perf, tools: Refactor and support interval and CSV metrics v6

perf, tools: Refactor and support interval and CSV metrics v6

[Andi Kleen]

[v4: Addressed all review feedback.]
[v3: Addressed all review feedback. Update manpage for CSV. Various changes
     (see individual patches). Remove some more redundant code 
     in printout callers.]
[v2: Addressed (near) all review feedback. No manpage updates so far.
     Add support for --per-core metrics. Various cleanups.]
[v3: Everything compiles again. Some more cleanups.]
[v4: Split up abstract metrics patch into two. Fix bug with earlier
patch already enabling metrics for CSV/interval. Minor cleanups.
Man page is included]
[v5: Fix mainly bisect problems. No regressions introduced by one
patch and fixed again later. Some minor fixes in addition]
[v6: Fix running/noise printing patch.]

Currently perf stat does not support printing computed metrics for interval (-I xxx)
or CSV (-x,) mode. For example IPC or TSX metrics over time are quite useful to know.

This patch implements them. The main obstacle was that the
metrics printing was all open coded all over the metrics computation code.
The second patch refactors the metrics printing to work through call backs that
can be more easily changed. This also cleans up the metrics printing significantly.
The indentation is now handled through printf, no more need to manually count spaces.

Then based on that it implements metrics printing for CSV and interval mode.

Example output:

% perf stat  -I1000 -a sleep 1
#          time              counts unit events                    metric                              multiplex
     1.001301370       12020.049593      task-clock (msec)                                             (100.00%)
     1.001301370              3,952      context-switches          #    0.329 K/sec                    (100.00%)
     1.001301370                 69      cpu-migrations            #    0.006 K/sec                    (100.00%)
     1.001301370                 76      page-faults               #    0.006 K/sec                  
     1.001301370        386,582,789      cycles                    #    0.032 GHz                      (100.00%)
     1.001301370        716,441,544      stalled-cycles-frontend   #  185.33% frontend cycles idle     (100.00%)
     1.001301370    <not supported>      stalled-cycles-backend   
     1.001301370        101,751,678      instructions              #    0.26  insn per cycle         
     1.001301370                                                   #    7.04  stalled cycles per insn  (100.00%)
     1.001301370         20,914,692      branches                  #    1.740 M/sec                    (100.00%)
     1.001301370          1,943,630      branch-misses             #    9.29% of all branches        

CSV mode

% perf stat  -x, -I1000 -a sleep 1
     1.000852081,12016.143006,,task-clock
     1.000852081,4457,,context-switches,12015168277,100.00,0.371,K/sec
     1.000852081,50,,cpu-migrations,12014024424,100.00,0.004,K/sec
     1.000852081,76,,page-faults,12013076716,100.00,0.006,K/sec
     1.000852081,515854373,,cycles,12011235336,100.00,0.043,GHz
     1.000852081,1030742150,,stalled-cycles-frontend,12010984057,100.00,199.81,frontend cycles idle
     1.000852081,<not supported>,,stalled-cycles-backend,0,100.00
     1.000852081,116782495,,instructions,12011130729,100.00,0.23,insn per cycle
     1.000852081,,,,12011130729,100.00,8.83,stalled cycles per insn
     1.000852081,23748237,,branches,12010745125,100.00,1.976,M/sec
     1.000852081,1976560,,branch-misses,12010501884,100.00,8.32,of all branches

Available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-10

[PATCH 1/9] perf, tools, stat: Move sw clock metrics printout to stat-shadow

[Andi Kleen]

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

The sw clock metrics printing was missed in the earlier move to
stat-shadow of all the other metric printouts. Move it too.

Acked-by: Jiri Olsa <jolsa@kernel.org>
v2: Fix metrics printing in this version to make bisect safe.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     | 8 +++-----
 tools/perf/util/stat-shadow.c | 5 +++++
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2f438f7..8a78895 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -493,6 +493,7 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	double msecs = avg / 1e6;
 	const char *fmt_v, *fmt_n;
 	char name[25];
+	int cpu = cpu_map__id_to_cpu(id);
 
 	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
 	fmt_n = csv_output ? "%s" : "%-25s";
@@ -517,11 +518,8 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	if (csv_output || stat_config.interval)
 		return;
 
-	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		fprintf(output, " # %8.3f CPUs utilized          ",
-			avg / avg_stats(&walltime_nsecs_stats));
-	else
-		fprintf(output, "                                   ");
+	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
+				      stat_config.aggr_mode);
 }
 
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2a5d8d7..6ac0314 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -413,6 +413,11 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
+			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+		else
+			fprintf(out, "                                   ");
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 
-- 
2.4.3

[PATCH 2/9] tools, perf, stat: Use common printout faction to avoid duplicated code

[Andi Kleen]

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

Instead of every caller deciding whether to call abs or nsec printout
do it all in a single central function. No functional changes.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 57 +++++++++++++++++------------------------------
 1 file changed, 20 insertions(+), 37 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8a78895..b74ee0f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -493,7 +493,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	double msecs = avg / 1e6;
 	const char *fmt_v, *fmt_n;
 	char name[25];
-	int cpu = cpu_map__id_to_cpu(id);
 
 	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
 	fmt_n = csv_output ? "%s" : "%-25s";
@@ -514,12 +513,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-
-	if (csv_output || stat_config.interval)
-		return;
-
-	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
-				      stat_config.aggr_mode);
 }
 
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
@@ -527,7 +520,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	FILE *output = stat_config.output;
 	double sc =  evsel->scale;
 	const char *fmt;
-	int cpu = cpu_map__id_to_cpu(id);
 
 	if (csv_output) {
 		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
@@ -540,9 +532,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	aggr_printout(evsel, id, nr);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
-
 	fprintf(output, fmt, avg, csv_sep);
 
 	if (evsel->unit)
@@ -554,12 +543,24 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+}
 
-	if (csv_output || stat_config.interval)
-		return;
+static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+{
+	int cpu = cpu_map__id_to_cpu(id);
+
+	if (stat_config.aggr_mode == AGGR_GLOBAL)
+		cpu = 0;
+
+	if (nsec_counter(counter))
+		nsec_printout(id, nr, counter, uval);
+	else
+		abs_printout(id, nr, counter, uval);
 
-	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
-				      stat_config.aggr_mode);
+	if (!csv_output && !stat_config.interval)
+		perf_stat__print_shadow_stats(stat_config.output, counter,
+					      uval, cpu,
+					      stat_config.aggr_mode);
 }
 
 static void print_aggr(char *prefix)
@@ -615,12 +616,7 @@ static void print_aggr(char *prefix)
 				continue;
 			}
 			uval = val * counter->scale;
-
-			if (nsec_counter(counter))
-				nsec_printout(id, nr, counter, uval);
-			else
-				abs_printout(id, nr, counter, uval);
-
+			printout(id, nr, counter, uval);
 			if (!csv_output)
 				print_noise(counter, 1.0);
 
