Skip to content

L
linux
Commit 91f85f98 authored by Namhyung Kim's avatar Namhyung Kim Committed by Arnaldo Carvalho de Melo
Browse files
Options

perf stat: Display event stats using aggr counts 

Now aggr counts are ready for use.  Convert the display routines to use
the aggr counts and update the shadow stat with them.  It doesn't need
to aggregate counts or collect aliases anymore during the display.  Get
rid of now unused struct perf_aggr_thread_value.

Note that there's a difference in the display order among the aggr mode.
For per-core/die/socket/node aggregation, it shows relevant events in
the same unit together, whereas global/thread/no aggregation it shows
the same events for different units together.  So it still uses separate
codes to display them due to the ordering.

One more thing to note is that it breaks per-core event display for now.
The next patch will fix it to have identical output as of now.
Signed-off-by: default avatarNamhyung Kim <namhyung@kernel.org>
Acked-by: default avatarIan Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20221018020227.85905-19-namhyung@kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent 88f1d351
Show whitespace changes
Inline Side-by-side
Showing with 49 additions and 386 deletions
tools/perf/util/stat-display.c
View file @ 91f85f98
...@@ -442,31 +442,6 @@ static void print_metric_header(struct perf_stat_config *config, ...@@ -442,31 +442,6 @@ static void print_metric_header(struct perf_stat_config *config,
fprintf(os->fh, "%*s ", config->metric_only_len, unit); fprintf(os->fh, "%*s ", config->metric_only_len, unit);
} }
static int first_shadow_map_idx(struct perf_stat_config *config,
struct evsel *evsel, const struct aggr_cpu_id *id)
{
struct perf_cpu_map *cpus = evsel__cpus(evsel);
struct perf_cpu cpu;
int idx;
if (config->aggr_mode == AGGR_NONE)
return perf_cpu_map__idx(cpus, id->cpu);
if (config->aggr_mode == AGGR_THREAD)
return id->thread_idx;
if (!config->aggr_get_id)
return 0;
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
struct aggr_cpu_id cpu_id = config->aggr_get_id(config, cpu);
if (aggr_cpu_id__equal(&cpu_id, id))
return idx;
}
return 0;
}
static void abs_printout(struct perf_stat_config *config, static void abs_printout(struct perf_stat_config *config,
struct aggr_cpu_id id, int nr, struct evsel *evsel, double avg) struct aggr_cpu_id id, int nr, struct evsel *evsel, double avg)
{ {
...@@ -537,7 +512,7 @@ static bool is_mixed_hw_group(struct evsel *counter) ...@@ -537,7 +512,7 @@ static bool is_mixed_hw_group(struct evsel *counter)
static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr, static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr,
struct evsel *counter, double uval, struct evsel *counter, double uval,
char *prefix, u64 run, u64 ena, double noise, char *prefix, u64 run, u64 ena, double noise,
struct runtime_stat *st) struct runtime_stat *st, int map_idx)
{ {
struct perf_stat_output_ctx out; struct perf_stat_output_ctx out;
struct outstate os = { struct outstate os = {
...@@ -648,8 +623,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int ...@@ -648,8 +623,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
print_running(config, run, ena); print_running(config, run, ena);
} }
perf_stat__print_shadow_stats(config, counter, uval, perf_stat__print_shadow_stats(config, counter, uval, map_idx,
first_shadow_map_idx(config, counter, &id),
&out, &config->metric_events, st); &out, &config->metric_events, st);
if (!config->csv_output && !config->metric_only && !config->json_output) { if (!config->csv_output && !config->metric_only && !config->json_output) {
