perf stat: Implement CSV metrics output

Now support CSV output for metrics. With the new output callbacks this
is relatively straight forward by creating new callbacks.

This allows to easily plot metrics from CSV files.

The new line callback needs to know the number of fields to skip them
correctly

Example output before:

  % perf stat -x, true
  0.200687,,task-clock,200687,100.00
  0,,context-switches,200687,100.00
  0,,cpu-migrations,200687,100.00
  40,,page-faults,200687,100.00
  730871,,cycles,203601,100.00
  551056,,stalled-cycles-frontend,203601,100.00
  <not supported>,,stalled-cycles-backend,0,100.00
  385523,,instructions,203601,100.00
  78028,,branches,203601,100.00
  3946,,branch-misses,203601,100.00

After:

  % perf stat -x, true
  .502457,,task-clock,502457,100.00,0.485,CPUs utilized
  0,,context-switches,502457,100.00,0.000,K/sec
  0,,cpu-migrations,502457,100.00,0.000,K/sec
  45,,page-faults,502457,100.00,0.090,M/sec
  644692,,cycles,509102,100.00,1.283,GHz
  423470,,stalled-cycles-frontend,509102,100.00,65.69,frontend cycles idle
  <not supported>,,stalled-cycles-backend,0,100.00,,,,
  492701,,instructions,509102,100.00,0.76,insn per cycle
  ,,,,,0.86,stalled cycles per insn
  97767,,branches,509102,100.00,194.578,M/sec
  4788,,branch-misses,509102,100.00,4.90,of all branches

or easier readable

  $ perf stat  -x, -o x.csv true
  $ column -s, -t x.csv
  0.490635        task-clock              490635 100.00 0.489   CPUs utilized
  0               context-switches        490635 100.00 0.000   K/sec
  0               cpu-migrations          490635 100.00 0.000   K/sec
  45              page-faults             490635 100.00 0.092   M/sec
  629080          cycles                  497698 100.00 1.282   GHz
  409498          stalled-cycles-frontend 497698 100.00 65.09   frontend cycles idle
  <not supported> stalled-cycles-backend  0      100.00
  491424          instructions            497698 100.00 0.78    insn per cycle
                                                        0.83    stalled cycles per insn
  97278           branches                497698 100.00 198.270 M/sec
  4569            branch-misses           497698 100.00 4.70    of all branches

Two new fields are added: metric value and metric name.

v2: Split out function argument changes
v3: Reenable metrics for real.
v4: Fix wrong hunk from refactoring.
v5: Remove extra "noise" printing (Jiri), but add it to the not counted case.
Print empty metrics for not counted.
v6: Avoid outputting metric on empty format.
v7: Print metric at the end
v8: Remove extra run, ena fields
v9: Avoid extra new line for unsupported counters

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/1456785386-19481-3-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-stat.c

@@ -739,6 +739,7 @@ struct outstate {
 	FILE *fh;
 	bool newline;
 	const char *prefix;
+	int  nfields;
 };
 
 #define METRIC_LEN  35
@@ -789,6 +790,43 @@ static void print_metric_std(void *ctx, const char *color, const char *fmt,
 	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
 }
 
+static void new_line_csv(void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+	for (i = 0; i < os->nfields; i++)
+		fputs(csv_sep, os->fh);
+}
+
+static void print_metric_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;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	while (isspace(*unit))
+		unit++;
+	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -860,6 +898,22 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	nl = new_line_std;
 
+	if (csv_output) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[stat_config.aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
 	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
 		aggr_printout(counter, id, nr);
 
@@ -880,7 +934,12 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 			fprintf(stat_config.output, "%s%s",
 				csv_sep, counter->cgrp->name);
 
+		if (!csv_output)
+			pm(&os, NULL, NULL, "", 0);
+		print_noise(counter, noise);
 		print_running(run, ena);
+		if (csv_output)
+			pm(&os, NULL, NULL, "", 0);
 		return;
 	}
 
@@ -893,14 +952,20 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.new_line = nl;
 	out.ctx = &os;
 
-	if (!csv_output)
+	if (csv_output) {
-		perf_stat__print_shadow_stats(counter, uval,
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
+
+	perf_stat__print_shadow_stats(counter, uval,
 				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
 				cpu_map__id_to_cpu(id),
 				&out);
 
-	print_noise(counter, noise);
+	if (!csv_output) {
-	print_running(run, ena);
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
 }
 
 static void print_aggr(char *prefix)

tools/perf/util/stat-shadow.c

@@ -310,8 +310,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
-		out->new_line(ctxp);
 		if (total && avg) {
+			out->new_line(ctxp);
 			ratio = total / avg;
 			print_metric(ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",