@@ -651,11 +647,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-
-		if (nsec_counter(counter))
-			nsec_printout(thread, 0, counter, uval);
-		else
-			abs_printout(thread, 0, counter, uval);
+		printout(thread, 0, counter, uval);
 
 		if (!csv_output)
 			print_noise(counter, 1.0);
@@ -705,11 +697,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	}
 
 	uval = avg * counter->scale;
-
-	if (nsec_counter(counter))
-		nsec_printout(-1, 0, counter, uval);
-	else
-		abs_printout(-1, 0, counter, uval);
+	printout(-1, 0, counter, uval);
 
 	print_noise(counter, avg);
 
@@ -762,12 +750,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		}
 
 		uval = val * counter->scale;
-
-		if (nsec_counter(counter))
-			nsec_printout(cpu, 0, counter, uval);
-		else
-			abs_printout(cpu, 0, counter, uval);
-
+		printout(cpu, 0, counter, uval);
 		if (!csv_output)
 			print_noise(counter, 1.0);
 		print_running(run, ena);
-- 
2.4.3

[PATCH 3/9] perf, tools, stat: Abstract stat metrics printing

[Andi Kleen]

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

Abstract the printing of shadow metrics. Instead of every
metric calling fprintf directly and taking care of indentation,
use two call backs: one to print metrics and another to
start a new line.

This will allow adding metrics to CSV mode and also
using them for other purposes.

The computation of padding is now done in the central
callback, instead of every metric doing it manually.
This makes it easier to add new metrics.

v2: Refactor functions, printout now does more. Move
shadow printing. Improve fallback callbacks. Don't
use void * callback data.
v3: Remove unnecessary hunk. Add typedef for new_line
v4: Remove unnecessary hunk. Don't print metrics for CSV/interval
mode yet.  Move printout change to separate patch.
v5: Fix bisect bugs. Avoid bogus frontend cycles printing.
Fix indentation in different aggregation modes.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     |  59 ++++++++++--
 tools/perf/util/stat-shadow.c | 211 +++++++++++++++++++++++-------------------
 tools/perf/util/stat.h        |  15 ++-
 3 files changed, 182 insertions(+), 103 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b74ee0f..27ca063 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -487,6 +487,46 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 	}
 }
 
+struct outstate {
+	FILE *fh;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(void *ctx)
+{
+	struct outstate *os = ctx;
+
+	fputc('\n', os->fh);
+	if (stat_config.aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	if (stat_config.aggr_mode == AGGR_CORE)
+		fprintf(os->fh, "                  ");
+	if (stat_config.aggr_mode == AGGR_SOCKET)
+		fprintf(os->fh, "            ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -547,20 +587,27 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 static void printout(int id, int nr, struct perf_evsel *counter, double uval)
 {
-	int cpu = cpu_map__id_to_cpu(id);
+	struct outstate os = { .fh = stat_config.output };
+	struct perf_stat_output_ctx out;
+	print_metric_t pm = print_metric_std;
+	void (*nl)(void *);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
+	nl = new_line_std;
 
 	if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
 
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+
 	if (!csv_output && !stat_config.interval)
-		perf_stat__print_shadow_stats(stat_config.output, counter,
-					      uval, cpu,
-					      stat_config.aggr_mode);
+		perf_stat__print_shadow_stats(counter, uval,
+				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+				cpu_map__id_to_cpu(id),
+				&out);
 }
 
 static void print_aggr(char *prefix)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac0314..4d8f185 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
+static void print_stalled_cycles_frontend(int cpu,
 					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
+					  __maybe_unused, double avg,
+					  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -152,14 +153,17 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " frontend cycles idle   ");
+	if (ratio)
+		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+				  ratio);
+	else
+		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(FILE *out, int cpu,
+static void print_stalled_cycles_backend(int cpu,
 					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
+					 __maybe_unused, double avg,
+					 struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -172,14 +176,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " backend  cycles idle   ");
+	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(FILE *out, int cpu,
+static void print_branch_misses(int cpu,
 				struct perf_evsel *evsel __maybe_unused,
-				double avg)
+				double avg,
+				struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -192,14 +195,13 @@ static void print_branch_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all branches        ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(FILE *out, int cpu,
+static void print_l1_dcache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -212,14 +214,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-dcache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(FILE *out, int cpu,
+static void print_l1_icache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -231,15 +232,13 @@ static void print_l1_icache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-icache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(FILE *out, int cpu,
+static void print_dtlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -251,15 +250,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all dTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(FILE *out, int cpu,
+static void print_itlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -271,15 +268,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all iTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(FILE *out, int cpu,
+static void print_ll_cache_misses(int cpu,
 				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
+				  double avg,
+				  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -291,15 +286,15 @@ static void print_ll_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all LL-cache hits   ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out)
 {
+	void *ctxp = out->ctx;
+	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	int ctx = evsel_context(evsel);
 
@@ -307,119 +302,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"insn per cycle", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 		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) {
 			ratio = total / avg;
-			fprintf(out, "\n");
-			if (aggr == AGGR_NONE)
-				fprintf(out, "        ");
-			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"stalled cycles per insn",
+					ratio);
+		} else {
+			print_metric(ctxp, NULL, NULL,
+				     "stalled cycles per insn", 0);
 		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+		if (runtime_branches_stats[ctx][cpu].n != 0)
+			print_branch_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
-		print_l1_dcache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+			print_l1_dcache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_icache_stats[ctx][cpu].n != 0) {
-		print_l1_icache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+			print_l1_icache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
-		print_dtlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+			print_dtlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
-		print_itlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+			print_itlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_ll_cache_stats[ctx][cpu].n != 0) {
-		print_ll_cache_misses(out, cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+			print_ll_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+		if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.3f %%",
+				     "of all cache refs", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+		print_stalled_cycles_frontend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(out, cpu, evsel, avg);
+		print_stalled_cycles_backend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " # %8.3f GHz                    ", ratio);
+			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
+			print_metric(ctxp, NULL,
+					"%7.2f%%", "transactional cycles",
+					100.0 * (avg / total));
+		else
+			print_metric(ctxp, NULL, NULL, "transactional cycles",
+				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% aborted cycles         ",
+			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
-	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		else
+			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
-	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.0f",
+				     "cycles / transaction", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+				     0);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+				     avg / ratio);
 		else
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
+		char unit_buf[10];
 
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -429,9 +450,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio *= 1000;
 			unit = 'K';
 		}
-
-		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else {
-		fprintf(out, "                                   ");
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 	}
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index da1d11c..f51d94e 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,11 +68,22 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
 extern struct stats walltime_nsecs_stats;
 
+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+			       const char *fmt, double val);
+typedef void (*new_line_t )(void *ctx);
+
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 				    int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr);
+struct perf_stat_output_ctx {
+	void *ctx;
+	print_metric_t print_metric;
+	new_line_t new_line;
+};
+
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out);
 
 void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
 int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
-- 
2.4.3

[PATCH 4/9] perf, tools, stat: Add support for metrics in interval mode

[Andi Kleen]

