aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/builtin-stat.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/builtin-stat.c')
-rw-r--r--tools/perf/builtin-stat.c85
1 files changed, 68 insertions, 17 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 07b48f6df48e..6bba1a89d030 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -653,7 +653,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
if ((evsel__leader(counter) != counter) ||
!(counter->core.leader->nr_members > 1))
return COUNTER_SKIP;
- } else if (evsel__fallback(counter, errno, msg, sizeof(msg))) {
+ } else if (evsel__fallback(counter, &target, errno, msg, sizeof(msg))) {
if (verbose > 0)
ui__warning("%s\n", msg);
return COUNTER_RETRY;
@@ -1204,8 +1204,9 @@ static struct option stat_options[] = {
OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
"list of cpus to monitor in system-wide"),
OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
- "disable CPU count aggregation", AGGR_NONE),
- OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"),
+ "disable aggregation across CPUs or PMUs", AGGR_NONE),
+ OPT_SET_UINT(0, "no-merge", &stat_config.aggr_mode,
+ "disable aggregation the same as -A or -no-aggr", AGGR_NONE),
OPT_BOOLEAN(0, "hybrid-merge", &stat_config.hybrid_merge,
"Merge identical named hybrid events"),
OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",
@@ -1237,6 +1238,8 @@ static struct option stat_options[] = {
"aggregate counts per processor socket", AGGR_SOCKET),
OPT_SET_UINT(0, "per-die", &stat_config.aggr_mode,
"aggregate counts per processor die", AGGR_DIE),
+ OPT_SET_UINT(0, "per-cluster", &stat_config.aggr_mode,
+ "aggregate counts per processor cluster", AGGR_CLUSTER),
OPT_CALLBACK_OPTARG(0, "per-cache", &stat_config.aggr_mode, &stat_config.aggr_level,
"cache level", "aggregate count at this cache level (Default: LLC)",
parse_cache_level),
@@ -1255,7 +1258,7 @@ static struct option stat_options[] = {
OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge,
"don't try to share events between metrics in a group"),
OPT_BOOLEAN(0, "metric-no-threshold", &stat_config.metric_no_threshold,
- "don't try to share events between metrics in a group "),
+ "disable adding events for the metric threshold calculation"),
OPT_BOOLEAN(0, "topdown", &topdown_run,
"measure top-down statistics"),
OPT_UINTEGER(0, "td-level", &stat_config.topdown_level,
@@ -1316,7 +1319,7 @@ static int cpu__get_cache_id_from_map(struct perf_cpu cpu, char *map)
* be the first online CPU in the cache domain else use the
* first online CPU of the cache domain as the ID.
*/
- if (perf_cpu_map__empty(cpu_map))
+ if (perf_cpu_map__has_any_cpu_or_is_empty(cpu_map))
id = cpu.cpu;
else
id = perf_cpu_map__cpu(cpu_map, 0).cpu;
@@ -1427,6 +1430,7 @@ static struct aggr_cpu_id aggr_cpu_id__cache(struct perf_cpu cpu, void *data)
static const char *const aggr_mode__string[] = {
[AGGR_CORE] = "core",
[AGGR_CACHE] = "cache",
+ [AGGR_CLUSTER] = "cluster",
[AGGR_DIE] = "die",
[AGGR_GLOBAL] = "global",
[AGGR_NODE] = "node",
@@ -1454,6 +1458,12 @@ static struct aggr_cpu_id perf_stat__get_cache_id(struct perf_stat_config *confi
return aggr_cpu_id__cache(cpu, /*data=*/NULL);
}
+static struct aggr_cpu_id perf_stat__get_cluster(struct perf_stat_config *config __maybe_unused,
+ struct perf_cpu cpu)
+{
+ return aggr_cpu_id__cluster(cpu, /*data=*/NULL);
+}
+
static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
struct perf_cpu cpu)
{
@@ -1506,6 +1516,12 @@ static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *con
return perf_stat__get_aggr(config, perf_stat__get_die, cpu);
}
+static struct aggr_cpu_id perf_stat__get_cluster_cached(struct perf_stat_config *config,
+ struct perf_cpu cpu)
+{
+ return perf_stat__get_aggr(config, perf_stat__get_cluster, cpu);
+}
+
static struct aggr_cpu_id perf_stat__get_cache_id_cached(struct perf_stat_config *config,
struct perf_cpu cpu)
{
@@ -1543,6 +1559,8 @@ static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode aggr_mode)
return aggr_cpu_id__socket;
case AGGR_DIE:
return aggr_cpu_id__die;
+ case AGGR_CLUSTER:
+ return aggr_cpu_id__cluster;
case AGGR_CACHE:
return aggr_cpu_id__cache;
case AGGR_CORE:
@@ -1568,6 +1586,8 @@ static aggr_get_id_t aggr_mode__get_id(enum aggr_mode aggr_mode)
return perf_stat__get_socket_cached;
case AGGR_DIE:
return perf_stat__get_die_cached;
+ case AGGR_CLUSTER:
+ return perf_stat__get_cluster_cached;
case AGGR_CACHE:
return perf_stat__get_cache_id_cached;
case AGGR_CORE:
@@ -1622,7 +1642,7 @@ static int perf_stat_init_aggr_mode(void)
* taking the highest cpu number to be the size of
* the aggregation translate cpumap.
