perf stat: Add --per-node agregation support

Adding new --per-node option to aggregate counts per NUMA
nodes for system-wide mode measurements.

You can specify --per-node in live mode:

  # perf stat  -a -I 1000 -e cycles --per-node
  #           time node   cpus             counts unit events
       1.000542550 N0       20          6,202,097      cycles
       1.000542550 N1       20            639,559      cycles
       2.002040063 N0       20          7,412,495      cycles
       2.002040063 N1       20          2,185,577      cycles
       3.003451699 N0       20          6,508,917      cycles
       3.003451699 N1       20            765,607      cycles
  ...

Or in the record/report stat session:

  # perf stat record -a -I 1000 -e cycles
  #           time             counts unit events
       1.000536937         10,008,468      cycles
       2.002090152          9,578,539      cycles
       3.003625233          7,647,869      cycles
       4.005135036          7,032,086      cycles
  ^C     4.340902364          3,923,893      cycles

  # perf stat report --per-node
  #           time node   cpus             counts unit events
       1.000536937 N0       20          9,355,086      cycles
       1.000536937 N1       20            653,382      cycles
       2.002090152 N0       20          7,712,838      cycles
       2.002090152 N1       20          1,865,701      cycles
       3.003625233 N0       20          6,604,441      cycles
       3.003625233 N1       20          1,043,428      cycles
       4.005135036 N0       20          6,350,522      cycles
       4.005135036 N1       20            681,564      cycles
       4.340902364 N0       20          3,403,188      cycles
       4.340902364 N1       20            520,705      cycles

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20190904073415.723-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 38 insertions, 0 deletions

diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index a22c1114e880..983b7388f22b 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -206,6 +206,11 @@ int cpu_map__get_core_id(int cpu)
 	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;
@@ -235,6 +240,14 @@ int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
 	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);
@@ -250,6 +263,11 @@ int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **cor
 	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)
 {
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 2553bef1279d..57943f3685f8 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -20,9 +20,12 @@ int cpu_map__get_die_id(int cpu);
 int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
 int cpu_map__get_core_id(int cpu);
 int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
+int cpu_map__get_node_id(int cpu);
+int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data);
 int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp);
 int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep);
 int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep);
+int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **nodep);
 const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */
 
 static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index ed3b0ac2f785..bc31fccc0057 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -100,6 +100,15 @@ static void aggr_printout(struct perf_stat_config *config,
 			nr,
 			config->csv_sep);
 			break;
+	case AGGR_NODE:
+		fprintf(config->output, "N%*d%s%*d%s",
+			config->csv_output ? 0 : -5,
+			id,
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+			break;
 	case AGGR_NONE:
 		if (evsel->percore) {
 			fprintf(config->output, "S%d-D%d-C%*d%s",
@@ -965,6 +974,11 @@ static void print_interval(struct perf_stat_config *config,
 
 	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
 		switch (config->aggr_mode) {
+		case AGGR_NODE:
+			fprintf(output, "#           time node   cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus");
 			if (!metric_only)
@@ -1188,6 +1202,7 @@ perf_evlist__print_counters(struct evlist *evlist,
 	case AGGR_CORE:
 	case AGGR_DIE:
 	case AGGR_SOCKET:
+	case AGGR_NODE:
 		print_aggr(config, evlist, prefix);
 		break;
 	case AGGR_THREAD:
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 6822e4ffe224..332cb730785b 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -299,6 +299,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 	case AGGR_CORE:
 	case AGGR_DIE:
 	case AGGR_SOCKET:
+	case AGGR_NODE:
 	case AGGR_NONE:
 		if (!evsel->snapshot)
 			perf_evsel__compute_deltas(evsel, cpu, thread, count);
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 081c4a5113c6..bfa9aaf36ce6 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -47,6 +47,7 @@ enum aggr_mode {
 	AGGR_CORE,
 	AGGR_THREAD,
 	AGGR_UNSET,
+	AGGR_NODE,
 };
 
 enum {