perf, tools: Refactor and support interval and CSV metrics v3

perf, tools: Refactor and support interval and CSV metrics v3

[Andi Kleen]

[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. Updated to latest tip tree.]

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-3

[PATCH 1/7] 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.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     | 9 ---------
 tools/perf/util/stat-shadow.c | 4 ++++
 2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a054ddc..fac0c50 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -509,15 +509,6 @@ 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;
-
-	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		fprintf(output, " # %8.3f CPUs utilized          ",
-			avg / avg_stats(&walltime_nsecs_stats));
-	else
-		fprintf(output, "                                   ");
 }
 
 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..fc970db 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -413,6 +413,10 @@ 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) &&
+		   (ratio = avg_stats(&walltime_nsecs_stats)) != 0) {
+		fprintf(output, " # %8.3f CPUs utilized          ",
+				     avg / ratio);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 
-- 
2.4.3

Re: [PATCH 1/7] perf, tools, stat: Move sw clock metrics printout to stat-shadow

[Jiri Olsa]

On Fri, Aug 07, 2015 at 05:51:53PM -0700, 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.
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  tools/perf/builtin-stat.c     | 9 ---------
>  tools/perf/util/stat-shadow.c | 4 ++++
>  2 files changed, 4 insertions(+), 9 deletions(-)
> 
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index a054ddc..fac0c50 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -509,15 +509,6 @@ 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;
> -
> -	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
> -		fprintf(output, " # %8.3f CPUs utilized          ",
> -			avg / avg_stats(&walltime_nsecs_stats));
> -	else
> -		fprintf(output, "                                   ");
>  }
>  
>  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..fc970db 100644
> --- a/tools/perf/util/stat-shadow.c
> +++ b/tools/perf/util/stat-shadow.c
> @@ -413,6 +413,10 @@ 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) &&
> +		   (ratio = avg_stats(&walltime_nsecs_stats)) != 0) {
> +		fprintf(output, " # %8.3f CPUs utilized          ",
> +				     avg / ratio);

s/output/out/           ^^^^


  CC       util/stat-shadow.o
util/stat-shadow.c: In function ‘perf_stat__print_shadow_stats’:
util/stat-shadow.c:418:11: error: ‘output’ undeclared (first use in this function)
   fprintf(output, " # %8.3f CPUs utilized          ",


jirka

[PATCH 2/7] 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.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     |  96 +++++++++++++++++--------
 tools/perf/util/stat-shadow.c | 158 ++++++++++++++++++++++--------------------
 tools/perf/util/stat.h        |  10 ++-
 3 files changed, 157 insertions(+), 107 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index fac0c50..bf6c02c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -483,6 +483,47 @@ 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;
@@ -516,7 +557,6 @@ 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";
@@ -529,9 +569,6 @@ 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)
@@ -543,12 +580,30 @@ 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)
+{
+	struct outstate os = { .fh = output };
+	print_metric_t pm = print_metric_std;
+	void (*nl)(void *);
 
-	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
-				      stat_config.aggr_mode);
+	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);
+
+	perf_stat__print_shadow_stats(counter, uval,
+				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+				cpu_map__id_to_cpu(id),
+				pm,
+				nl,
+				&os);
 }
 
 static void print_aggr(char *prefix)
@@ -605,12 +660,7 @@ 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);
 
@@ -641,11 +691,7 @@ 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);
@@ -695,11 +741,7 @@ 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);
 
