tools/perf/builtin-stat.c
> > +++ b/tools/perf/builtin-stat.c
> > @@ -963,9 +963,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
> > init_stats(&walltime_nsecs_stats);
> > update_stats(&walltime_nsecs_stats, t1 - t0);
> >
> > - if (stat_config.aggr_mode == AGGR_GLOBAL)
> > - evlist__save_aggr_prev_raw_counts(evsel_list);
> > -
> > evlist__copy_prev_raw_counts(evsel_list);
> > evlist__reset_prev_raw_counts(evsel_list);
> > perf_stat__reset_shadow_per_stat(&rt_stat);
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index a6ea91c72659..a1fcb3166149 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -1526,13 +1526,8 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread,
> > if (!evsel->prev_raw_counts)
> > return;
> >
> > - if (cpu_map_idx == -1) {
> > - tmp = evsel->prev_raw_counts->aggr;
> > - evsel->prev_raw_counts->aggr = *count;
> > - } else {
> > - tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
> > - *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
> > - }
> > + tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
> > + *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
> >
> > count->val = count->val - tmp.val;
> > count->ena = count->ena - tmp.ena;
> > diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
> > index 1f2040f36d4e..7bc8559dce6a 100644
> > --- a/tools/perf/util/scripting-engines/trace-event-python.c
> > +++ b/tools/perf/util/scripting-engines/trace-event-python.c
> > @@ -1653,12 +1653,6 @@ static void python_process_stat(struct perf_stat_config *config,
> > struct perf_cpu_map *cpus = counter->core.cpus;
> > int cpu, thread;
> >
> > - if (config->aggr_mode == AGGR_GLOBAL) {
> > - process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp,
> > - &counter->counts->aggr);
> > - return;
> > - }
> > -
> > for (thread = 0; thread < threads->nr; thread++) {
> > for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
> > process_stat(counter, perf_cpu_map__cpu(cpus, cpu),
> > diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> > index 374149628507..99874254809d 100644
> > --- a/tools/perf/util/stat.c
> > +++ b/tools/perf/util/stat.c
> > @@ -387,6 +387,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> > struct perf_counts_values *count)
> > {
> > struct perf_counts_values *aggr = &evsel->counts->aggr;
> > + struct perf_stat_evsel *ps = evsel->stats;
> > static struct perf_counts_values zero;
> > bool skip = false;
> >
> > @@ -398,6 +399,44 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> > if (skip)
> > count = &zero;
> >
> > + if (!evsel->snapshot)
> > + evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
> > + perf_counts_values__scale(count, config->scale, NULL);
> > +
> > + 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);
> > + struct perf_stat_aggr *ps_aggr;
> > + int i;
> > +
> > + for (i = 0; i < ps->nr_aggr; i++) {
>
> Would it be cleaner to have a helper function here that returns i or
> ps_aggr for the first CPU being aggregated into? That would avoid the
> continue/break.
Right, we need cpu -> aggr_idx mapping.
>
> > + if (!aggr_cpu_id__equal(&aggr_id, &config->aggr_map->map[i]))
> > + continue;
> > +
> > + ps_aggr = &ps->aggr[i];
> > + ps_aggr->nr++;
> > +
> > + /*
> > + * When any result is bad, make them all to give
> > + * consistent output in interval mode.
> > + */
> > + if (count->ena == 0 || count->run == 0 ||
> > + evsel->counts->scaled == -1) {
> > + ps_aggr->counts.val = 0;
> > + ps_aggr->counts.ena = 0;
> > + ps_aggr->counts.run = 0;
> > + ps_aggr->failed = true;
> > + }
> > +
> > + if (!ps_aggr->failed) {
> > + ps_aggr->counts.val += count->val;
> > + ps_aggr->counts.ena += count->ena;
> > + ps_aggr->counts.run += count->run;
> > + }
> > + break;
> > + }
> > + }
> > +
> > switch (config->aggr_mode) {
> > case AGGR_THREAD:
> > case AGGR_CORE:
> > @@ -405,9 +444,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> > case AGGR_SOCKET:
> > case AGGR_NODE:
> > case AGGR_NONE:
> > - if (!evsel->snapshot)
> > - evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
> > - perf_counts_values__scale(count, config->scale, NULL);
> > if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
> > perf_stat__update_shadow_stats(evsel, count->val,
> > cpu_map_idx, &rt_stat);
> > @@ -469,10 +505,6 @@ int perf_stat_process_counter(struct perf_stat_config *config,
> > if (config->aggr_mode != AGGR_GLOBAL)
> > return 0;
> >
> > - if (!counter->snapshot)
> > - evsel__compute_deltas(counter, -1, -1, aggr);
> > - perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
> > -
>
> It isn't clear to me how this relates to the patch.
It's moved to process_counter_values() to be handled like other
aggr_mode.
Thanks,
Namhyung
>
> > update_stats(&ps->res_stats, *count);
> >
> > if (verbose > 0) {
> > --
> > 2.38.0.rc1.362.ged0d419d3c-goog
> >
© 2016 - 2026 Red Hat, Inc.