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

Now that we can modify the metrics printout functions easily,
it's straight forward to support metric printing for interval mode.
All that is needed is to print the time stamp on every new line.
Pass the prefix into the context and print it out.

v2: Move wrong hunk to here.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 27ca063..f13c02d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -489,6 +489,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 
 struct outstate {
 	FILE *fh;
+	const char *prefix;
 };
 
 #define METRIC_LEN  35
@@ -498,6 +499,7 @@ static void new_line_std(void *ctx)
 	struct outstate *os = ctx;
 
 	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
 	if (stat_config.aggr_mode == AGGR_NONE)
 		fprintf(os->fh, "        ");
 	if (stat_config.aggr_mode == AGGR_CORE)
@@ -585,10 +587,14 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
-static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+static void printout(int id, int nr, struct perf_evsel *counter, double uval,
+		     char *prefix)
 {
-	struct outstate os = { .fh = stat_config.output };
 	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = stat_config.output,
+		.prefix = prefix ? prefix : ""
+	};
 	print_metric_t pm = print_metric_std;
 	void (*nl)(void *);
 
@@ -603,7 +609,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval)
 	out.new_line = nl;
 	out.ctx = &os;
 
-	if (!csv_output && !stat_config.interval)
+	if (!csv_output)
 		perf_stat__print_shadow_stats(counter, uval,
 				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
 				cpu_map__id_to_cpu(id),
@@ -663,7 +669,7 @@ static void print_aggr(char *prefix)
 				continue;
 			}
 			uval = val * counter->scale;
-			printout(id, nr, counter, uval);
+			printout(id, nr, counter, uval, prefix);
 			if (!csv_output)
 				print_noise(counter, 1.0);
 
@@ -694,7 +700,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(thread, 0, counter, uval);
+		printout(thread, 0, counter, uval, prefix);
 
 		if (!csv_output)
 			print_noise(counter, 1.0);
@@ -744,7 +750,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	}
 
 	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval);
+	printout(-1, 0, counter, uval, prefix);
 
 	print_noise(counter, avg);
 
@@ -797,7 +803,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		}
 
 		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval);
+		printout(cpu, 0, counter, uval, prefix);
 		if (!csv_output)
 			print_noise(counter, 1.0);
 		print_running(run, ena);
-- 
2.4.3

[PATCH 5/9] perf, tools, stat: Move noise/running printing into printout

[Andi Kleen]

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

Move the running/noise printing into printout to avoid
duplicated code in the callers.

v2: Merged with other patches. Remove unnecessary hunk.
Readd hunk that ended in earlier patch.
v3: Fix noise/running output in CSV mode
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 50 ++++++++---------------------------------------
 1 file changed, 8 insertions(+), 42 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f13c02d..c6835a4 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -588,7 +588,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 }
 
 static void printout(int id, int nr, struct perf_evsel *counter, double uval,
-		     char *prefix)
+		     char *prefix, u64 run, u64 ena, double noise)
 {
 	struct perf_stat_output_ctx out;
 	struct outstate os = {
@@ -614,6 +614,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
 				cpu_map__id_to_cpu(id),
 				&out);
+
+	print_noise(counter, noise);
+	print_running(run, ena);
 }
 
 static void print_aggr(char *prefix)
@@ -669,11 +672,7 @@ static void print_aggr(char *prefix)
 				continue;
 			}
 			uval = val * counter->scale;
-			printout(id, nr, counter, uval, prefix);
-			if (!csv_output)
-				print_noise(counter, 1.0);
-
-			print_running(run, ena);
+			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
 			fputc('\n', output);
 		}
 	}
@@ -700,12 +699,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(thread, 0, counter, uval, prefix);
-
-		if (!csv_output)
-			print_noise(counter, 1.0);
-
-		print_running(run, ena);
+		printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
 		fputc('\n', output);
 	}
 }
@@ -719,7 +713,6 @@ 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]);
-	int scaled = counter->counts->scaled;
 	double uval;
 	double avg_enabled, avg_running;
 
@@ -729,32 +722,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	if (prefix)
 		fprintf(output, "%s", prefix);
 
-	if (scaled == -1 || !counter->supported) {
-		fprintf(output, "%*s%s",
-			csv_output ? 0 : 18,
-			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep);
-		fprintf(output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			counter->unit, csv_sep);
-		fprintf(output, "%*s",
-			csv_output ? 0 : -25,
-			perf_evsel__name(counter));
-
-		if (counter->cgrp)
-			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
-
-		print_running(avg_running, avg_enabled);
-		fputc('\n', output);
-		return;
-	}
-
 	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix);
-
-	print_noise(counter, avg);
-
-	print_running(avg_running, avg_enabled);
+	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
 	fprintf(output, "\n");
 }
 
@@ -803,10 +772,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		}
 
 		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval, prefix);
-		if (!csv_output)
-			print_noise(counter, 1.0);
-		print_running(run, ena);
+		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
 
 		fputc('\n', output);
 	}
-- 
2.4.3

[PATCH 6/9] perf, tools, stat: Implement CSV metrics output

[Andi Kleen]

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

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

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

v2: Split out function argument changes
v3: Reenable metrics for real.
v4: Fix wrong hunk from refactoring.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 67 +++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 65 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c6835a4..a42ec99 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -490,6 +490,8 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 struct outstate {
 	FILE *fh;
 	const char *prefix;
+	int  nfields;
+	u64  run, ena;
 };
 
 #define METRIC_LEN  35
@@ -529,6 +531,49 @@ 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) {
+		fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+		return;
+	}
+	fprintf(out, "%s%" PRIu64 "%s%.2f%s",
+		csv_sep,
+		os->run,
+		csv_sep,
+		os->ena ? 100.0 * os->run / os->ena : 100.0,
+		csv_sep);
+	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", vals, csv_sep, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -600,6 +645,25 @@ 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 = 1;
+		os.nfields += aggr_fields[stat_config.aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+		os.run = run;
+		os.ena = ena;
+	}
+
 	if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
@@ -609,8 +673,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.new_line = nl;
 	out.ctx = &os;
 
-	if (!csv_output)
-		perf_stat__print_shadow_stats(counter, uval,
+	perf_stat__print_shadow_stats(counter, uval,
 				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
 				cpu_map__id_to_cpu(id),
 				&out);
-- 
2.4.3

[PATCH 7/9] perf, tools, stat: Move non counting counter printing to printout

[Andi Kleen]

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

Move the special case printing for non-running counters to
printout, so it can be shared by all the output options.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 73 ++++++++++++++++-------------------------------
 1 file changed, 24 insertions(+), 49 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a42ec99..5057a4b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -664,6 +664,30 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		os.ena = ena;
 	}
 
