mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-12-27 13:30:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

perf metricgroup: Binary search when resolving referred to metrics

Browse Source 
Unlike with events, metrics can be matched by name or a list of metric
groups.

However, when a metric refers to another metric it isn't referring to a
group but the singular metric in question.

Prior to this change every "id" in a metric expression is checked to see
if it is a metric by scanning all the metrics in the metrics table.

As the table is sorted my metric name we can speed the search in the
resolution case by binary searching for the metric.

Rename some of the metricgroup functions to make it clearer whether
they match a metric by name or by both name and group.

Before:
```
$ time perf test -v 10
 10: PMU JSON event tests                                            :
 10.1: PMU event table sanity                                        : Ok
 10.2: PMU event map aliases                                         : Ok
 10.3: Parsing of PMU event table metrics                            : Ok
 10.4: Parsing of PMU event table metrics with fake PMUs             : Ok
 10.5: Parsing of metric thresholds with fake PMUs                   : Ok

real    0m15.972s
user    0m13.176s
sys     0m3.001s
```

After:
```
$ time perf test -v 10
 10: PMU JSON event tests                                            :
 10.1: PMU event table sanity                                        : Ok
 10.2: PMU event map aliases                                         : Ok
 10.3: Parsing of PMU event table metrics                            : Ok
 10.4: Parsing of PMU event table metrics with fake PMUs             : Ok
 10.5: Parsing of metric thresholds with fake PMUs                   : Ok

real    0m5.343s
user    0m1.871s
sys     0m2.128s
```

Committer testing:

  root@number:~# grep -m1 'model name' /proc/cpuinfo
  model name	: AMD Ryzen 9 9950X3D 16-Core Processor
  root@number:~#

Before:

  root@number:~# time perf test "Parsing of PMU event table metrics"
   10.3: Parsing of PMU event table metrics                            : Ok
   10.4: Parsing of PMU event table metrics with fake PMUs             : Ok

  real	0m9.286s
  user	0m9.354s
  sys	0m0.062s
  root@number:~#

After:

  root@number:~# time perf test "Parsing of PMU event table metrics"
   10.3: Parsing of PMU event table metrics                            : Ok
   10.4: Parsing of PMU event table metrics with fake PMUs             : Ok

  real	0m0.689s
  user	0m0.766s
  sys	0m0.042s
  root@number:~# time perf test 10
   10: PMU JSON event tests                                            :
   10.1: PMU event table sanity                                        : Ok
   10.2: PMU event map aliases                                         : Ok
   10.3: Parsing of PMU event table metrics                            : Ok
   10.4: Parsing of PMU event table metrics with fake PMUs             : Ok
   10.5: Parsing of metric thresholds with fake PMUs                   : Ok

  real	0m0.696s
  user	0m0.807s
  sys	0m0.064s
  root@number:~#

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20250512194622.33258-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Ian Rogers
2025-05-12 12:46:22 -07:00
committed by Arnaldo Carvalho de Melo
parent 754baf426e
commit 4102ff8b1f
6 changed files with 192 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tools/perf/builtin-stat.c
View File

@@ -1854,7 +1854,7 @@ static int add_default_events(void)
* will use this approach. To determine transaction support
* on an architecture test for such a metric name.
*/
if (!metricgroup__has_metric(pmu, "transaction")) {
if (!metricgroup__has_metric_or_groups(pmu, "transaction")) {
pr_err("Missing transaction metrics\n");
ret = -1;
goto out;
@@ -1888,7 +1888,7 @@ static int add_default_events(void)
smi_reset = true;
}
if (!metricgroup__has_metric(pmu, "smi")) {
if (!metricgroup__has_metric_or_groups(pmu, "smi")) {
pr_err("Missing smi metrics\n");
ret = -1;
goto out;
@@ -1978,7 +1978,7 @@ static int add_default_events(void)
* Add TopdownL1 metrics if they exist. To minimize
* multiplexing, don't request threshold computation.
*/
if (metricgroup__has_metric(pmu, "Default")) {
if (metricgroup__has_metric_or_groups(pmu, "Default")) {
struct evlist *metric_evlist = evlist__new();
if (!metric_evlist) {

