Skip to contentSkip to conversation

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

PATCH In review Andi Kleen 3 participants 22 messages Nov 3, 2015 – Nov 8, 2015 perf events

lore
Share & tools
lore

Andi Kleen

author
#0 lore raw

[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

author
#1 lore raw

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

From: Andi Kleen <[email protected]>

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 <[email protected]>

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

Signed-off-by Andi Kleen <[email protected]>
---
 tools/perf/builtin-stat.c     | 8 +++-----
 tools/perf/util/stat-shadow.c | 5 +++++
 2 files changed, 8 insertions(+), 5 deletions(-)
tools/perf/builtin-stat.c +3 -5
index 2f438f7..8a78895 100644
@@ -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)
tools/perf/util/stat-shadow.c +5 -0
index 2a5d8d7..6ac0314 100644
@@ -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';
Signature · 1 line
2.4.3
Acked-by on v1 1/9
#2 lore raw

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

Quoted 5 lines · Andi Kleen

From: Andi Kleen <[email protected]>

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

Quoted 7 lines
Acked-by Jiri Olsa <[email protected]>

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

Signed-off-by Andi Kleen <[email protected]>
---
 tools/perf/builtin-stat.c     | 8 +++-----
 tools/perf/util/stat-shadow.c | 5 +++++
 2 files changed, 8 insertions(+), 5 deletions(-)
Acked-by Jiri Olsa <[email protected]>

thanks,
jirka

merge bot
#3 lore raw

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

In reply to Andi Kleen
perf stat: Move sw clock metrics printout to stat-shadow
Commit-ID:  4579ecc8b3e0c611b5c8f6ca7f7b07d1412d8a7b
Gitweb:     http://git.kernel.org/tip/4579ecc8b3e0c611b5c8f6ca7f7b07d1412d8a7b
Author:     Andi Kleen <[email protected]>
AuthorDate: Mon, 2 Nov 2015 17:50:20 -0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
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 <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Link http://lkml.kernel.org/r/[email protected] open here
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
---
 tools/perf/builtin-stat.c     | 8 +++-----
 tools/perf/util/stat-shadow.c | 5 +++++
 2 files changed, 8 insertions(+), 5 deletions(-)
tools/perf/builtin-stat.c +3 -5
index 2f438f7..8a78895 100644
@@ -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)
tools/perf/util/stat-shadow.c +5 -0
index 2a5d8d7..6ac0314 100644
@@ -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';
author
#4 lore raw

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

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 tools/perf/builtin-stat.c | 57 +++++++++++++++++------------------------------
 1 file changed, 20 insertions(+), 37 deletions(-)
tools/perf/builtin-stat.c +20 -37
index 8a78895..b74ee0f 100644
@@ -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);
Signature · 1 line
2.4.3
Acked-by on v1 2/9
#5 lore raw

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

Quoted 9 lines · Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 tools/perf/builtin-stat.c | 57 +++++++++++++++++------------------------------
 1 file changed, 20 insertions(+), 37 deletions(-)
Acked-by Jiri Olsa <[email protected]>

thanks,
jirka

merge bot
#6 lore raw

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

In reply to Andi Kleen
perf stat: Use common printout function to avoid duplicated code
Commit-ID:  eedfcb4bc5f0185a14fc9e1e5a9770ad833ea5a4
Gitweb:     http://git.kernel.org/tip/eedfcb4bc5f0185a14fc9e1e5a9770ad833ea5a4
Author:     Andi Kleen <[email protected]>
AuthorDate: Mon, 2 Nov 2015 17:50:21 -0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
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 <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Link http://lkml.kernel.org/r/[email protected] open here
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
---
 tools/perf/builtin-stat.c | 57 +++++++++++++++++------------------------------
 1 file changed, 20 insertions(+), 37 deletions(-)
tools/perf/builtin-stat.c +20 -37
index 8a78895..b74ee0f 100644
@@ -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);
author
#7 lore raw

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

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 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(-)
tools/perf/builtin-stat.c +53 -6
index b74ee0f..27ca063 100644
@@ -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)
tools/perf/util/stat-shadow.c +116 -95

369 lines not on this page · raw message

tools/perf/util/stat.h +13 -2
index da1d11c..f51d94e 100644
@@ -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);
Signature · 1 line
2.4.3
#8 lore raw

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

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

SNIP

Quoted 5 lines
(quoted diff) +0 -1
@@ -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);

Review void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, · line 313

Quoted 10 lines
(quoted diff) +4 -1
+			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