+	if (run == 0 || ena == 0) {
+		aggr_printout(counter, id, nr);
+
+		fprintf(stat_config.output, "%*s%s",
+			csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			csv_sep);
+
+		fprintf(stat_config.output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			counter->unit, csv_sep);
+
+		fprintf(stat_config.output, "%*s",
+			csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(stat_config.output, "%s%s",
+				csv_sep, counter->cgrp->name);
+
+		print_running(run, ena);
+		return;
+	}
+
 	if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
@@ -710,30 +734,6 @@ static void print_aggr(char *prefix)
 			if (prefix)
 				fprintf(output, "%s", prefix);
 
-			if (run == 0 || ena == 0) {
-				aggr_printout(counter, id, nr);
-
-				fprintf(output, "%*s%s",
-					csv_output ? 0 : 18,
-					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-					csv_sep);
-
-				fprintf(output, "%-*s%s",
-					csv_output ? 0 : unit_width,
-					counter->unit, csv_sep);
-
-				fprintf(output, "%*s",
-					csv_output ? 0 : -25,
-					perf_evsel__name(counter));
-
-				if (counter->cgrp)
-					fprintf(output, "%s%s",
-						csv_sep, counter->cgrp->name);
-
-				print_running(run, ena);
-				fputc('\n', output);
-				continue;
-			}
 			uval = val * counter->scale;
 			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
 			fputc('\n', output);
@@ -809,31 +809,6 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		if (prefix)
 			fprintf(output, "%s", prefix);
 
-		if (run == 0 || ena == 0) {
-			fprintf(output, "CPU%*d%s%*s%s",
-				csv_output ? 0 : -4,
-				perf_evsel__cpus(counter)->map[cpu], csv_sep,
-				csv_output ? 0 : 18,
-				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-				csv_sep);
-
-				fprintf(output, "%-*s%s",
-					csv_output ? 0 : unit_width,
-					counter->unit, csv_sep);
-
-				fprintf(output, "%*s",
-					csv_output ? 0 : -25,
-					perf_evsel__name(counter));
-
-			if (counter->cgrp)
-				fprintf(output, "%s%s",
-					csv_sep, counter->cgrp->name);
-
-			print_running(run, ena);
-			fputc('\n', output);
-			continue;
-		}
-
 		uval = val * counter->scale;
 		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
 
-- 
2.4.3

[PATCH 8/9] perf, tools: Support metrics in --per-core/socket mode

[Andi Kleen]

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

Enable metrics printing in --per-core / --per-socket mode. We need
to save the shadow metrics in a unique place. Always use the first
CPU in the aggregation. Then use the same CPU to retrieve the
shadow value later.

Example output:

% perf stat --per-core -a ./BC1s

 Performance counter stats for 'system wide':

S0-C0           2        2966.020381      task-clock (msec)         #    2.004 CPUs utilized            (100.00%)
S0-C0           2                 49      context-switches          #    0.017 K/sec                    (100.00%)
S0-C0           2                  4      cpu-migrations            #    0.001 K/sec                    (100.00%)
S0-C0           2                467      page-faults               #    0.157 K/sec
S0-C0           2      4,599,061,773      cycles                    #    1.551 GHz                      (100.00%)
S0-C0           2      9,755,886,883      instructions              #    2.12  insn per cycle           (100.00%)
S0-C0           2      1,906,272,125      branches                  #  642.704 M/sec                    (100.00%)
S0-C0           2         81,180,867      branch-misses             #    4.26% of all branches
S0-C1           2        2965.995373      task-clock (msec)         #    2.003 CPUs utilized            (100.00%)
S0-C1           2                 62      context-switches          #    0.021 K/sec                    (100.00%)
S0-C1           2                  8      cpu-migrations            #    0.003 K/sec                    (100.00%)
S0-C1           2                281      page-faults               #    0.095 K/sec
S0-C1           2          6,347,290      cycles                    #    0.002 GHz                      (100.00%)
S0-C1           2          4,654,156      instructions              #    0.73  insn per cycle           (100.00%)
S0-C1           2            947,121      branches                  #    0.319 M/sec                    (100.00%)
S0-C1           2             37,322      branch-misses             #    3.94% of all branches

       1.480409747 seconds time elapsed

v2: Rebase to older patches
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 58 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 51 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5057a4b..564b3a2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -492,6 +492,8 @@ struct outstate {
 	const char *prefix;
 	int  nfields;
 	u64  run, ena;
+	int  id, nr;
+	struct perf_evsel *evsel;
 };
 
 #define METRIC_LEN  35
@@ -502,12 +504,9 @@ static void new_line_std(void *ctx)
 
 	fputc('\n', os->fh);
 	fputs(os->prefix, os->fh);
+	aggr_printout(os->evsel, os->id, os->nr);
 	if (stat_config.aggr_mode == AGGR_NONE)
 		fprintf(os->fh, "        ");
-	if (stat_config.aggr_mode == AGGR_CORE)
-		fprintf(os->fh, "                  ");
-	if (stat_config.aggr_mode == AGGR_SOCKET)
-		fprintf(os->fh, "            ");
 	fprintf(os->fh, "                                                 ");
 }
 
@@ -539,6 +538,7 @@ static void new_line_csv(void *ctx)
 	fputc('\n', os->fh);
 	if (os->prefix)
 		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+	aggr_printout(os->evsel, os->id, os->nr);
 	for (i = 0; i < os->nfields; i++)
 		fputs(csv_sep, os->fh);
 }
@@ -602,6 +602,22 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
+static int first_shadow_cpu(struct perf_evsel *evsel, int id)
+{
+	int i;
+
+	if (aggr_get_id == NULL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+		if (aggr_get_id(evsel_list->cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -638,7 +654,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	struct perf_stat_output_ctx out;
 	struct outstate os = {
 		.fh = stat_config.output,
-		.prefix = prefix ? prefix : ""
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
 	};
 	print_metric_t pm = print_metric_std;
 	void (*nl)(void *);
@@ -699,13 +718,36 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	perf_stat__print_shadow_stats(counter, uval,
 				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
-				cpu_map__id_to_cpu(id),
+				first_shadow_cpu(counter, id),
 				&out);
-
 	print_noise(counter, noise);
 	print_running(run, ena);
 }
 
+static void aggr_update_shadow(void)
+{
+	int cpu, cpu2, s2, id, s;
+	u64 val;
+	struct perf_evsel *counter;
+
+	for (s = 0; s < aggr_map->nr; s++) {
+		id = aggr_map->map[s];
+		evlist__for_each(evsel_list, counter) {
+			val = 0;
+			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 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			val = val * counter->scale;
+			perf_stat__update_shadow_stats(counter, &val,
+						       first_shadow_cpu(counter, id));
+		}
+	}
+}
+
 static void print_aggr(char *prefix)
 {
 	FILE *output = stat_config.output;
@@ -717,6 +759,8 @@ static void print_aggr(char *prefix)
 	if (!(aggr_map || aggr_get_id))
 		return;
 
+	aggr_update_shadow();
+
 	for (s = 0; s < aggr_map->nr; s++) {
 		id = aggr_map->map[s];
 		evlist__for_each(evsel_list, counter) {
-- 
2.4.3

[PATCH 9/9] perf, tools, stat: Document CSV format in manpage

[Andi Kleen]