66
tools/perf/pmu-events/empty-pmu-events.c
View File

@@ -449,7 +449,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table,
const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
int ret;
if (!perf_pmu__name_wildcard_match(pmu, pmu_name))
if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name))
continue;
ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data);
@@ -495,6 +495,49 @@ static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table
return 0;
}
static int pmu_metrics_table__find_metric_pmu(const struct pmu_metrics_table *table,
const struct pmu_table_entry *pmu,
const char *metric,
pmu_metric_iter_fn fn,
void *data)
{
struct pmu_metric pm = {
.pmu = &big_c_string[pmu->pmu_name.offset],
};
int low = 0, high = pmu->num_entries - 1;
while (low <= high) {
int cmp, mid = (low + high) / 2;
decompress_metric(pmu->entries[mid].offset, &pm);
if (!pm.metric_name && !metric)
goto do_call;
if (!pm.metric_name && metric) {
low = mid + 1;
continue;
}
if (pm.metric_name && !metric) {
high = mid - 1;
continue;
}
cmp = strcmp(pm.metric_name, metric);
if (cmp < 0) {
low = mid + 1;
continue;
}
if (cmp > 0) {
high = mid - 1;
continue;
}
do_call:
return fn ? fn(&pm, table, data) : 0;
}
return PMU_METRICS__NOT_FOUND;
}
int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
pmu_metric_iter_fn fn,
void *data)
@@ -509,6 +552,27 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
return 0;
}
int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table,
struct perf_pmu *pmu,
const char *metric,
pmu_metric_iter_fn fn,
void *data)
{
for (size_t i = 0; i < table->num_pmus; i++) {
const struct pmu_table_entry *table_pmu = &table->pmus[i];
const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
int ret;
if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name))
continue;
ret = pmu_metrics_table__find_metric_pmu(table, table_pmu, metric, fn, data);
if (ret != PMU_METRICS__NOT_FOUND)
return ret;
}
return PMU_METRICS__NOT_FOUND;
}
static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu)
{
static struct {

66
tools/perf/pmu-events/jevents.py
View File

@@ -972,7 +972,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table,
const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
int ret;
if (!perf_pmu__name_wildcard_match(pmu, pmu_name))
if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name))
continue;
ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data);
@@ -1018,6 +1018,49 @@ static int pmu_metrics_table__for_each_metric_pmu(const struct pmu_metrics_table
return 0;
}
static int pmu_metrics_table__find_metric_pmu(const struct pmu_metrics_table *table,
const struct pmu_table_entry *pmu,
const char *metric,
pmu_metric_iter_fn fn,
void *data)
{
struct pmu_metric pm = {
.pmu = &big_c_string[pmu->pmu_name.offset],
};
int low = 0, high = pmu->num_entries - 1;
while (low <= high) {
int cmp, mid = (low + high) / 2;
decompress_metric(pmu->entries[mid].offset, &pm);
if (!pm.metric_name && !metric)
goto do_call;
if (!pm.metric_name && metric) {
low = mid + 1;
continue;
}
if (pm.metric_name && !metric) {
high = mid - 1;
continue;
}
cmp = strcmp(pm.metric_name, metric);
if (cmp < 0) {
low = mid + 1;
continue;
}
if (cmp > 0) {
high = mid - 1;
continue;
}
do_call:
return fn ? fn(&pm, table, data) : 0;
}
return PMU_METRICS__NOT_FOUND;
}
int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
pmu_metric_iter_fn fn,
void *data)
@@ -1032,6 +1075,27 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
return 0;
}
int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table,
struct perf_pmu *pmu,
const char *metric,
pmu_metric_iter_fn fn,
void *data)
{
for (size_t i = 0; i < table->num_pmus; i++) {
const struct pmu_table_entry *table_pmu = &table->pmus[i];
const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
int ret;
if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name))
continue;
ret = pmu_metrics_table__find_metric_pmu(table, table_pmu, metric, fn, data);
if (ret != PMU_METRICS__NOT_FOUND)
return ret;
}
return PMU_METRICS__NOT_FOUND;
}
static const struct pmu_events_map *map_for_cpu(struct perf_cpu cpu)
{
static struct {

