perf, tools: Refactor and support interval and CSV metrics

perf, tools: Refactor and support interval and CSV metrics

[Andi Kleen]

Fixed even more last feedback.

[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.]
[v7: Reorder and merge two patches to avoid a bisect hole where unsupported was
printed as 0]
[v8: Minor fixes for review feedback. See changelog in patches.]
[v9: Fix newline bug. Add support for -A for --metric-only]
[v10: Remove extra "noise" printing (Jiri)
      Fix fields in documentation (Jiri)]
[v11: Fix manpage again. Avoid extra metric output in CSV mode.]
[v12: Move CSV metrics fields to after running/enabled/variance.
      Minor fixes.]
[v13: Address review comments. Now probe for stalled events 
      in advance to avoid empty columns or lines. Fix -A shadowing.
      Various minor changes. Drop merged patches.]
[v14: Fix empty lines with CSV metrics. Avoid one more empty column
      in metric-only.]
[v15: Add missing fields in manpage. Use extra init function 
      for frontend event. Various smaller fixes. Add acked-by.]
[v16: Fix manpage again. Merge --per-thread crash patch.
      Add comments to --metric-only.]
[v17: Man page fixes. Simplify -A --metric-only nrcpus computation.]

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,
and finally a --metric-only 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
     1.000982778,12006.549977,,task-clock,12006547787,100.00,,,,
     1.000982778,12822,,context-switches,12007100604,100.00,0.001,M/sec
     1.000982778,175,,cpu-migrations,12007180306,100.00,0.015,K/sec
     1.000982778,3404,,page-faults,12007185482,100.00,0.284,K/sec
     1.000982778,1930307489,,cycles,12007018233,100.00,0.161,GHz
     1.000982778,6971803638,,stalled-cycles-frontend,12006902870,100.00,361.18,frontend cycles idle
     1.000982778,464493941,,instructions,12006873327,100.00,0.24,insn per cycle
     1.000982778,,,,,,15.01,stalled cycles per insn
     1.000982778,86548409,,branches,12006758420,100.00,7.208,M/sec
     1.000982778,4933638,,branch-misses,12006648104,100.00,5.70,of all branches

Now includes metrics

Metric only mode:

Concicse information if you only care about computed metrics, not raw values

% perf stat --metric-only  -a -I 1000
         1.001452803 frontend cycles idle insn per cycle       stalled cycles per insn branch-misses of all branches
         1.001452803  158.91%               0.66                2.39                    2.92%
         2.002192321  180.63%               0.76                2.08                    2.96%
         3.003088282  150.59%               0.62                2.57                    2.84%
         4.004369835  196.20%               0.98                1.62                    3.79%
         5.005227314  231.98%               0.84                1.90                    4.71%


Metric only mode in CSV (flat format, easy to plot and analyze in statistical tools like JMP, R, pandas, gnuplot):

% perf stat -x, --metric-only  -a -I 1000
     1.001381652,frontend cycles idle,insn per cycle,stalled cycles per insn,branch-misses of all branches,
     1.001381652,173.32,0.83,2.09,1.73,
     2.002073343,199.47,1.07,1.60,2.14,
     3.002875524,109.52,0.22,7.83,1.63,
     4.003970059,132.10,0.17,10.85,1.51,
     5.004818754,181.60,0.22,8.87,2.22,


Available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-21

[PATCH 1/7] perf, tools, stat: Check existence of frontend/backed stalled cycles

[Andi Kleen]

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

Only put the frontend/backend stalled cycles into the default
perf stat events when the CPU actually supports them.

This avoids empty columns with --metric-only on newer Intel CPUs.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8c0bc0f..24f222d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1441,7 +1441,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
  */
 static int add_default_attributes(void)
 {
-	struct perf_event_attr default_attrs[] = {
+	struct perf_event_attr default_attrs0[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
@@ -1449,8 +1449,14 @@ static int add_default_attributes(void)
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
 
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
+};
+	struct perf_event_attr frontend_attrs[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},
+};
+	struct perf_event_attr backend_attrs[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
+};
+	struct perf_event_attr default_attrs1[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
@@ -1567,7 +1573,19 @@ static int add_default_attributes(void)
 	}
 
 	if (!evsel_list->nr_entries) {
-		if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
+			return -1;
+		if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
+			if (perf_evlist__add_default_attrs(evsel_list,
+						frontend_attrs) < 0)
+				return -1;
+		}
+		if (pmu_have_event("cpu", "stalled-cycles-backend")) {
+			if (perf_evlist__add_default_attrs(evsel_list,
+						backend_attrs) < 0)
+				return -1;
+		}
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
 			return -1;
 	}
 
-- 
2.5.0

[PATCH 2/7] 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.