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

With all the recently added fields in the perf stat CSV output
we should finally document them in the man page. Do this here.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4e074a6..079b141 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -177,6 +177,25 @@ $ perf stat -- make -j
 
  Wall-clock time elapsed:   719.554352 msecs
 
+CSV FORMAT
+----------
+
+With -x, perf stat is able to output a not-quite-CSV format output
+(commas in the output are not put into "")
+
+The fields are in this order:
+
+	- optional usec time stamp in fractions of second (with -I xxx)
+	- unit of the counter value or empty
+	- event name
+	- counter value
+	- run time of counter
+	- percentage of measurement time the counter was running
+	- optional metric value
+	- optional unit of metric
+
+Additional metrics may be printed with all earlier fields being empty.
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-list[1]
-- 
2.4.3

Re: perf, tools: Refactor and support interval and CSV metrics v6

[Jiri Olsa]

On Mon, Nov 02, 2015 at 05:50:19PM -0800, Andi Kleen wrote:
> [v4: Addressed all review feedback.]
> [v3: Addressed all review feedback. Update manpage for CSV. Various changes
>      (see individual patches). Remove some more redundant code 
>      in printout callers.]
> [v2: Addressed (near) all review feedback. No manpage updates so far.
>      Add support for --per-core metrics. Various cleanups.]
> [v3: Everything compiles again. Some more cleanups.]
> [v4: Split up abstract metrics patch into two. Fix bug with earlier
> patch already enabling metrics for CSV/interval. Minor cleanups.
> Man page is included]
> [v5: Fix mainly bisect problems. No regressions introduced by one
> patch and fixed again later. Some minor fixes in addition]
> [v6: Fix running/noise printing patch.]

I like the list.. starting with v4 goes down to v2 and raise again to v6 ;-)

I'll try to check it this week

thanks,
jirka

Re: [PATCH 1/9] perf, tools, stat: Move sw clock metrics printout to stat-shadow

[Jiri Olsa]

On Mon, Nov 02, 2015 at 05:50:20PM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> The sw clock metrics printing was missed in the earlier move to
> stat-shadow of all the other metric printouts. Move it too.
> 
> Acked-by: Jiri Olsa <jolsa@kernel.org>
> v2: Fix metrics printing in this version to make bisect safe.
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  tools/perf/builtin-stat.c     | 8 +++-----
>  tools/perf/util/stat-shadow.c | 5 +++++
>  2 files changed, 8 insertions(+), 5 deletions(-)

Acked-by: Jiri Olsa <jolsa@kernel.org>

thanks,
jirka

Re: [PATCH 2/9] tools, perf, stat: Use common printout faction to avoid duplicated code

[Jiri Olsa]

On Mon, Nov 02, 2015 at 05:50:21PM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Instead of every caller deciding whether to call abs or nsec printout
> do it all in a single central function. No functional changes.
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  tools/perf/builtin-stat.c | 57 +++++++++++++++++------------------------------
>  1 file changed, 20 insertions(+), 37 deletions(-)

Acked-by: Jiri Olsa <jolsa@kernel.org>

thanks,
jirka

Re: [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing

[Jiri Olsa]

On Mon, Nov 02, 2015 at 05:50:22PM -0800, Andi Kleen wrote:

SNIP

> @@ -307,119 +302,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
>  		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
>  		if (total) {
>  			ratio = avg / total;
> -			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
> +			print_metric(ctxp, NULL, "%7.2f ",
> +					"insn per cycle", ratio);
>  		} else {
> -			fprintf(out, "                                   ");
> +			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
>  		}
>  		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);

I think this needs to be in the condition below (check patch below)
otherwise you'll get empty new line in case there's no stalled-cycles events

>  		if (total && avg) {
>  			ratio = total / avg;
> -			fprintf(out, "\n");
> -			if (aggr == AGGR_NONE)
> -				fprintf(out, "        ");
> -			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
> +			print_metric(ctxp, NULL, "%7.2f ",
> +					"stalled cycles per insn",
> +					ratio);
> +		} else {
> +			print_metric(ctxp, NULL, NULL,
> +				     "stalled cycles per insn", 0);
>  		}

also I dont understand the reason for the else case in here

jirka

> -
> -	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
> -			runtime_branches_stats[ctx][cpu].n != 0) {
> -		print_branch_misses(out, cpu, evsel, avg);


---
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 4d8f18581b9b..367e220e93d5 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/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",

Re: [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing

[Jiri Olsa]

On Mon, Nov 02, 2015 at 05:50:22PM -0800, Andi Kleen wrote:

SNIP

>  		evsel->attr.type == PERF_TYPE_HW_CACHE &&
>  		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
>  					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
> -					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
> -			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
> -		print_l1_dcache_misses(out, cpu, evsel, avg);
> +					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
> +		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
> +			print_l1_dcache_misses(cpu, evsel, avg, out);
> +		else
> +			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);

hum, what's the reason for all those else cases
ending up printing nothing?

we have one metric per line anyway right?

jirka

Re: [PATCH 5/9] perf, tools, stat: Move noise/running printing into printout

[Jiri Olsa]

On Mon, Nov 02, 2015 at 05:50:24PM -0800, Andi Kleen wrote:

SNIP

> @@ -729,32 +722,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
>  	if (prefix)
>  		fprintf(output, "%s", prefix);
>  
> -	if (scaled == -1 || !counter->supported) {
> -		fprintf(output, "%*s%s",
> -			csv_output ? 0 : 18,
> -			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
> -			csv_sep);
> -		fprintf(output, "%-*s%s",
> -			csv_output ? 0 : unit_width,
> -			counter->unit, csv_sep);
> -		fprintf(output, "%*s",
> -			csv_output ? 0 : -25,
> -			perf_evsel__name(counter));

so this changed current 'not supported' output:

   <not supported>      stalled-cycles-frontend  
   <not supported>      stalled-cycles-backend   


into

                 0      stalled-cycles-frontend                                     
                 0      stalled-cycles-backend    #   0.00% backend cycles idle     

> -
> -		if (counter->cgrp)
> -			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);

haven't tried with cgroup, but I think that removing
above hunk will not do any good to it..

jirka

> -
> -		print_running(avg_running, avg_enabled);
> -		fputc('\n', output);
> -		return;
> -	}
> -
>  	uval = avg * counter->scale;
> -	printout(-1, 0, counter, uval, prefix);
> -

SNIP

Re: [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing

[Andi Kleen]

On Wed, Nov 04, 2015 at 09:42:48AM +0100, Jiri Olsa wrote:
> On Mon, Nov 02, 2015 at 05:50:22PM -0800, Andi Kleen wrote:
> 
> SNIP
> 
> >  		evsel->attr.type == PERF_TYPE_HW_CACHE &&
> >  		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
> >  					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
> > -					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
> > -			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
> > -		print_l1_dcache_misses(out, cpu, evsel, avg);
> > +					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
> > +		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
> > +			print_l1_dcache_misses(cpu, evsel, avg, out);
> > +		else
> > +			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
> 
> hum, what's the reason for all those else cases
> ending up printing nothing?
> 
> we have one metric per line anyway right?

