Support --metric-only in perf

Support --metric-only in perf

[Andi Kleen]

Support --metric-only to only output metrics in perf stat. This
can give much more concise and easier to read output in some situations.

Plus one bug fix.

This patchkit is on top of the earlier posted perf stat metrics
refactoring patches.

[PATCH 1/2] perf, tools, stat: Implement --metric-only mode

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add a new mode to only print metrics. Sometimes we don't care about
the raw values, just want the computed metrics. This allows more
compact printing, so with -I each sample is only a single line.
This also allows easier plotting and processing with other tools.

The main target is with using --topdown, but it also works with
-T and standard perf stat. A few metrics are not supported.

To avoiding having to hardcode all the metrics in the code it uses
a two pass approach: first compute dummy metrics and only
print the headers in the print_metric callback. Then use the callback
to print the actual values. There are some additional changes
in the stat printout code to handle all metrics being on a single line.

Example:

% perf stat -a -I 1000 --metric-only
     1.000604977 frontend cycles idle     backend cycles idle      insn per cycle           stalled cycles per insn  branch-misses of all branches
     1.000604977                                                    0.76                                             2.35%
     2.000924680                                                    0.72                                             2.34%
     3.001139592                                                    0.76                                             2.57%
     4.001358452                                                    0.73                                             2.44%

The output is fairly wide, but that's a trade off for the concise format.

v2: Lots of updates.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt |   4 +
 tools/perf/builtin-stat.c              | 210 +++++++++++++++++++++++++++++++--
 2 files changed, 204 insertions(+), 10 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 079b141..58296e7 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -132,6 +132,10 @@ Print count deltas every N milliseconds (minimum: 10ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+--metric-only::
+Only print computed metrics. Print them in a single line.
+Don't show any raw values. Not supported with -A or --per-thread.
+
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
 is a useful mode to detect imbalance between sockets.  To enable this mode,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c80cc64..a18db2b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -119,6 +119,7 @@ static bool			sync_run			= false;
 static unsigned int		initial_delay			= 0;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
+static bool			metric_only			= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -594,6 +595,99 @@ static void print_metric_csv(void *ctx,
 	fprintf(out, "%s%s%s", vals, csv_sep, unit);
 }
 
+#define METRIC_ONLY_LEN 24
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	char buf[1024];
+	unsigned mlen = METRIC_ONLY_LEN;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (color)
+		n = color_fprintf(out, color, fmt, val);
+	else
+		n = fprintf(out, fmt, val);
+	if (n > METRIC_ONLY_LEN)
+		n = METRIC_ONLY_LEN;
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+	fprintf(out, "%*s", mlen - n, "");
+}
+
+static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, csv_sep);
+}
+
+static void new_line_metric(void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (csv_output)
+		fprintf(os->fh, "%s%s", unit, csv_sep);
+	else
+		fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -682,9 +776,16 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	print_metric_t pm = print_metric_std;
 	void (*nl)(void *);
 
-	nl = new_line_std;
+	if (metric_only) {
+		nl = new_line_metric;
+		if (csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
 
-	if (csv_output) {
+	if (csv_output && !metric_only) {
 		static int aggr_fields[] = {
 			[AGGR_GLOBAL] = 0,
 			[AGGR_THREAD] = 1,
@@ -703,6 +804,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		os.ena = ena;
 	}
 	if (run == 0 || ena == 0) {
+		if (metric_only) {
+			pm(&os, NULL, "", "", 0);
+			return;
+		}
 		aggr_printout(counter, id, nr);
 
 		fprintf(stat_config.output, "%*s%s",
@@ -726,7 +831,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		return;
 	}
 
