[PATCH 07/10] perf, tools: Collapse identically named events in perf stat

[Andi Kleen]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

The uncore PMU has a lot of duplicated PMUs for different subsystems.
When expanding an uncore alias we usually end up with a large
number of identically named aliases, which makes perf stat
output difficult to read.

Automatically sum them up in perf stat, unless --no-merge is specified.

This can be default because only the uncores generally have duplicated
aliases. Other PMUs have unique names.

Before:

% perf stat --no-merge -a  -e unc_c_llc_lookup.any sleep 1

 Performance counter stats for 'system wide':

           694,976 Bytes unc_c_llc_lookup.any
           706,304 Bytes unc_c_llc_lookup.any
           956,608 Bytes unc_c_llc_lookup.any
           782,720 Bytes unc_c_llc_lookup.any
           605,696 Bytes unc_c_llc_lookup.any
           442,816 Bytes unc_c_llc_lookup.any
           659,328 Bytes unc_c_llc_lookup.any
           509,312 Bytes unc_c_llc_lookup.any
           263,936 Bytes unc_c_llc_lookup.any
           592,448 Bytes unc_c_llc_lookup.any
           672,448 Bytes unc_c_llc_lookup.any
           608,640 Bytes unc_c_llc_lookup.any
           641,024 Bytes unc_c_llc_lookup.any
           856,896 Bytes unc_c_llc_lookup.any
           808,832 Bytes unc_c_llc_lookup.any
           684,864 Bytes unc_c_llc_lookup.any
           710,464 Bytes unc_c_llc_lookup.any
           538,304 Bytes unc_c_llc_lookup.any

       1.002577660 seconds time elapsed

After:

% perf stat  -a  -e unc_c_llc_lookup.any sleep 1

 Performance counter stats for 'system wide':

         2,685,120 Bytes unc_c_llc_lookup.any

       1.002648032 seconds time elapsed

v2: Split collect_aliases. Rename alias flag.
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 tools/perf/Documentation/perf-stat.txt |   3 +
 tools/perf/builtin-stat.c              | 132 +++++++++++++++++++++++++++------
 tools/perf/util/evsel.h                |   1 +
 3 files changed, 113 insertions(+), 23 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index d96ccd4844df..320d8020bc5b 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -237,6 +237,9 @@ To interpret the results it is usually needed to know on which
 CPUs the workload runs on. If needed the CPUs can be forced using
 taskset.
 
+--no-merge::
+Do not merge results from same PMUs.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 688dea7cb08f..501d58a4925a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -140,6 +140,7 @@ static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static bool			metric_only			= false;
 static bool			force_metric_only		= false;
+static bool			no_merge			= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -1178,11 +1179,66 @@ static void aggr_update_shadow(void)
 	}
 }
 
+static void collect_all_aliases(struct perf_evsel *counter,
+			    void (*cb)(struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	struct perf_evsel *alias;
+
+	alias = list_prepare_entry(counter, &(evsel_list->entries), node);
+	list_for_each_entry_continue (alias, &evsel_list->entries, node) {
+		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		    alias->scale != counter->scale ||
+		    alias->cgrp != counter->cgrp ||
+		    strcmp(alias->unit, counter->unit) ||
+		    nsec_counter(alias) != nsec_counter(counter))
+			break;
+		alias->merged_stat = true;
+		cb(alias, data, false);
+	}
+}
+
+static void collect_aliases(struct perf_evsel *counter,
+			    void (*cb)(struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	cb(counter, data, true);
+	if (!no_merge)
+		collect_all_aliases(counter, cb, data);
+}
+
+struct aggr_data {
+	u64 ena, run, val;
+	int id;
+	int nr;
+	int cpu;
+};
+
+static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
+{
+	struct aggr_data *ad = data;
+	int cpu, cpu2, s2;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		cpu2 = perf_evsel__cpus(counter)->map[cpu];
+		s2 = aggr_get_id(evsel_list->cpus, cpu2);
+		if (s2 != ad->id)
+			continue;
+		ad->val += perf_counts(counter->counts, cpu, 0)->val;
+		ad->ena += perf_counts(counter->counts, cpu, 0)->ena;
+		ad->run += perf_counts(counter->counts, cpu, 0)->run;
+		if (first)
+			ad->nr++;
+	}
+}
+
 static void print_aggr(char *prefix)
 {
 	FILE *output = stat_config.output;
 	struct perf_evsel *counter;
-	int cpu, s, s2, id, nr;
+	int s, id, nr;
 	double uval;
 	u64 ena, run, val;
 	bool first;
@@ -1197,23 +1253,22 @@ static void print_aggr(char *prefix)
 	 * Without each counter has its own line.
 	 */
 	for (s = 0; s < aggr_map->nr; s++) {
+		struct aggr_data ad;
 		if (prefix && metric_only)
 			fprintf(output, "%s", prefix);
 