There can be stuff after the metric, need to print spaces then to get
the correct indentation.

Also it's needed for the metrics only patch (posted separately) so
that it can catch all column headers, even if some are missing initially.

-Andi

-- 
ak@linux.intel.com -- Speaking for myself only.

Re: perf, tools: Refactor and support interval and CSV metrics v6

[Andi Kleen]

On Tue, Nov 03, 2015 at 08:46:16AM +0100, Jiri Olsa wrote:
> On Mon, Nov 02, 2015 at 05:50:19PM -0800, Andi Kleen wrote:
> > [v4: Addressed all review feedback.]
> > [v3: Addressed all review feedback. Update manpage for CSV. Various changes
> >      (see individual patches). Remove some more redundant code 
> >      in printout callers.]
> > [v2: Addressed (near) all review feedback. No manpage updates so far.
> >      Add support for --per-core metrics. Various cleanups.]
> > [v3: Everything compiles again. Some more cleanups.]
> > [v4: Split up abstract metrics patch into two. Fix bug with earlier
> > patch already enabling metrics for CSV/interval. Minor cleanups.
> > Man page is included]
> > [v5: Fix mainly bisect problems. No regressions introduced by one
> > patch and fixed again later. Some minor fixes in addition]
> > [v6: Fix running/noise printing patch.]
> 
> I like the list.. starting with v4 goes down to v2 and raise again to v6 ;-)

Oops. I switched order at some point. Will fix.

-Andi
> 
> I'll try to check it this week
> 
> thanks,
> jirka
> 

-- 
ak@linux.intel.com -- Speaking for myself only.

Re: [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing

[Jiri Olsa]

On Thu, Nov 05, 2015 at 03:43:07AM +0100, Andi Kleen wrote:
> On Wed, Nov 04, 2015 at 09:42:48AM +0100, Jiri Olsa wrote:
> > On Mon, Nov 02, 2015 at 05:50:22PM -0800, Andi Kleen wrote:
> > 
> > SNIP
> > 
> > >  		evsel->attr.type == PERF_TYPE_HW_CACHE &&
> > >  		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
> > >  					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
> > > -					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
> > > -			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
> > > -		print_l1_dcache_misses(out, cpu, evsel, avg);
> > > +					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
> > > +		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
> > > +			print_l1_dcache_misses(cpu, evsel, avg, out);
> > > +		else
> > > +			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
> > 
> > hum, what's the reason for all those else cases
> > ending up printing nothing?
> > 
> > we have one metric per line anyway right?
> 
> There can be stuff after the metric, need to print spaces then to get
> the correct indentation.

what stuff?

jirka

> 
> Also it's needed for the metrics only patch (posted separately) so
> that it can catch all column headers, even if some are missing initially.
> 
> -Andi
> 
> -- 
> ak@linux.intel.com -- Speaking for myself only.

Re: [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing

[Andi Kleen]

> > There can be stuff after the metric, need to print spaces then to get
> > the correct indentation.
> 
> what stuff?

The stddev (with -rX) or the enabled/run ratio.

-Andi

-- 
ak@linux.intel.com -- Speaking for myself only.

[tip:perf/urgent] perf stat: Move sw clock metrics printout to stat-shadow

[tip-bot for Andi Kleen]

Commit-ID:  4579ecc8b3e0c611b5c8f6ca7f7b07d1412d8a7b
Gitweb:     http://git.kernel.org/tip/4579ecc8b3e0c611b5c8f6ca7f7b07d1412d8a7b
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Mon, 2 Nov 2015 17:50:20 -0800
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 4 Nov 2015 15:11:41 -0300

perf stat: Move sw clock metrics printout to stat-shadow

The sw clock metrics printing was missed in the earlier move to
stat-shadow of all the other metric printouts. Move it too.

v2: Fix metrics printing in this version to make bisect safe.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1446515428-7450-2-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c     | 8 +++-----
 tools/perf/util/stat-shadow.c | 5 +++++
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2f438f7..8a78895 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -493,6 +493,7 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	double msecs = avg / 1e6;
 	const char *fmt_v, *fmt_n;
 	char name[25];
+	int cpu = cpu_map__id_to_cpu(id);
 
 	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
 	fmt_n = csv_output ? "%s" : "%-25s";
@@ -517,11 +518,8 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	if (csv_output || stat_config.interval)
 		return;
 
-	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		fprintf(output, " # %8.3f CPUs utilized          ",
-			avg / avg_stats(&walltime_nsecs_stats));
-	else
-		fprintf(output, "                                   ");
+	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
+				      stat_config.aggr_mode);
 }
 
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2a5d8d7..6ac0314 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -413,6 +413,11 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
+			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+		else
+			fprintf(out, "                                   ");
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 

[tip:perf/urgent] perf stat: Use common printout function to avoid duplicated code

[tip-bot for Andi Kleen]

Commit-ID:  eedfcb4bc5f0185a14fc9e1e5a9770ad833ea5a4
Gitweb:     http://git.kernel.org/tip/eedfcb4bc5f0185a14fc9e1e5a9770ad833ea5a4
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Mon, 2 Nov 2015 17:50:21 -0800
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 4 Nov 2015 15:12:04 -0300

perf stat: Use common printout function to avoid duplicated code

Instead of every caller deciding whether to call abs or nsec printout
do it all in a single central function. No functional changes.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1446515428-7450-3-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 57 +++++++++++++++++------------------------------
 1 file changed, 20 insertions(+), 37 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8a78895..b74ee0f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -493,7 +493,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	double msecs = avg / 1e6;
 	const char *fmt_v, *fmt_n;
 	char name[25];
-	int cpu = cpu_map__id_to_cpu(id);
 
 	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
 	fmt_n = csv_output ? "%s" : "%-25s";
@@ -514,12 +513,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-
-	if (csv_output || stat_config.interval)
-		return;
-
-	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
-				      stat_config.aggr_mode);
 }
 
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
@@ -527,7 +520,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	FILE *output = stat_config.output;
 	double sc =  evsel->scale;
 	const char *fmt;
-	int cpu = cpu_map__id_to_cpu(id);
 
 	if (csv_output) {
 		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
@@ -540,9 +532,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	aggr_printout(evsel, id, nr);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
-
 	fprintf(output, fmt, avg, csv_sep);
 
 	if (evsel->unit)
@@ -554,12 +543,24 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+}
 
-	if (csv_output || stat_config.interval)
-		return;
+static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+{
+	int cpu = cpu_map__id_to_cpu(id);
+
+	if (stat_config.aggr_mode == AGGR_GLOBAL)
+		cpu = 0;
+
+	if (nsec_counter(counter))
+		nsec_printout(id, nr, counter, uval);
+	else
+		abs_printout(id, nr, counter, uval);
 