This allows to easily plot metrics from CSV files.

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

Example output before:

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

After:

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

or easier readable

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

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

v2: Split out function argument changes
v3: Reenable metrics for real.
v4: Fix wrong hunk from refactoring.
v5: Remove extra "noise" printing (Jiri), but add it to the not counted case.
Print empty metrics for not counted.
v6: Avoid outputting metric on empty format.
v7: Print metric at the end
v8: Remove extra run, ena fields
v9: Avoid extra new line for unsupported counters
Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     | 73 ++++++++++++++++++++++++++++++++++++++++---
 tools/perf/util/stat-shadow.c |  2 +-
 2 files changed, 70 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 24f222d..2ffb822 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -739,6 +739,7 @@ struct outstate {
 	FILE *fh;
 	bool newline;
 	const char *prefix;
+	int  nfields;
 };
 
 #define METRIC_LEN  35
@@ -789,6 +790,43 @@ static void print_metric_std(void *ctx, const char *color, const char *fmt,
 	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
 }
 
+static void new_line_csv(void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+	for (i = 0; i < os->nfields; i++)
+		fputs(csv_sep, os->fh);
+}
+
+static void print_metric_csv(void *ctx,
+			     const char *color __maybe_unused,
+			     const char *fmt, const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	while (isspace(*unit))
+		unit++;
+	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -860,6 +898,22 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	nl = new_line_std;
 
+	if (csv_output) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[stat_config.aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
 	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
 		aggr_printout(counter, id, nr);
 
@@ -880,7 +934,12 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 			fprintf(stat_config.output, "%s%s",
 				csv_sep, counter->cgrp->name);
 
+		if (!csv_output)
+			pm(&os, NULL, NULL, "", 0);
+		print_noise(counter, noise);
 		print_running(run, ena);
+		if (csv_output)
+			pm(&os, NULL, NULL, "", 0);
 		return;
 	}
 
@@ -893,14 +952,20 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.new_line = nl;
 	out.ctx = &os;
 
-	if (!csv_output)
-		perf_stat__print_shadow_stats(counter, uval,
+	if (csv_output) {
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
+
+	perf_stat__print_shadow_stats(counter, uval,
 				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
 				cpu_map__id_to_cpu(id),
 				&out);
 
-	print_noise(counter, noise);
-	print_running(run, ena);
+	if (!csv_output) {
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
 }
 
 static void print_aggr(char *prefix)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 4d8f185..367e220 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -310,8 +310,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
-		out->new_line(ctxp);
 		if (total && avg) {
+			out->new_line(ctxp);
 			ratio = total / avg;
 			print_metric(ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
-- 
2.5.0

[PATCH 3/7] perf, tools, stat: Support metrics in --per-core/socket mode

[Andi Kleen]

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

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

Example output:

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

 Performance counter stats for 'system wide':

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

       1.480409747 seconds time elapsed

v2: Rebase to older patches
v3: Document shadow cpus. Fix aggr_get_id argument. Fix -A shadows (Jiri)
v4: Fix crash with --per-thread
Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     | 64 +++++++++++++++++++++++++++++++++++++------
 tools/perf/util/stat-shadow.c |  7 +++++
 2 files changed, 63 insertions(+), 8 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2ffb822..9b5089c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -740,6 +740,8 @@ struct outstate {
 	bool newline;
 	const char *prefix;
 	int  nfields;
+	int  id, nr;
+	struct perf_evsel *evsel;
 };
 
 #define METRIC_LEN  35
@@ -755,12 +757,9 @@ static void do_new_line_std(struct outstate *os)
 {
 	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, "                                                 ");
 }
 