print_noise(config, counter, noise); print_noise(config, counter, noise);
...@@ -657,34 +631,6 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int ...@@ -657,34 +631,6 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
} }
} }
static void aggr_update_shadow(struct perf_stat_config *config,
struct evlist *evlist)
{
int idx, s;
struct perf_cpu cpu;
struct aggr_cpu_id s2, id;
u64 val;
struct evsel *counter;
struct perf_cpu_map *cpus;
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
evlist__for_each_entry(evlist, counter) {
cpus = evsel__cpus(counter);
val = 0;
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
s2 = config->aggr_get_id(config, cpu);
if (!aggr_cpu_id__equal(&s2, &id))
continue;
val += perf_counts(counter->counts, idx, 0)->val;
}
perf_stat__update_shadow_stats(counter, val,
first_shadow_map_idx(config, counter, &id),
&rt_stat);
}
}
}
static void uniquify_event_name(struct evsel *counter) static void uniquify_event_name(struct evsel *counter)
{ {
char *new_name; char *new_name;
...@@ -721,137 +667,51 @@ static void uniquify_event_name(struct evsel *counter) ...@@ -721,137 +667,51 @@ static void uniquify_event_name(struct evsel *counter)
counter->uniquified_name = true; counter->uniquified_name = true;
} }
static void collect_all_aliases(struct perf_stat_config *config, struct evsel *counter, static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config)
void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
bool first),
void *data)
{ {
struct evlist *evlist = counter->evlist; return evsel__is_hybrid(evsel) && !config->hybrid_merge;
struct evsel *alias;
alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
/* Merge events with the same name, etc. but on different PMUs. */
if (!strcmp(evsel__name(alias), evsel__name(counter)) &&
alias->scale == counter->scale &&
alias->cgrp == counter->cgrp &&
!strcmp(alias->unit, counter->unit) &&
evsel__is_clock(alias) == evsel__is_clock(counter) &&
strcmp(alias->pmu_name, counter->pmu_name)) {
alias->merged_stat = true;
cb(config, alias, data, false);
}
}
}
static bool hybrid_merge(struct evsel *counter, struct perf_stat_config *config,
bool check)
{
if (evsel__is_hybrid(counter)) {
if (check)
return config->hybrid_merge;
else
return !config->hybrid_merge;
}
return false;
} }
static bool collect_data(struct perf_stat_config *config, struct evsel *counter, static void uniquify_counter(struct perf_stat_config *config, struct evsel *counter)
void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
bool first),
void *data)
{ {
if (counter->merged_stat) if (config->no_merge || hybrid_uniquify(counter, config))
return false;
cb(config, counter, data, true);
if (config->no_merge || hybrid_merge(counter, config, false))
uniquify_event_name(counter); uniquify_event_name(counter);
else if (counter->auto_merge_stats || hybrid_merge(counter, config, true))
collect_all_aliases(config, counter, cb, data);
return true;
}
struct aggr_data {
u64 ena, run, val;
struct aggr_cpu_id id;
int nr;
int cpu_map_idx;
};
static void aggr_cb(struct perf_stat_config *config,
struct evsel *counter, void *data, bool first)
{
struct aggr_data *ad = data;
int idx;
struct perf_cpu cpu;
struct perf_cpu_map *cpus;
struct aggr_cpu_id s2;
cpus = evsel__cpus(counter);
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
struct perf_counts_values *counts;
s2 = config->aggr_get_id(config, cpu);
if (!aggr_cpu_id__equal(&s2, &ad->id))
continue;
if (first)
ad->nr++;
counts = perf_counts(counter->counts, idx, 0);
/*
* When any result is bad, make them all to give
* consistent output in interval mode.