-	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
-				      stat_config.aggr_mode);
+	if (!csv_output && !stat_config.interval)
+		perf_stat__print_shadow_stats(stat_config.output, counter,
+					      uval, cpu,
+					      stat_config.aggr_mode);
 }
 
 static void print_aggr(char *prefix)
@@ -615,12 +616,7 @@ static void print_aggr(char *prefix)
 				continue;
 			}
 			uval = val * counter->scale;
-
-			if (nsec_counter(counter))
-				nsec_printout(id, nr, counter, uval);
-			else
-				abs_printout(id, nr, counter, uval);
-
+			printout(id, nr, counter, uval);
 			if (!csv_output)
 				print_noise(counter, 1.0);
 
@@ -651,11 +647,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-
-		if (nsec_counter(counter))
-			nsec_printout(thread, 0, counter, uval);
-		else
-			abs_printout(thread, 0, counter, uval);
+		printout(thread, 0, counter, uval);
 
 		if (!csv_output)
 			print_noise(counter, 1.0);
@@ -705,11 +697,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	}
 
 	uval = avg * counter->scale;
-
-	if (nsec_counter(counter))
-		nsec_printout(-1, 0, counter, uval);
-	else
-		abs_printout(-1, 0, counter, uval);
+	printout(-1, 0, counter, uval);
 
 	print_noise(counter, avg);
 
@@ -762,12 +750,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		}
 
 		uval = val * counter->scale;
-
-		if (nsec_counter(counter))
-			nsec_printout(cpu, 0, counter, uval);
-		else
-			abs_printout(cpu, 0, counter, uval);
-
+		printout(cpu, 0, counter, uval);
 		if (!csv_output)
 			print_noise(counter, 1.0);
 		print_running(run, ena);

[PATCH 3/9] perf, tools, stat: Abstract stat metrics printing

[Andi Kleen]

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

Abstract the printing of shadow metrics. Instead of every
metric calling fprintf directly and taking care of indentation,
use two call backs: one to print metrics and another to
start a new line.

This will allow adding metrics to CSV mode and also
using them for other purposes.

The computation of padding is now done in the central
callback, instead of every metric doing it manually.
This makes it easier to add new metrics.

v2: Refactor functions, printout now does more. Move
shadow printing. Improve fallback callbacks. Don't
use void * callback data.
v3: Remove unnecessary hunk. Add typedef for new_line
v4: Remove unnecessary hunk. Don't print metrics for CSV/interval
mode yet.  Move printout change to separate patch.
v5: Fix bisect bugs. Avoid bogus frontend cycles printing.
Fix indentation in different aggregation modes.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     |  59 ++++++++++--
 tools/perf/util/stat-shadow.c | 211 +++++++++++++++++++++++-------------------
 tools/perf/util/stat.h        |  15 ++-
 3 files changed, 182 insertions(+), 103 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 14b6a8a..9fb8aed 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -485,6 +485,46 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 	}
 }
 
+struct outstate {
+	FILE *fh;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(void *ctx)
+{
+	struct outstate *os = ctx;
+
+	fputc('\n', os->fh);
+	if (stat_config.aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	if (stat_config.aggr_mode == AGGR_CORE)
+		fprintf(os->fh, "                  ");
+	if (stat_config.aggr_mode == AGGR_SOCKET)
+		fprintf(os->fh, "            ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -545,20 +585,27 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 static void printout(int id, int nr, struct perf_evsel *counter, double uval)
 {
-	int cpu = cpu_map__id_to_cpu(id);
+	struct outstate os = { .fh = stat_config.output };
+	struct perf_stat_output_ctx out;
+	print_metric_t pm = print_metric_std;
+	void (*nl)(void *);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
+	nl = new_line_std;
 
 	if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
 
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+
 	if (!csv_output && !stat_config.interval)
-		perf_stat__print_shadow_stats(stat_config.output, counter,
-					      uval, cpu,
-					      stat_config.aggr_mode);
+		perf_stat__print_shadow_stats(counter, uval,
+				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+				cpu_map__id_to_cpu(id),
+				&out);
 }
 
 static void print_aggr(char *prefix)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac0314..4d8f185 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
+static void print_stalled_cycles_frontend(int cpu,
 					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
+					  __maybe_unused, double avg,
+					  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -152,14 +153,17 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " frontend cycles idle   ");
+	if (ratio)
+		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+				  ratio);
+	else
+		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(FILE *out, int cpu,
+static void print_stalled_cycles_backend(int cpu,
 					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
+					 __maybe_unused, double avg,
+					 struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -172,14 +176,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " backend  cycles idle   ");
+	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(FILE *out, int cpu,
+static void print_branch_misses(int cpu,
 				struct perf_evsel *evsel __maybe_unused,
-				double avg)
+				double avg,
+				struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -192,14 +195,13 @@ static void print_branch_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all branches        ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(FILE *out, int cpu,
+static void print_l1_dcache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -212,14 +214,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-dcache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(FILE *out, int cpu,
+static void print_l1_icache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -231,15 +232,13 @@ static void print_l1_icache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-icache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(FILE *out, int cpu,
+static void print_dtlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -251,15 +250,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all dTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(FILE *out, int cpu,
+static void print_itlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -271,15 +268,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all iTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(FILE *out, int cpu,
+static void print_ll_cache_misses(int cpu,
 				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
+				  double avg,
+				  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -291,15 +286,15 @@ static void print_ll_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all LL-cache hits   ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out)
 {
+	void *ctxp = out->ctx;
+	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	int ctx = evsel_context(evsel);
 
@@ -307,119 +302,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"insn per cycle", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 		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) {
 			ratio = total / avg;
-			fprintf(out, "\n");
-			if (aggr == AGGR_NONE)
-				fprintf(out, "        ");
-			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"stalled cycles per insn",
+					ratio);
+		} else {
+			print_metric(ctxp, NULL, NULL,
+				     "stalled cycles per insn", 0);
 		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+		if (runtime_branches_stats[ctx][cpu].n != 0)
+			print_branch_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
-		print_l1_dcache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+			print_l1_dcache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_icache_stats[ctx][cpu].n != 0) {
-		print_l1_icache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+			print_l1_icache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
-		print_dtlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+			print_dtlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
-		print_itlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+			print_itlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_ll_cache_stats[ctx][cpu].n != 0) {
-		print_ll_cache_misses(out, cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+			print_ll_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+		if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.3f %%",
+				     "of all cache refs", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+		print_stalled_cycles_frontend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(out, cpu, evsel, avg);
+		print_stalled_cycles_backend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " # %8.3f GHz                    ", ratio);
+			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
+			print_metric(ctxp, NULL,
+					"%7.2f%%", "transactional cycles",
+					100.0 * (avg / total));
+		else
+			print_metric(ctxp, NULL, NULL, "transactional cycles",
+				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% aborted cycles         ",
+			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
-	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		else
+			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
-	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.0f",
+				     "cycles / transaction", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+				     0);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+				     avg / ratio);
 		else
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
+		char unit_buf[10];
 
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -429,9 +450,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio *= 1000;
 			unit = 'K';
 		}
-
-		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else {
-		fprintf(out, "                                   ");
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 	}
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index da1d11c..f51d94e 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,11 +68,22 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
 extern struct stats walltime_nsecs_stats;
 
+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+			       const char *fmt, double val);
+typedef void (*new_line_t )(void *ctx);
+
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 				    int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr);
+struct perf_stat_output_ctx {
+	void *ctx;
+	print_metric_t print_metric;
+	new_line_t new_line;
+};
+
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out);
 
 void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
 int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
-- 
2.4.3

[PATCH 3/9] perf, tools, stat: Abstract stat metrics printing

[Andi Kleen]

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

Abstract the printing of shadow metrics. Instead of every
metric calling fprintf directly and taking care of indentation,
use two call backs: one to print metrics and another to
start a new line.

