"aggregate counts per physical processor core", AGGR_CORE),
OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
"aggregate counts per thread", AGGR_THREAD),
+ OPT_SET_UINT(0, "per-node", &stat_config.aggr_mode,
+ "aggregate counts per numa node", AGGR_NODE),
OPT_UINTEGER('D', "delay", &stat_config.initial_delay,
"ms to wait before starting measurement after program start"),
OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL,
return cpu_map__get_core(map, cpu, NULL);
}
+static int perf_stat__get_node(struct perf_stat_config *config __maybe_unused,
+ struct perf_cpu_map *map, int cpu)
+{
+ return cpu_map__get_node(map, cpu, NULL);
+}
+
static int perf_stat__get_aggr(struct perf_stat_config *config,
aggr_get_id_t get_id, struct perf_cpu_map *map, int idx)
{
return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);
}
+static int perf_stat__get_node_cached(struct perf_stat_config *config,
+ struct perf_cpu_map *map, int idx)
+{
+ return perf_stat__get_aggr(config, perf_stat__get_node, map, idx);
+}
+
static bool term_percore_set(void)
{
struct evsel *counter;
}
stat_config.aggr_get_id = perf_stat__get_core_cached;
break;
+ case AGGR_NODE:
+ if (cpu_map__build_node_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
+ perror("cannot build core map");
+ return -1;
+ }
+ stat_config.aggr_get_id = perf_stat__get_node_cached;
+ break;
case AGGR_NONE:
if (term_percore_set()) {
if (cpu_map__build_core_map(evsel_list->core.cpus,
return core;
}
+static int perf_env__get_node(struct perf_cpu_map *map, int idx, void *data)
+{
+ int cpu = perf_env__get_cpu(data, map, idx);
+
+ return perf_env__numa_node(data, cpu);
+}
+
static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus,
struct perf_cpu_map **sockp)
{
return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
}
+static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus,
+ struct perf_cpu_map **nodep)
+{
+ return cpu_map__build_map(cpus, nodep, perf_env__get_node, env);
+}
+
static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
struct perf_cpu_map *map, int idx)
{
return perf_env__get_core(map, idx, &perf_stat.session->header.env);
}
+static int perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused,
+ struct perf_cpu_map *map, int idx)
+{
+ return perf_env__get_node(map, idx, &perf_stat.session->header.env);
+}
+
static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
{
struct perf_env *env = &st->session->header.env;
}
stat_config.aggr_get_id = perf_stat__get_core_file;
break;
+ case AGGR_NODE:
+ if (perf_env__build_node_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
+ perror("cannot build core map");
+ return -1;
+ }
+ stat_config.aggr_get_id = perf_stat__get_node_file;
+ break;
case AGGR_NONE:
case AGGR_GLOBAL:
case AGGR_THREAD:
"aggregate counts per processor die", AGGR_DIE),
OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode,
"aggregate counts per physical processor core", AGGR_CORE),
+ OPT_SET_UINT(0, "per-node", &perf_stat.aggr_mode,
+ "aggregate counts per numa node", AGGR_NODE),
OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode,
"disable CPU count aggregation", AGGR_NONE),
OPT_END()
}
}
+ if (stat_config.aggr_mode == AGGR_NODE)
+ cpu__setup_cpunode_map();
+
if (stat_config.times && interval)
interval_count = true;
else if (stat_config.times && !interval) {
return ret ?: value;
}
+int cpu_map__get_node_id(int cpu)
+{
+ return cpu__get_node(cpu);
+}
+
int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
{
int cpu, s_die;
return (s_die << 16) | (cpu & 0xffff);
}
+int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
+{
+ if (idx < 0 || idx >= map->nr)
+ return -1;
+
+ return cpu_map__get_node_id(map->map[idx]);
+}
+
int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp)
{
return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
}
+int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **numap)
+{
+ return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL);
+}
+
/* setup simple routines to easily access node numbers given a cpu number */
static int get_max_num(char *path, int *max)
{