@@ -798,6 +797,7 @@ 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);
 }
@@ -855,6 +855,28 @@ 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)
+		return 0;
+
+	if (stat_config.aggr_mode == AGGR_NONE)
+		return id;
+
+	if (stat_config.aggr_mode == AGGR_GLOBAL)
+		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;
@@ -891,7 +913,10 @@ 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 *);
@@ -958,16 +983,37 @@ 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);
-
 	if (!csv_output) {
 		print_noise(counter, noise);
 		print_running(run, ena);
 	}
 }
 
+static void aggr_update_shadow(void)
+{
+	int cpu, 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++) {
+				s2 = aggr_get_id(evsel_list->cpus, cpu);
+				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;
@@ -979,6 +1025,8 @@ 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) {
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 367e220..5e2d2e3 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -14,6 +14,13 @@ enum {
 
 #define NUM_CTX CTX_BIT_MAX
 
+/*
+ * AGGR_GLOBAL: Use CPU 0
+ * AGGR_SOCKET: Use first CPU of socket
+ * AGGR_CORE: Use first CPU of core
+ * AGGR_NONE: Use matching CPU
+ * AGGR_THREAD: Not supported?
+ */
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
 static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
-- 
2.5.0

[PATCH 4/7] perf, tools, stat: Document CSV format in manpage

[Andi Kleen]

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

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

v2: Fix fields in documentation (Jiri)
v3: fix order of fields again (Jiri)
v4: Change order again.
v5: Document more fields (Jiri)
v6: Move time stamp first
v7: More fixes (Jiri)
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 52ef7a9..e513a1c 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -211,6 +211,29 @@ $ 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 "". To make it easy to parse
+it is recommended to use a different character like -x \;
+
+The fields are in this order:
+
+	- optional usec time stamp in fractions of second (with -I xxx)
+	- optional CPU, core, or socket identifier
+	- optional number of logical CPUs aggregated
+	- counter value
+	- unit of the counter value or empty
+	- event name
+	- run time of counter
+	- percentage of measurement time the counter was running
+	- optional variance if multiple values are collected with -r
+	- optional metric value
+	- optional unit of metric
+
+Additional metrics may be printed with all earlier fields being empty.
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-list[1]
-- 
2.5.0

Re: [PATCH 4/7] perf, tools, stat: Document CSV format in manpage

[Jiri Olsa]

On Thu, Mar 03, 2016 at 03:57:35PM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> With all the recently added fields in the perf stat CSV output
> we should finally document them in the man page. Do this here.
> 
> v2: Fix fields in documentation (Jiri)
> v3: fix order of fields again (Jiri)
> v4: Change order again.
> v5: Document more fields (Jiri)
> v6: Move time stamp first
> v7: More fixes (Jiri)

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

thanks,
jirka

> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  tools/perf/Documentation/perf-stat.txt | 23 +++++++++++++++++++++++
>  1 file changed, 23 insertions(+)
> 
> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
> index 52ef7a9..e513a1c 100644
> --- a/tools/perf/Documentation/perf-stat.txt
> +++ b/tools/perf/Documentation/perf-stat.txt
> @@ -211,6 +211,29 @@ $ 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 "". To make it easy to parse
> +it is recommended to use a different character like -x \;
> +
> +The fields are in this order:
> +
> +	- optional usec time stamp in fractions of second (with -I xxx)
> +	- optional CPU, core, or socket identifier
> +	- optional number of logical CPUs aggregated
> +	- counter value
> +	- unit of the counter value or empty
> +	- event name
> +	- run time of counter
> +	- percentage of measurement time the counter was running
> +	- optional variance if multiple values are collected with -r
> +	- optional metric value
> +	- optional unit of metric
> +
> +Additional metrics may be printed with all earlier fields being empty.
> +
>  SEE ALSO
>  --------
>  linkperf:perf-top[1], linkperf:perf-list[1]
> -- 
> 2.5.0
> 

[tip:perf/core] perf stat: Document CSV format in manpage

[tip-bot for Andi Kleen]

Commit-ID:  6b45f7b2a37b0e00693985fd0abfc8e0319f91ce
Gitweb:     http://git.kernel.org/tip/6b45f7b2a37b0e00693985fd0abfc8e0319f91ce
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Thu, 3 Mar 2016 15:57:35 -0800
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Thu, 10 Mar 2016 16:49:06 -0300

perf stat: Document CSV format in manpage

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

v2: Fix fields in documentation (Jiri)
v3: fix order of fields again (Jiri)
v4: Change order again.
v5: Document more fields (Jiri)
v6: Move time stamp first
v7: More fixes (Jiri)