*/
if (counts->ena == 0 || counts->run == 0 ||
counter->counts->scaled == -1) {
ad->ena = 0;
ad->run = 0;
break;
}
ad->val += counts->val;
ad->ena += counts->ena;
ad->run += counts->run;
}
} }
static void print_counter_aggrdata(struct perf_stat_config *config, static void print_counter_aggrdata(struct perf_stat_config *config,
struct evsel *counter, int s, struct evsel *counter, int s,
char *prefix, bool metric_only, char *prefix, bool metric_only,
bool *first, struct perf_cpu cpu) bool *first)
{ {
struct aggr_data ad;
FILE *output = config->output; FILE *output = config->output;
u64 ena, run, val; u64 ena, run, val;
int nr;
struct aggr_cpu_id id;
double uval; double uval;
struct perf_stat_evsel *ps = counter->stats;
struct perf_stat_aggr *aggr = &ps->aggr[s];
struct aggr_cpu_id id = config->aggr_map->map[s];
double avg = aggr->counts.val;
ad.id = id = config->aggr_map->map[s]; if (counter->supported && aggr->nr == 0)
ad.val = ad.ena = ad.run = 0;
ad.nr = 0;
if (!collect_data(config, counter, aggr_cb, &ad))
return; return;
if (perf_pmu__has_hybrid() && ad.ena == 0) uniquify_counter(config, counter);
return;
val = aggr->counts.val;
ena = aggr->counts.ena;
run = aggr->counts.run;
nr = ad.nr;
ena = ad.ena;
run = ad.run;
val = ad.val;
if (*first && metric_only) { if (*first && metric_only) {
*first = false; *first = false;
aggr_printout(config, counter, id, nr); aggr_printout(config, counter, id, aggr->nr);
} }
if (prefix && !metric_only) if (prefix && !metric_only)
fprintf(output, "%s", prefix); fprintf(output, "%s", prefix);
uval = val * counter->scale; uval = val * counter->scale;
if (cpu.cpu != -1)
id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
printout(config, id, nr, counter, uval, printout(config, id, aggr->nr, counter, uval,
prefix, run, ena, 1.0, &rt_stat); prefix, run, ena, avg, &rt_stat, s);
if (!metric_only) if (!metric_only)
fputc('\n', output); fputc('\n', output);
} }
...@@ -869,8 +729,6 @@ static void print_aggr(struct perf_stat_config *config, ...@@ -869,8 +729,6 @@ static void print_aggr(struct perf_stat_config *config,
if (!config->aggr_map || !config->aggr_get_id) if (!config->aggr_map || !config->aggr_get_id)
return; return;
aggr_update_shadow(config, evlist);
/* /*
* With metric_only everything is on a single line. * With metric_only everything is on a single line.
* Without each counter has its own line. * Without each counter has its own line.
...@@ -881,188 +739,36 @@ static void print_aggr(struct perf_stat_config *config, ...@@ -881,188 +739,36 @@ static void print_aggr(struct perf_stat_config *config,
first = true; first = true;
evlist__for_each_entry(evlist, counter) { evlist__for_each_entry(evlist, counter) {
if (counter->merged_stat)
continue;
print_counter_aggrdata(config, counter, s, print_counter_aggrdata(config, counter, s,
prefix, metric_only, prefix, metric_only,
&first, (struct perf_cpu){ .cpu = -1 }); &first);
} }
if (metric_only) if (metric_only)
fputc('\n', output); fputc('\n', output);
} }
} }
static int cmp_val(const void *a, const void *b) static void print_counter(struct perf_stat_config *config,
{
return ((struct perf_aggr_thread_value *)b)->val -
((struct perf_aggr_thread_value *)a)->val;
}
static struct perf_aggr_thread_value *sort_aggr_thread(
struct evsel *counter,
int *ret,
struct target *_target)
{
int nthreads = perf_thread_map__nr(counter->core.threads);
int i = 0;
double uval;
struct perf_aggr_thread_value *buf;
buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
if (!buf)
return NULL;
for (int thread = 0; thread < nthreads; thread++) {
int idx;
u64 ena = 0, run = 0, val = 0;
perf_cpu_map__for_each_idx(idx, evsel__cpus(counter)) {
struct perf_counts_values *counts =
perf_counts(counter->counts, idx, thread);
val += counts->val;
ena += counts->ena;
run += counts->run;
}
uval = val * counter->scale;
/*
* Skip value 0 when enabling --per-thread globally,
* otherwise too many 0 output.