@@ -752,11 +794,7 @@ 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);
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index fc970db..073e66f7 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,11 @@ 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,
+					  print_metric_t print_metric,
+					  void *ctxp)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -152,14 +154,14 @@ 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   ");
+	print_metric(ctxp, 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,
+					 print_metric_t print_metric,
+					 void *ctxp)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -172,14 +174,14 @@ 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   ");
+	print_metric(ctxp, 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,
+				print_metric_t print_metric,
+				void *ctxp)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -192,14 +194,14 @@ 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        ");
+	print_metric(ctxp, 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,
+				   print_metric_t print_metric,
+				   void *ctxp)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -212,14 +214,14 @@ 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  ");
+	print_metric(ctxp, 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,
+				   print_metric_t print_metric,
+				   void *ctxp)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -231,15 +233,14 @@ 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  ");
+	print_metric(ctxp, 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,
+				    print_metric_t print_metric,
+				    void *ctxp)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -251,15 +252,14 @@ 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 ");
+	print_metric(ctxp, 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,
+				    print_metric_t print_metric,
+				    void *ctxp)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -271,15 +271,14 @@ 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 ");
+	print_metric(ctxp, 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,
+				  print_metric_t print_metric,
+				  void *ctxp)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -291,14 +290,14 @@ 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   ");
+	print_metric(ctxp, 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,
+				   print_metric_t print_metric,
+				   void (*new_line)(void *ctx),
+				   void *ctxp)
 {
 	double total, ratio = 0.0, total2;
 	int ctx = evsel_context(evsel);
@@ -307,59 +306,60 @@ 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, NULL, 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);
+			new_line(ctxp);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"stalled cycles per insn",
+					ratio);
 		}
 
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
 			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);
+		print_branch_misses(cpu, evsel, avg, print_metric, ctxp);
 	} 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);
+		print_l1_dcache_misses(cpu, evsel, avg, print_metric, ctxp);
 	} 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);
+		print_l1_icache_misses(cpu, evsel, avg, print_metric, ctxp);
 	} 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);
+		print_dtlb_cache_misses(cpu, evsel, avg, print_metric, ctxp);
 	} 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);
+		print_itlb_cache_misses(cpu, evsel, avg, print_metric, ctxp);
 	} 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);
+		print_ll_cache_misses(cpu, evsel, avg, print_metric, ctxp);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
 			runtime_cacherefs_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
@@ -367,36 +367,41 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+		print_metric(ctxp, NULL, "%8.3f %%",
+				"of all cache refs", ratio);
 	} 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, print_metric,
+				ctxp);
 	} 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, print_metric,
+				ctxp);
 	} 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, NULL, 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, NULL, 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
+			print_metric(ctxp, NULL, NULL, NULL, 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
 		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
@@ -404,7 +409,8 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
+		print_metric(ctxp, NULL, "%8.0f",
+				"cycles / transaction", ratio);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
 		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
@@ -412,13 +418,13 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		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) &&
 		   (ratio = avg_stats(&walltime_nsecs_stats)) != 0) {
-		fprintf(output, " # %8.3f CPUs utilized          ",
-				     avg / ratio);
+		print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", avg / ratio);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
+		char unit_buf[10];
 
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -428,9 +434,9 @@ 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 0b897b0..a492e64 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,11 +90,17 @@ 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);
+
 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);
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   print_metric_t print_metric,
+				   void (*new_line)(void *ctx),
+				   void *ctx);
 
 struct perf_counts *perf_counts__new(int ncpus, int nthreads);
 void perf_counts__delete(struct perf_counts *counts);
-- 
2.4.3

Re: [PATCH 2/7] perf, tools, stat: Abstract stat metrics printing

[Jiri Olsa]

On Fri, Aug 07, 2015 at 05:51:54PM -0700, Andi Kleen wrote:

SNIP

> +
>  static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
>  {
>  	FILE *output = stat_config.output;
> @@ -516,7 +557,6 @@ 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";
> @@ -529,9 +569,6 @@ 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)
> @@ -543,12 +580,30 @@ 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)
> +{
> +	struct outstate os = { .fh = output };

hum..

  CC       builtin-stat.o
builtin-stat.c: In function ‘printout’:
builtin-stat.c:587:31: error: ‘output’ undeclared (first use in this function)
  struct outstate os = { .fh = output };
                               ^

jirka

[PATCH 3/7] 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.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index bf6c02c..30c2046 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -485,6 +485,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 
 struct outstate {
 	FILE *fh;
+	const char *prefix;
 };
 