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1457049458-28956-5-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-stat.txt | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 14d9e8f..8812d73 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -219,6 +219,29 @@ $ 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 "". To make it easy to parse
+it is recommended to use a different character like -x \;
+
+The fields are in this order:
+
+	- optional usec time stamp in fractions of second (with -I xxx)
+	- optional CPU, core, or socket identifier
+	- optional number of logical CPUs aggregated
+	- counter value
+	- unit of the counter value or empty
+	- event name
+	- run time of counter
+	- percentage of measurement time the counter was running
+	- optional variance if multiple values are collected with -r
+	- 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]

[PATCH 5/7] perf, tools, stat: Implement --metric-only mode

[Andi Kleen]

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

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

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

To avoiding having to hardcode all the metrics in the code it uses
a two pass approach: first compute dummy metrics and only
print the headers in the print_metric callback. Then use the callback
to print the actual values.

There are some additional changes
in the stat printout code to handle all metrics being on a single line.

One issue is that the column code doesn't know in advance what events
are not supported by the CPU, and it would be hard to find out
as this could change based on dynamic conditions. That causes
empty columns in some cases.

The output can be fairly wide, often you may need more than 80 columns.

Example:

% perf stat -a -I 1000 --metric-only
     1.001452803 frontend cycles idle insn per cycle       stalled cycles per insn branch-misses of all branches
     1.001452803  158.91%               0.66                2.39                    2.92%
     2.002192321  180.63%               0.76                2.08                    2.96%
     3.003088282  150.59%               0.62                2.57                    2.84%
     4.004369835  196.20%               0.98                1.62                    3.79%
     5.005227314  231.98%               0.84                1.90                    4.71%

v2: Lots of updates.
v3: Use slightly narrower columns
v4: Add comment
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt |   4 +
 tools/perf/builtin-stat.c              | 211 +++++++++++++++++++++++++++++++--
 2 files changed, 205 insertions(+), 10 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index e513a1c..88a27ca 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -139,6 +139,10 @@ Print count deltas every N milliseconds (minimum: 10ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+--metric-only::
+Only print computed metrics. Print them in a single line.
+Don't show any raw values. Not supported with -A or --per-thread.
+
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
 is a useful mode to detect imbalance between sockets.  To enable this mode,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 9b5089c..0196fed 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -122,6 +122,7 @@ static bool			sync_run			= false;
 static unsigned int		initial_delay			= 0;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
+static bool			metric_only			= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -827,6 +828,99 @@ static void print_metric_csv(void *ctx,
 	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
 }
 
+#define METRIC_ONLY_LEN 20
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	char buf[1024];
+	unsigned mlen = METRIC_ONLY_LEN;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (color)
+		n = color_fprintf(out, color, fmt, val);
+	else
+		n = fprintf(out, fmt, val);
+	if (n > METRIC_ONLY_LEN)
+		n = METRIC_ONLY_LEN;
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+	fprintf(out, "%*s", mlen - n, "");
+}
+
+static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, csv_sep);
+}
+
+static void new_line_metric(void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (csv_output)
+		fprintf(os->fh, "%s%s", unit, csv_sep);
+	else
+		fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -921,9 +1015,16 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	print_metric_t pm = print_metric_std;
 	void (*nl)(void *);
 
-	nl = new_line_std;
+	if (metric_only) {
+		nl = new_line_metric;
+		if (csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
 
-	if (csv_output) {
+	if (csv_output && !metric_only) {
 		static int aggr_fields[] = {
 			[AGGR_GLOBAL] = 0,
 			[AGGR_THREAD] = 1,
@@ -940,6 +1041,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 			os.nfields++;
 	}
 	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (metric_only) {
+			pm(&os, NULL, "", "", 0);
+			return;
+		}
 		aggr_printout(counter, id, nr);
 
 		fprintf(stat_config.output, "%*s%s",
@@ -968,7 +1073,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		return;
 	}
 
-	if (nsec_counter(counter))
+	if (metric_only)
+		/* nothing */;
+	else if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
@@ -977,7 +1084,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.new_line = nl;
 	out.ctx = &os;
 