*/
if (uval == 0.0 && target__has_per_thread(_target))
continue;
buf[i].counter = counter;
buf[i].id = aggr_cpu_id__empty();
buf[i].id.thread_idx = thread;
buf[i].uval = uval;
buf[i].val = val;
buf[i].run = run;
buf[i].ena = ena;
i++;
}
qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
if (ret)
*ret = i;
return buf;
}
static void print_aggr_thread(struct perf_stat_config *config,
struct target *_target,
struct evsel *counter, char *prefix)
{
FILE *output = config->output;
int thread, sorted_threads;
struct aggr_cpu_id id;
struct perf_aggr_thread_value *buf;
buf = sort_aggr_thread(counter, &sorted_threads, _target);
if (!buf) {
perror("cannot sort aggr thread");
return;
}
for (thread = 0; thread < sorted_threads; thread++) {
if (prefix)
fprintf(output, "%s", prefix);
id = buf[thread].id;
printout(config, id, 0, buf[thread].counter, buf[thread].uval,
prefix, buf[thread].run, buf[thread].ena, 1.0,
&rt_stat);
fputc('\n', output);
}
free(buf);
}
struct caggr_data {
double avg, avg_enabled, avg_running;
};
static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
struct evsel *counter, void *data,
bool first __maybe_unused)
{
struct caggr_data *cd = data;
struct perf_counts_values *aggr = &counter->counts->aggr;
cd->avg += aggr->val;
cd->avg_enabled += aggr->ena;
cd->avg_running += aggr->run;
}
/*
* Print out the results of a single counter:
* aggregated counts in system-wide mode
*/
static void print_counter_aggr(struct perf_stat_config *config,
struct evsel *counter, char *prefix) struct evsel *counter, char *prefix)
{ {
bool metric_only = config->metric_only; bool metric_only = config->metric_only;
FILE *output = config->output; bool first = false;
double uval; int s;
struct caggr_data cd = { .avg = 0.0 };
if (!collect_data(config, counter, counter_aggr_cb, &cd)) /* AGGR_THREAD doesn't have config->aggr_get_id */
if (!config->aggr_map)
return; return;
if (prefix && !metric_only) if (counter->merged_stat)
fprintf(output, "%s", prefix);
uval = cd.avg * counter->scale;
printout(config, aggr_cpu_id__empty(), 0, counter, uval, prefix, cd.avg_running,
cd.avg_enabled, cd.avg, &rt_stat);
if (!metric_only)
fprintf(output, "\n");
}
static void counter_cb(struct perf_stat_config *config __maybe_unused,
struct evsel *counter, void *data,
bool first __maybe_unused)
{
struct aggr_data *ad = data;
ad->val += perf_counts(counter->counts, ad->cpu_map_idx, 0)->val;
ad->ena += perf_counts(counter->counts, ad->cpu_map_idx, 0)->ena;
ad->run += perf_counts(counter->counts, ad->cpu_map_idx, 0)->run;
}
/*
* Print out the results of a single counter:
* does not use aggregated count in system-wide
*/
static void print_counter(struct perf_stat_config *config,
struct evsel *counter, char *prefix)
{
FILE *output = config->output;
u64 ena, run, val;
double uval;
int idx;
struct perf_cpu cpu;
struct aggr_cpu_id id;
perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) {
struct aggr_data ad = { .cpu_map_idx = idx };
if (!collect_data(config, counter, counter_cb, &ad))
return; return;
val = ad.val;
ena = ad.ena;
run = ad.run;
if (prefix)
fprintf(output, "%s", prefix);
uval = val * counter->scale; for (s = 0; s < config->aggr_map->nr; s++) {
id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); print_counter_aggrdata(config, counter, s,
printout(config, id, 0, counter, uval, prefix, prefix, metric_only,
run, ena, 1.0, &rt_stat); &first);
fputc('\n', output);
} }
} }
...@@ -1081,6 +787,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config, ...@@ -1081,6 +787,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
u64 ena, run, val; u64 ena, run, val;
double uval; double uval;
struct aggr_cpu_id id; struct aggr_cpu_id id;
struct perf_stat_evsel *ps = counter->stats;
int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu); int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu);
if (counter_idx < 0) if (counter_idx < 0)
...@@ -1093,13 +800,13 @@ static void print_no_aggr_metric(struct perf_stat_config *config, ...@@ -1093,13 +800,13 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
aggr_printout(config, counter, id, 0); aggr_printout(config, counter, id, 0);
first = false; first = false;
} }
val = perf_counts(counter->counts, counter_idx, 0)->val; val = ps->aggr[counter_idx].counts.val;