 #define BASE_INDENT 41
@@ -495,13 +496,13 @@ struct outstate {
 static void new_line_no_aggr_std(void *ctx)
 {
 	struct outstate *os = ctx;
-	fprintf(os->fh, "\n%*s", BASE_INDENT + NA_INDENT, "");
+	fprintf(os->fh, "\n%s%-*s", os->prefix, BASE_INDENT + NA_INDENT, "");
 }
 
 static void new_line_std(void *ctx)
 {
 	struct outstate *os = ctx;
-	fprintf(os->fh, "\n%-*s", BASE_INDENT + AGGR_INDENT, "");
+	fprintf(os->fh, "\n%s%-*s", os->prefix, BASE_INDENT + AGGR_INDENT, "");
 }
 
 static void print_metric_std(void *ctx, const char *color, const char *fmt,
@@ -582,9 +583,13 @@ 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 = output };
+	struct outstate os = {
+		.fh = stat_config.output,
+		.prefix = prefix ? prefix : ""
+	};
 	print_metric_t pm = print_metric_std;
 	void (*nl)(void *);
 
@@ -660,7 +665,7 @@ 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);
 
@@ -691,7 +696,7 @@ 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);
@@ -741,7 +746,7 @@ 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);
 
@@ -794,7 +799,7 @@ 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);
-- 
2.4.3

[PATCH 4/7] 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.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 33 +++++++++++----------------------
 1 file changed, 11 insertions(+), 22 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 30c2046..0174aca 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -584,7 +584,7 @@ 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 outstate os = {
 		.fh = stat_config.output,
@@ -609,6 +609,12 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 				pm,
 				nl,
 				&os);
+
+	if (!csv_output) {
+		print_noise(counter, noise);
+		if (run != ena)
+			fprintf(stat_config.output, "  (%.2f%%)", 100.0 * run / ena);
+	}
 }
 
 static void print_aggr(char *prefix)
@@ -665,11 +671,7 @@ 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);
 		}
 	}
@@ -696,12 +698,7 @@ 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);
 	}
 }
@@ -746,11 +743,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	}
 
 	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");
 }
 
@@ -799,11 +792,7 @@ 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 5/7] 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
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0174aca..7801665 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -486,6 +486,8 @@ 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 BASE_INDENT 41
@@ -525,6 +527,49 @@ 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;
@@ -598,6 +643,25 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	else
 		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
-- 
2.4.3

[PATCH 6/7] 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 7801665..d777bb6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -662,6 +662,30 @@ 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);
@@ -830,31 +830,6 @@ 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 7/7] 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

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 62 ++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 58 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d777bb6..ea5298a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -488,6 +488,8 @@ struct outstate {
 	const char *prefix;
 	int  nfields;
 	u64  run, ena;
+	int  id, nr;
+	struct perf_evsel *evsel;
 };
 
 #define BASE_INDENT 41
@@ -498,13 +500,19 @@ struct outstate {
 static void new_line_no_aggr_std(void *ctx)
 {
 	struct outstate *os = ctx;
-	fprintf(os->fh, "\n%s%-*s", os->prefix, BASE_INDENT + NA_INDENT, "");
+
+	fprintf(os->fh, "\n%s", os->prefix);
+	aggr_printout(os->evsel, os->id, os->nr);
+	fprintf(os->fh, "%-*s", BASE_INDENT + NA_INDENT, "");
 }
 
 static void new_line_std(void *ctx)
 {
 	struct outstate *os = ctx;
-	fprintf(os->fh, "\n%s%-*s", os->prefix, BASE_INDENT + AGGR_INDENT, "");
+
+	fprintf(os->fh, "\n%s", os->prefix);
+	aggr_printout(os->evsel, os->id, os->nr);
+	fprintf(os->fh, "%-*s", BASE_INDENT + AGGR_INDENT, "");
 }
 
 static void print_metric_std(void *ctx, const char *color, const char *fmt,
@@ -535,6 +543,7 @@ 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);
 }
@@ -598,6 +607,22 @@ 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;
@@ -633,7 +658,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 {
 	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 *);
@@ -693,7 +721,7 @@ 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),
 				pm,
 				nl,
 				&os);
@@ -705,6 +733,30 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	}
 }
 
+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;
@@ -716,6 +768,8 @@ 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