-	if (nsec_counter(counter))
+	if (metric_only)
+		/* nothing */;
+	else if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
@@ -739,8 +846,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
 				first_shadow_cpu(counter, id),
 				&out);
-	print_noise(counter, noise);
-	print_running(run, ena);
+
+	if (!metric_only) {
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
 }
 
 static void aggr_update_shadow(void)
@@ -774,6 +884,7 @@ static void print_aggr(char *prefix)
 	int cpu, s, s2, id, nr;
 	double uval;
 	u64 ena, run, val;
+	bool first;
 
 	if (!(aggr_map || aggr_get_id))
 		return;
@@ -781,7 +892,11 @@ static void print_aggr(char *prefix)
 	aggr_update_shadow();
 
 	for (s = 0; s < aggr_map->nr; s++) {
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
 		id = aggr_map->map[s];
+		first = true;
 		evlist__for_each(evsel_list, counter) {
 			val = ena = run = 0;
 			nr = 0;
@@ -794,13 +909,20 @@ static void print_aggr(char *prefix)
 				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
-			if (prefix)
+			if (first && metric_only) {
+				first = false;
+				aggr_printout(counter, id, nr);
+			}
+			if (prefix && !metric_only)
 				fprintf(output, "%s", prefix);
 
 			uval = val * counter->scale;
 			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
-			fputc('\n', output);
+			if (!metric_only)
+				fputc('\n', output);
 		}
+		if (metric_only)
+			fputc('\n', output);
 	}
 }
 
@@ -845,12 +967,13 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	avg_enabled = avg_stats(&ps->res_stats[1]);
 	avg_running = avg_stats(&ps->res_stats[2]);
 
-	if (prefix)
+	if (prefix && !metric_only)
 		fprintf(output, "%s", prefix);
 
 	uval = avg * counter->scale;
 	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
-	fprintf(output, "\n");
+	if (!metric_only)
+		fprintf(output, "\n");
 }
 
 /*
@@ -879,6 +1002,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 15,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
+
+static void print_metric_headers(char *prefix)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = stat_config.output
+	};
+
+	if (prefix)
+		fprintf(stat_config.output, "%s", prefix);
+
+	if (!csv_output)
+		fprintf(stat_config.output, "%*s",
+			aggr_header_lens[stat_config.aggr_mode], "");
+
+	/* Print metrics headers only */
+	evlist__for_each(evsel_list, counter) {
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(counter, 0,
+					      0,
+					      &out);
+	}
+	fputc('\n', stat_config.output);
+}
+
 static void print_interval(char *prefix, struct timespec *ts)
 {
 	FILE *output = stat_config.output;
@@ -886,7 +1046,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output) {
+	if (num_print_interval == 0 && !csv_output && !metric_only) {
 		switch (stat_config.aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
@@ -969,6 +1129,17 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	else
 		print_header(argc, argv);
 
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0)
+			print_metric_headers(prefix);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(stat_config.output, "%s", prefix);
+	}
+
 	switch (stat_config.aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
@@ -981,6 +1152,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
+		if (metric_only)
+			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
 		evlist__for_each(evsel_list, counter)
@@ -1105,6 +1278,8 @@ static const struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
+	OPT_BOOLEAN(0, "metric-only", &metric_only,
+			"Only print computed metrics. No raw values"),
 	OPT_END()
 };
 
@@ -1393,6 +1568,21 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+		fprintf(stderr, "--metric-only is not supported with --per-thread\n");
+		goto out;
+	}
+
+	if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
+		fprintf(stderr, "--metric-only is not supported with -A\n");
+		goto out;
+	}
+
+	if (metric_only && run_count > 1) {
+		fprintf(stderr, "--metric-only is not supported with -r\n");
+		goto out;
+	}
+
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
 		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
-- 
2.4.3

[PATCH 2/2] perf, tools, stat: Fix indentation of counter running printout

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Fix the indentation of the counter running printout for non supported
counters.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a18db2b..4777355 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -827,6 +827,8 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 			fprintf(stat_config.output, "%s%s",
 				csv_sep, counter->cgrp->name);
 
+		pm(&os, NULL, NULL, "", 0);
+
 		print_running(run, ena);
 		return;
 	}
-- 
2.4.3