*/
- if (evsel_list->core.user_requested_cpus)
+ if (!perf_cpu_map__has_any_cpu_or_is_empty(evsel_list->core.user_requested_cpus))
nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu;
else
nr = 0;
@@ -1736,6 +1756,21 @@ static struct aggr_cpu_id perf_env__get_cache_aggr_by_cpu(struct perf_cpu cpu,
return id;
}
+static struct aggr_cpu_id perf_env__get_cluster_aggr_by_cpu(struct perf_cpu cpu,
+ void *data)
+{
+ struct perf_env *env = data;
+ struct aggr_cpu_id id = aggr_cpu_id__empty();
+
+ if (cpu.cpu != -1) {
+ id.socket = env->cpu[cpu.cpu].socket_id;
+ id.die = env->cpu[cpu.cpu].die_id;
+ id.cluster = env->cpu[cpu.cpu].cluster_id;
+ }
+
+ return id;
+}
+
static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, void *data)
{
struct perf_env *env = data;
@@ -1743,12 +1778,12 @@ static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, vo
if (cpu.cpu != -1) {
/*
- * core_id is relative to socket and die,
- * we need a global id. So we set
- * socket, die id and core id
+ * core_id is relative to socket, die and cluster, we need a
+ * global id. So we set socket, die id, cluster id and core id.
*/
id.socket = env->cpu[cpu.cpu].socket_id;
id.die = env->cpu[cpu.cpu].die_id;
+ id.cluster = env->cpu[cpu.cpu].cluster_id;
id.core = env->cpu[cpu.cpu].core_id;
}
@@ -1804,6 +1839,12 @@ static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *confi
return perf_env__get_die_aggr_by_cpu(cpu, &perf_stat.session->header.env);
}
+static struct aggr_cpu_id perf_stat__get_cluster_file(struct perf_stat_config *config __maybe_unused,
+ struct perf_cpu cpu)
+{
+ return perf_env__get_cluster_aggr_by_cpu(cpu, &perf_stat.session->header.env);
+}
+
static struct aggr_cpu_id perf_stat__get_cache_file(struct perf_stat_config *config __maybe_unused,
struct perf_cpu cpu)
{
@@ -1841,6 +1882,8 @@ static aggr_cpu_id_get_t aggr_mode__get_aggr_file(enum aggr_mode aggr_mode)
return perf_env__get_socket_aggr_by_cpu;
case AGGR_DIE:
return perf_env__get_die_aggr_by_cpu;
+ case AGGR_CLUSTER:
+ return perf_env__get_cluster_aggr_by_cpu;
case AGGR_CACHE:
return perf_env__get_cache_aggr_by_cpu;
case AGGR_CORE:
@@ -1866,6 +1909,8 @@ static aggr_get_id_t aggr_mode__get_id_file(enum aggr_mode aggr_mode)
return perf_stat__get_socket_file;
case AGGR_DIE:
return perf_stat__get_die_file;
+ case AGGR_CLUSTER:
+ return perf_stat__get_cluster_file;
case AGGR_CACHE:
return perf_stat__get_cache_file;
case AGGR_CORE:
@@ -2289,7 +2334,7 @@ int process_stat_config_event(struct perf_session *session,
perf_event__read_stat_config(&stat_config, &event->stat_config);
- if (perf_cpu_map__empty(st->cpus)) {
+ if (perf_cpu_map__has_any_cpu_or_is_empty(st->cpus)) {
if (st->aggr_mode != AGGR_UNSET)
pr_warning("warning: processing task data, aggregation mode not set\n");
} else if (st->aggr_mode != AGGR_UNSET) {
@@ -2397,6 +2442,8 @@ static int __cmd_report(int argc, const char **argv)
"aggregate counts per processor socket", AGGR_SOCKET),
OPT_SET_UINT(0, "per-die", &perf_stat.aggr_mode,
"aggregate counts per processor die", AGGR_DIE),
+ OPT_SET_UINT(0, "per-cluster", &perf_stat.aggr_mode,
+ "aggregate counts perf processor cluster", AGGR_CLUSTER),
OPT_CALLBACK_OPTARG(0, "per-cache", &perf_stat.aggr_mode, &perf_stat.aggr_level,
"cache level",
"aggregate count at this cache level (Default: LLC)",
@@ -2695,15 +2742,19 @@ int cmd_stat(int argc, const char **argv)
*/
if (metrics) {
const char *pmu = parse_events_option_args.pmu_filter ?: "all";
+ int ret = metricgroup__parse_groups(evsel_list, pmu, metrics,
+ stat_config.metric_no_group,
+ stat_config.metric_no_merge,
+ stat_config.metric_no_threshold,
+ stat_config.user_requested_cpu_list,
+ stat_config.system_wide,
+ &stat_config.metric_events);
- metricgroup__parse_groups(evsel_list, pmu, metrics,
- stat_config.metric_no_group,
- stat_config.metric_no_merge,
- stat_config.metric_no_threshold,
- stat_config.user_requested_cpu_list,
- stat_config.system_wide,
- &stat_config.metric_events);
zfree(&metrics);
+ if (ret) {
+ status = ret;
+ goto out;
+ }
}
if (add_default_attributes())
Powered by cgit, Gruvboxed by Blaster4385.