-		id = aggr_map->map[s];
+		ad.id = id = aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evsel_list, counter) {
-			val = ena = run = 0;
-			nr = 0;
-			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
-				if (s2 != id)
-					continue;
-				val += perf_counts(counter->counts, cpu, 0)->val;
-				ena += perf_counts(counter->counts, cpu, 0)->ena;
-				run += perf_counts(counter->counts, cpu, 0)->run;
-				nr++;
-			}
+			if (counter->merged_stat)
+				continue;
+			ad.val = ad.ena = ad.run = 0;
+			ad.nr = 0;
+			collect_aliases(counter, aggr_cb, &ad);
+			nr = ad.nr;
+			ena = ad.ena;
+			run = ad.run;
+			val = ad.val;
 			if (first && metric_only) {
 				first = false;
 				aggr_printout(counter, id, nr);
@@ -1257,6 +1312,21 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+struct caggr_data {
+	double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_evsel *counter, void *data,
+			    bool first __maybe_unused)
+{
+	struct caggr_data *cd = data;
+	struct perf_stat_evsel *ps = counter->priv;
+
+	cd->avg += avg_stats(&ps->res_stats[0]);
+	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+	cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -1264,23 +1334,32 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 {
 	FILE *output = stat_config.output;
-	struct perf_stat_evsel *ps = counter->priv;
-	double avg = avg_stats(&ps->res_stats[0]);
 	double uval;
-	double avg_enabled, avg_running;
+	struct caggr_data cd = { .avg = 0.0 };
 
-	avg_enabled = avg_stats(&ps->res_stats[1]);
-	avg_running = avg_stats(&ps->res_stats[2]);
+	if (counter->merged_stat)
+		return;
+	collect_aliases(counter, counter_aggr_cb, &cd);
 
 	if (prefix && !metric_only)
 		fprintf(output, "%s", prefix);
 
-	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
+	uval = cd.avg * counter->scale;
+	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg);
 	if (!metric_only)
 		fprintf(output, "\n");
 }
 
+static void counter_cb(struct perf_evsel *counter, void *data,
+		       bool first __maybe_unused)
+{
+	struct aggr_data *ad = data;
+
+	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
 /*
  * Print out the results of a single counter:
  * does not use aggregated count in system-wide
@@ -1292,10 +1371,16 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	double uval;
 	int cpu;
 
+	if (counter->merged_stat)
+		return;
+
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		val = perf_counts(counter->counts, cpu, 0)->val;
-		ena = perf_counts(counter->counts, cpu, 0)->ena;
-		run = perf_counts(counter->counts, cpu, 0)->run;
+		struct aggr_data ad = { .cpu = cpu };
+
+		collect_aliases(counter, counter_cb, &ad);
+		val = ad.val;
+		ena = ad.ena;
+		run = ad.run;
 
 		if (prefix)
 			fprintf(output, "%s", prefix);
@@ -1633,6 +1718,7 @@ static const struct option stat_options[] = {
 		    "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", &no_merge, "Do not merge identical named events"),
 	OPT_STRING('x', "field-separator", &csv_sep, "separator",
 		   "print counts with custom separator"),
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8cd7cd227483..343776422821 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -130,6 +130,7 @@ struct perf_evsel {
 	bool			cmdline_group_boundary;
 	struct list_head	config_terms;
 	int			bpf_fd;
+	bool			merged_stat;
 };
 
 union u64_swap {
-- 
2.5.5