ena = perf_counts(counter->counts, counter_idx, 0)->ena; ena = ps->aggr[counter_idx].counts.ena;
run = perf_counts(counter->counts, counter_idx, 0)->run; run = ps->aggr[counter_idx].counts.run;
uval = val * counter->scale; uval = val * counter->scale;
printout(config, id, 0, counter, uval, prefix, printout(config, id, 0, counter, uval, prefix,
run, ena, 1.0, &rt_stat); run, ena, 1.0, &rt_stat, counter_idx);
} }
if (!first) if (!first)
fputc('\n', config->output); fputc('\n', config->output);
...@@ -1379,31 +1086,6 @@ static void print_footer(struct perf_stat_config *config) ...@@ -1379,31 +1086,6 @@ static void print_footer(struct perf_stat_config *config)
"the same PMU. Try reorganizing the group.\n"); "the same PMU. Try reorganizing the group.\n");
} }
static void print_percore_thread(struct perf_stat_config *config,
struct evsel *counter, char *prefix)
{
int s;
struct aggr_cpu_id s2, id;
struct perf_cpu_map *cpus;
bool first = true;
int idx;
struct perf_cpu cpu;
cpus = evsel__cpus(counter);
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
s2 = config->aggr_get_id(config, cpu);
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
if (aggr_cpu_id__equal(&s2, &id))
break;
}
print_counter_aggrdata(config, counter, s,
prefix, false,
&first, cpu);
}
}
static void print_percore(struct perf_stat_config *config, static void print_percore(struct perf_stat_config *config,
struct evsel *counter, char *prefix) struct evsel *counter, char *prefix)
{ {
...@@ -1416,15 +1098,14 @@ static void print_percore(struct perf_stat_config *config, ...@@ -1416,15 +1098,14 @@ static void print_percore(struct perf_stat_config *config,
return; return;
if (config->percore_show_thread) if (config->percore_show_thread)
return print_percore_thread(config, counter, prefix); return print_counter(config, counter, prefix);
for (s = 0; s < config->aggr_map->nr; s++) { for (s = 0; s < config->aggr_map->nr; s++) {
if (prefix && metric_only) if (prefix && metric_only)
fprintf(output, "%s", prefix); fprintf(output, "%s", prefix);
print_counter_aggrdata(config, counter, s, print_counter_aggrdata(config, counter, s,
prefix, metric_only, prefix, metric_only, &first);
&first, (struct perf_cpu){ .cpu = -1 });
} }
if (metric_only) if (metric_only)
...@@ -1469,17 +1150,13 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf ...@@ -1469,17 +1150,13 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf
print_aggr(config, evlist, prefix); print_aggr(config, evlist, prefix);
break; break;
case AGGR_THREAD: case AGGR_THREAD:
evlist__for_each_entry(evlist, counter) {
print_aggr_thread(config, _target, counter, prefix);
}
break;
case AGGR_GLOBAL: case AGGR_GLOBAL:
if (config->iostat_run) if (config->iostat_run)
iostat_print_counters(evlist, config, ts, prefix = buf, iostat_print_counters(evlist, config, ts, prefix = buf,
print_counter_aggr); print_counter);
else { else {
evlist__for_each_entry(evlist, counter) { evlist__for_each_entry(evlist, counter) {
print_counter_aggr(config, counter, prefix); print_counter(config, counter, prefix);
} }
if (metric_only) if (metric_only)
fputc('\n', config->output); fputc('\n', config->output);
......
tools/perf/util/stat.c
View file @ 91f85f98
...@@ -565,11 +565,6 @@ int perf_stat_process_counter(struct perf_stat_config *config, ...@@ -565,11 +565,6 @@ int perf_stat_process_counter(struct perf_stat_config *config,
evsel__name(counter), count[0], count[1], count[2]); evsel__name(counter), count[0], count[1], count[2]);
} }
/*
* Save the full runtime - to allow normalization during printout:
*/
perf_stat__update_shadow_stats(counter, *count, 0, &rt_stat);
return 0; return 0;
} }
......
tools/perf/util/stat.h
View file @ 91f85f98
...@@ -224,15 +224,6 @@ static inline void update_rusage_stats(struct rusage_stats *ru_stats, struct rus ...@@ -224,15 +224,6 @@ static inline void update_rusage_stats(struct rusage_stats *ru_stats, struct rus
struct evsel; struct evsel;
struct evlist; struct evlist;
struct perf_aggr_thread_value {
struct evsel *counter;
struct aggr_cpu_id id;
double uval;
u64 val;
u64 run;
u64 ena;
};
bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id); bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id);
#define perf_stat_evsel__is(evsel, id) \ #define perf_stat_evsel__is(evsel, id) \
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7