This will allow adding metrics to CSV mode and also
using them for other purposes.

The computation of padding is now done in the central
callback, instead of every metric doing it manually.
This makes it easier to add new metrics.

v2: Refactor functions, printout now does more. Move
shadow printing. Improve fallback callbacks. Don't
use void * callback data.
v3: Remove unnecessary hunk. Add typedef for new_line
v4: Remove unnecessary hunk. Don't print metrics for CSV/interval
mode yet.  Move printout change to separate patch.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     |  63 +++++++++++--
 tools/perf/util/stat-shadow.c | 212 +++++++++++++++++++++++-------------------
 tools/perf/util/stat.h        |  15 ++-
 3 files changed, 185 insertions(+), 105 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6910cd3..bb6b186 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -484,6 +484,47 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 	}
 }
 
+struct outstate {
+	FILE *fh;
+};
+
+#define BASE_INDENT 41
+#define AGGR_INDENT  8
+#define METRIC_LEN  35
+#define NA_INDENT   16
+
+static void new_line_no_aggr_std(void *ctx)
+{
+	struct outstate *os = ctx;
+	fprintf(os->fh, "\n%*s", BASE_INDENT + NA_INDENT, "");
+}
+
+static void new_line_std(void *ctx)
+{
+	struct outstate *os = ctx;
+	fprintf(os->fh, "\n%-*s", BASE_INDENT + AGGR_INDENT, "");
+}
+
+static void print_metric_std(void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+
+	if (unit == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -544,20 +585,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 static void printout(int id, int nr, struct perf_evsel *counter, double uval)
 {
-	int cpu = cpu_map__id_to_cpu(id);
+	struct outstate os = { .fh = stat_config.output };
+	struct perf_stat_output_ctx out;
+	print_metric_t pm = print_metric_std;
+	void (*nl)(void *);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
+	if (stat_config.aggr_mode == AGGR_NONE)
+		nl = new_line_no_aggr_std;
+	else
+		nl = new_line_std;
 
 	if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
 
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+
 	if (!csv_output && !stat_config.interval)
-		perf_stat__print_shadow_stats(stat_config.output, counter,
-					      uval, cpu,
-					      stat_config.aggr_mode);
+		perf_stat__print_shadow_stats(counter, uval,
+				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+				cpu_map__id_to_cpu(id),
+				&out);
 }
 
 static void print_aggr(char *prefix)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 625ab3b..d7d27b5 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
+static void print_stalled_cycles_frontend(int cpu,
 					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
+					  __maybe_unused, double avg,
+					  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -152,14 +153,13 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " frontend cycles idle   ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle", ratio);
 }
 
-static void print_stalled_cycles_backend(FILE *out, int cpu,
+static void print_stalled_cycles_backend(int cpu,
 					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
+					 __maybe_unused, double avg,
+					 struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -172,14 +172,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " backend  cycles idle   ");
+	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(FILE *out, int cpu,
+static void print_branch_misses(int cpu,
 				struct perf_evsel *evsel __maybe_unused,
-				double avg)
+				double avg,
+				struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -192,14 +191,13 @@ static void print_branch_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all branches        ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(FILE *out, int cpu,
+static void print_l1_dcache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -212,14 +210,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-dcache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(FILE *out, int cpu,
+static void print_l1_icache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -231,15 +228,13 @@ static void print_l1_icache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-icache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(FILE *out, int cpu,
+static void print_dtlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -251,15 +246,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all dTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(FILE *out, int cpu,
+static void print_itlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -271,15 +264,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all iTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(FILE *out, int cpu,
+static void print_ll_cache_misses(int cpu,
 				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
+				  double avg,
+				  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -291,15 +282,15 @@ static void print_ll_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all LL-cache hits   ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out)
 {
+	void *ctxp = out->ctx;
+	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	int ctx = evsel_context(evsel);
 
@@ -307,117 +298,144 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"insn per cycle", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
 		if (total && avg) {
 			ratio = total / avg;
-			fprintf(out, "\n");
-			if (aggr == AGGR_NONE)
-				fprintf(out, "        ");
-			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+			out->new_line(ctxp);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"stalled cycles per insn",
+					ratio);
+		} else {
+			print_metric(ctxp, NULL, NULL,
+				     "stalled cycles per insn", 0);
 		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+		if (runtime_branches_stats[ctx][cpu].n != 0)
+			print_branch_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
-		print_l1_dcache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+			print_l1_dcache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_icache_stats[ctx][cpu].n != 0) {
-		print_l1_icache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+			print_l1_icache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
-		print_dtlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+			print_dtlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
-		print_itlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+			print_itlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_ll_cache_stats[ctx][cpu].n != 0) {
-		print_ll_cache_misses(out, cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+			print_ll_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+		if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.3f %%",
+				     "of all cache refs", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+		print_stalled_cycles_frontend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(out, cpu, evsel, avg);
+		print_stalled_cycles_backend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " # %8.3f GHz                    ", ratio);
+			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
+			print_metric(ctxp, NULL,
+					"%7.2f%%", "transactional cycles",
+					100.0 * (avg / total));
+		else
+			print_metric(ctxp, NULL, NULL, "transactional cycles",
+				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% aborted cycles         ",
+			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
-	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		else
+			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
-	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.0f",
+				     "cycles / transaction", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+				     0);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
-
-		fprintf(out, " # %8.0f cycles / elision       ", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) &&
-		   (ratio = avg_stats(&walltime_nsecs_stats)) != 0) {
-		fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
+	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
+			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+				     avg / ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
+		char unit_buf[10];
 
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -427,9 +445,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio *= 1000;
 			unit = 'K';
 		}
-
-		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else {
-		fprintf(out, "                                   ");
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 	}
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 62448c8..e1899f6 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -67,11 +67,22 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
 extern struct stats walltime_nsecs_stats;
 
+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+			       const char *fmt, double val);
+typedef void (*new_line_t )(void *ctx);
+
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 				    int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr);
+struct perf_stat_output_ctx {
+	void *ctx;
+	print_metric_t print_metric;
+	new_line_t new_line;
+};
+
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out);
 
 void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
 int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
-- 
2.4.3