23
tools/perf/pmu-events/pmu-events.h
View File

@@ -74,6 +74,7 @@ struct pmu_events_table;
struct pmu_metrics_table;
#define PMU_EVENTS__NOT_FOUND -1000
#define PMU_METRICS__NOT_FOUND -1000
typedef int (*pmu_event_iter_fn)(const struct pmu_event *pe,
const struct pmu_events_table *table,
@@ -88,11 +89,11 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table,
pmu_event_iter_fn fn,
void *data);
/*
* Search for table and entry matching with pmu__name_match. Each matching event
* has fn called on it. 0 implies to success/continue the search while non-zero
* means to terminate. The special value PMU_EVENTS__NOT_FOUND is used to
* indicate no event was found in one of the tables which doesn't terminate the
* search of all tables.
* Search for a table and entry matching with pmu__name_wildcard_match or any
* tables if pmu is NULL. Each matching event has fn called on it. 0 implies to
* success/continue the search while non-zero means to terminate. The special
* value PMU_EVENTS__NOT_FOUND is used to indicate no event was found in one of
* the tables which doesn't terminate the search of all tables.
*/
int pmu_events_table__find_event(const struct pmu_events_table *table,
struct perf_pmu *pmu,
@@ -104,6 +105,18 @@ size_t pmu_events_table__num_events(const struct pmu_events_table *table,
int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
void *data);
/*
* Search for a table and entry matching with pmu__name_wildcard_match or any
* tables if pmu is NULL. Each matching metric has fn called on it. 0 implies to
* success/continue the search while non-zero means to terminate. The special
* value PMU_METRICS__NOT_FOUND is used to indicate no metric was found in one
* of the tables which doesn't terminate the search of all tables.
*/
int pmu_metrics_table__find_metric(const struct pmu_metrics_table *table,
struct perf_pmu *pmu,
const char *metric,
pmu_metric_iter_fn fn,
void *data);
const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu);
const struct pmu_metrics_table *pmu_metrics_table__find(void);