Review void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, · line 322

Quoted 13 lines
(quoted diff) +6 -4
 		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

Review void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, · line 327

Quoted 4 lines
(quoted diff) +0 -4
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);

---

tools/perf/util/stat-shadow.c +1 -1
index 4d8f18581b9b..367e220e93d5 100644
@@ -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",
#9 lore raw

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

In reply to Andi Kleen

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

SNIP

tools/perf/util/stat-shadow.c void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, · line 336

Quoted 11 lines
tools/perf/util/stat-shadow.c +5 -3
 		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

author
#10 lore raw

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

Quoted 19 lines · Jiri Olsa

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

SNIP

tools/perf/util/stat-shadow.c void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, · line 336

Quoted 11 lines
tools/perf/util/stat-shadow.c +5 -3
 		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?

Quoted 1 line

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

Signature · 1 line
[email protected] -- Speaking for myself only.
#11 lore raw

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

Quoted 20 lines · Andi Kleen
Quoted 19 lines · Jiri Olsa

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

SNIP

tools/perf/util/stat-shadow.c void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, · line 336

Quoted 11 lines
tools/perf/util/stat-shadow.c +5 -3
 		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?

Quoted 4 lines
Quoted 1 line

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

Quoted 8 lines

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

Signature · 1 line
[email protected] -- Speaking for myself only.
author
#12 lore raw

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

Quoted 4 lines
Quoted 2 lines

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

Signature · 1 line
[email protected] -- Speaking for myself only.
author
#13 lore raw

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

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 tools/perf/builtin-stat.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)
tools/perf/builtin-stat.c +13 -7
index 27ca063..f13c02d 100644
@@ -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);
Signature · 1 line
2.4.3
author
#14 lore raw

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

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 tools/perf/builtin-stat.c | 50 ++++++++---------------------------------------
 1 file changed, 8 insertions(+), 42 deletions(-)
tools/perf/builtin-stat.c +8 -42
index f13c02d..c6835a4 100644
@@ -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);
 	}
Signature · 1 line
2.4.3
#15 lore raw

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

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

SNIP

Quoted 5 lines
tools/perf/builtin-stat.c +0 -1
@@ -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) {

tools/perf/builtin-stat.c static void print_counter_aggr(struct perf_evsel *counter, char *prefix) · line 742

Quoted 10 lines
tools/perf/builtin-stat.c +0 -10
-		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

tools/perf/builtin-stat.c static void print_counter_aggr(struct perf_evsel *counter, char *prefix) · line 745

Quoted 3 lines
tools/perf/builtin-stat.c +0 -3
-
-		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

Quoted 9 lines
tools/perf/builtin-stat.c +0 -8
-
-		print_running(avg_running, avg_enabled);
-		fputc('\n', output);
-		return;
-	}
-
 	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix);
-

SNIP

author
#16 lore raw

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

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 tools/perf/builtin-stat.c | 67 +++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 65 insertions(+), 2 deletions(-)
tools/perf/builtin-stat.c +65 -2
index c6835a4..a42ec99 100644
@@ -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);
Signature · 1 line
2.4.3
author
#17 lore raw

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

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 tools/perf/builtin-stat.c | 73 ++++++++++++++++-------------------------------
 1 file changed, 24 insertions(+), 49 deletions(-)
tools/perf/builtin-stat.c +24 -49
index a42ec99..5057a4b 100644
@@ -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);
Signature · 1 line
2.4.3
author
#18 lore raw

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

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 tools/perf/builtin-stat.c | 58 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 51 insertions(+), 7 deletions(-)
tools/perf/builtin-stat.c +51 -7
index 5057a4b..564b3a2 100644
@@ -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) {
Signature · 1 line
2.4.3
author
#19 lore raw

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

In reply to Andi Kleen

From: Andi Kleen <[email protected]>

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 <[email protected]>
---
 tools/perf/Documentation/perf-stat.txt | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
tools/perf/Documentation/perf-stat.txt +19 -0
index 4e074a6..079b141 100644
@@ -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]
Signature · 1 line
2.4.3
#20 lore raw
In reply to Andi Kleen
Quoted 5 lines · 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.

Quoted 8 lines

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

author
#21 lore raw
Quoted 15 lines · Jiri Olsa
Quoted 5 lines · 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.

Quoted 8 lines

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.]

Quoted 1 line

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

Quoted 6 lines

I'll try to check it this week

thanks,
jirka

Signature · 1 line
[email protected] -- Speaking for myself only.