102
tools/perf/util/metricgroup.c
View File

@@ -353,7 +353,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
return 0;
}
static bool match_metric(const char *metric_or_groups, const char *sought)
static bool match_metric_or_groups(const char *metric_or_groups, const char *sought)
{
int len;
char *m;
@@ -369,18 +369,19 @@ static bool match_metric(const char *metric_or_groups, const char *sought)
(metric_or_groups[len] == 0 || metric_or_groups[len] == ';'))
return true;
m = strchr(metric_or_groups, ';');
return m && match_metric(m + 1, sought);
return m && match_metric_or_groups(m + 1, sought);
}
static bool match_pm_metric(const struct pmu_metric *pm, const char *pmu, const char *metric)
static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *pmu,
const char *metric_or_groups)
{
const char *pm_pmu = pm->pmu ?: "cpu";
if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
return false;
return match_metric(pm->metric_group, metric) ||
match_metric(pm->metric_name, metric);
return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
match_metric_or_groups(pm->metric_name, metric_or_groups);
}
/** struct mep - RB-tree node for building printing information. */
@@ -802,11 +803,6 @@ struct metricgroup_add_iter_data {
const struct pmu_metrics_table *table;
};
static bool metricgroup__find_metric(const char *pmu,
const char *metric,
const struct pmu_metrics_table *table,
struct pmu_metric *pm);
static int add_metric(struct list_head *metric_list,
const struct pmu_metric *pm,
const char *modifier,
@@ -818,6 +814,16 @@ static int add_metric(struct list_head *metric_list,
const struct visited_metric *visited,
const struct pmu_metrics_table *table);
static int metricgroup__find_metric_callback(const struct pmu_metric *pm,
const struct pmu_metrics_table *table __maybe_unused,
void *vdata)
{
struct pmu_metric *copied_pm = vdata;
memcpy(copied_pm, pm, sizeof(*pm));
return 0;
}
/**
* resolve_metric - Locate metrics within the root metric and recursively add
* references to them.
@@ -838,7 +844,7 @@ static int add_metric(struct list_head *metric_list,
* architecture perf is running upon.
*/
static int resolve_metric(struct list_head *metric_list,
const char *pmu,
struct perf_pmu *pmu,
const char *modifier,
bool metric_no_group,
bool metric_no_threshold,
@@ -868,7 +874,9 @@ static int resolve_metric(struct list_head *metric_list,
hashmap__for_each_entry(root_metric->pctx->ids, cur, bkt) {
struct pmu_metric pm;
if (metricgroup__find_metric(pmu, cur->pkey, table, &pm)) {
if (pmu_metrics_table__find_metric(table, pmu, cur->pkey,
metricgroup__find_metric_callback,
&pm) != PMU_METRICS__NOT_FOUND) {
pending = realloc(pending,
(pending_cnt + 1) * sizeof(struct to_resolve));
if (!pending)
@@ -1019,7 +1027,12 @@ static int __add_metric(struct list_head *metric_list,
}
if (!ret) {
/* Resolve referenced metrics. */
const char *pmu = pm->pmu ?: "cpu";
struct perf_pmu *pmu;
if (pm->pmu && pm->pmu[0] != '\0')
pmu = perf_pmus__find(pm->pmu);
else
pmu = perf_pmus__scan_core(/*pmu=*/ NULL);
ret = resolve_metric(metric_list, pmu, modifier, metric_no_group,
metric_no_threshold, user_requested_cpu_list,
@@ -1036,44 +1049,6 @@ static int __add_metric(struct list_head *metric_list,
return ret;
}
struct metricgroup__find_metric_data {
const char *pmu;
const char *metric;
struct pmu_metric *pm;
};
static int metricgroup__find_metric_callback(const struct pmu_metric *pm,
const struct pmu_metrics_table *table __maybe_unused,
void *vdata)
{
struct metricgroup__find_metric_data *data = vdata;
const char *pm_pmu = pm->pmu ?: "cpu";
if (strcmp(data->pmu, "all") && strcmp(pm_pmu, data->pmu))
return 0;
if (!match_metric(pm->metric_name, data->metric))
return 0;
memcpy(data->pm, pm, sizeof(*pm));
return 1;
}
static bool metricgroup__find_metric(const char *pmu,
const char *metric,
const struct pmu_metrics_table *table,
struct pmu_metric *pm)
{
struct metricgroup__find_metric_data data = {
.pmu = pmu,
.metric = metric,
.pm = pm,
};
return pmu_metrics_table__for_each_metric(table, metricgroup__find_metric_callback, &data)
? true : false;
}
static int add_metric(struct list_head *metric_list,
const struct pmu_metric *pm,
const char *modifier,
@@ -1119,7 +1094,7 @@ static int metricgroup__add_metric_sys_event_iter(const struct pmu_metric *pm,
struct metricgroup_add_iter_data *d = data;
int ret;
if (!match_pm_metric(pm, d->pmu, d->metric_name))
if (!match_pm_metric_or_groups(pm, d->pmu, d->metric_name))
return 0;
ret = add_metric(d->metric_list, pm, d->modifier, d->metric_no_group,
@@ -1200,9 +1175,9 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm,
struct metricgroup__add_metric_data *data = vdata;
int ret = 0;
if (pm->metric_expr && match_pm_metric(pm, data->pmu, data->metric_name)) {
if (pm->metric_expr && match_pm_metric_or_groups(pm, data->pmu, data->metric_name)) {
bool metric_no_group = data->metric_no_group ||
match_metric(pm->metricgroup_no_group, data->metric_name);
match_metric_or_groups(pm->metricgroup_no_group, data->metric_name);
data->has_match = true;
ret = add_metric(data->list, pm, data->modifier, metric_no_group,
@@ -1723,29 +1698,32 @@ int metricgroup__parse_groups_test(struct evlist *evlist,
struct metricgroup__has_metric_data {
const char *pmu;
const char *metric;
const char *metric_or_groups;
};
static int metricgroup__has_metric_callback(const struct pmu_metric *pm,
const struct pmu_metrics_table *table __maybe_unused,
void *vdata)
static int metricgroup__has_metric_or_groups_callback(const struct pmu_metric *pm,
const struct pmu_metrics_table *table
__maybe_unused,
void *vdata)
{
struct metricgroup__has_metric_data *data = vdata;
return match_pm_metric(pm, data->pmu, data->metric) ? 1 : 0;
return match_pm_metric_or_groups(pm, data->pmu, data->metric_or_groups) ? 1 : 0;
}
bool metricgroup__has_metric(const char *pmu, const char *metric)
bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_groups)
{
const struct pmu_metrics_table *table = pmu_metrics_table__find();
struct metricgroup__has_metric_data data = {
.pmu = pmu,
.metric = metric,
.metric_or_groups = metric_or_groups,
};
if (!table)
return false;
return pmu_metrics_table__for_each_metric(table, metricgroup__has_metric_callback, &data)
return pmu_metrics_table__for_each_metric(table,
metricgroup__has_metric_or_groups_callback,
&data)
? true : false;
}

2
tools/perf/util/metricgroup.h
View File

@@ -85,7 +85,7 @@ int metricgroup__parse_groups_test(struct evlist *evlist,
struct rblist *metric_events);
void metricgroup__print(const struct print_callbacks *print_cb, void *print_state);
bool metricgroup__has_metric(const char *pmu, const char *metric);
bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_groups);
unsigned int metricgroups__topdown_max_level(void);
int arch_get_runtimeparam(const struct pmu_metric *pm);
void metricgroup__rblist_exit(struct rblist *metric_events);