-	if (csv_output) {
+	if (csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);
 	}
@@ -985,7 +1092,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	perf_stat__print_shadow_stats(counter, uval,
 				first_shadow_cpu(counter, id),
 				&out);
-	if (!csv_output) {
+	if (!csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);
 	}
@@ -1021,14 +1128,23 @@ static void print_aggr(char *prefix)
 	int cpu, s, s2, id, nr;
 	double uval;
 	u64 ena, run, val;
+	bool first;
 
 	if (!(aggr_map || aggr_get_id))
 		return;
 
 	aggr_update_shadow();
 
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
 	for (s = 0; s < aggr_map->nr; s++) {
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
 		id = aggr_map->map[s];
+		first = true;
 		evlist__for_each(evsel_list, counter) {
 			val = ena = run = 0;
 			nr = 0;
@@ -1041,13 +1157,20 @@ static void print_aggr(char *prefix)
 				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
-			if (prefix)
+			if (first && metric_only) {
+				first = false;
+				aggr_printout(counter, id, nr);
+			}
+			if (prefix && !metric_only)
 				fprintf(output, "%s", prefix);
 
 			uval = val * counter->scale;
 			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
-			fputc('\n', output);
+			if (!metric_only)
+				fputc('\n', output);
 		}
+		if (metric_only)
+			fputc('\n', output);
 	}
 }
 
@@ -1092,12 +1215,13 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	avg_enabled = avg_stats(&ps->res_stats[1]);
 	avg_running = avg_stats(&ps->res_stats[2]);
 
-	if (prefix)
+	if (prefix && !metric_only)
 		fprintf(output, "%s", prefix);
 
 	uval = avg * counter->scale;
 	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
-	fprintf(output, "\n");
+	if (!metric_only)
+		fprintf(output, "\n");
 }
 
 /*
@@ -1126,6 +1250,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 15,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
+
+static void print_metric_headers(char *prefix)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = stat_config.output
+	};
+
+	if (prefix)
+		fprintf(stat_config.output, "%s", prefix);
+
+	if (!csv_output)
+		fprintf(stat_config.output, "%*s",
+			aggr_header_lens[stat_config.aggr_mode], "");
+
+	/* Print metrics headers only */
+	evlist__for_each(evsel_list, counter) {
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(counter, 0,
+					      0,
+					      &out);
+	}
+	fputc('\n', stat_config.output);
+}
+
 static void print_interval(char *prefix, struct timespec *ts)
 {
 	FILE *output = stat_config.output;
@@ -1133,7 +1294,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output) {
+	if (num_print_interval == 0 && !csv_output && !metric_only) {
 		switch (stat_config.aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
@@ -1220,6 +1381,17 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	else
 		print_header(argc, argv);
 
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0)
+			print_metric_headers(prefix);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(stat_config.output, "%s", prefix);
+	}
+
 	switch (stat_config.aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
@@ -1232,6 +1404,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
+		if (metric_only)
+			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
 		evlist__for_each(evsel_list, counter)
@@ -1356,6 +1530,8 @@ static const struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
+	OPT_BOOLEAN(0, "metric-only", &metric_only,
+			"Only print computed metrics. No raw values"),
 	OPT_END()
 };
 
@@ -1996,6 +2172,21 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+		fprintf(stderr, "--metric-only is not supported with --per-thread\n");
+		goto out;
+	}
+
+	if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
+		fprintf(stderr, "--metric-only is not supported with -A\n");
+		goto out;
+	}
+
+	if (metric_only && run_count > 1) {
+		fprintf(stderr, "--metric-only is not supported with -r\n");
+		goto out;
+	}
+
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
 		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
-- 
2.5.0

Re: [PATCH 5/7] perf, tools, stat: Implement --metric-only mode

[Jiri Olsa]

On Thu, Mar 03, 2016 at 03:57:36PM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Add a new mode to only print metrics. Sometimes we don't care about
> the raw values, just want the computed metrics. This allows more
> compact printing, so with -I each sample is only a single line.
> This also allows easier plotting and processing with other tools.
> 
> The main target is with using --topdown, but it also works with
> -T and standard perf stat. A few metrics are not supported.
> 
> To avoiding having to hardcode all the metrics in the code it uses
> a two pass approach: first compute dummy metrics and only
> print the headers in the print_metric callback. Then use the callback
> to print the actual values.
> 
> There are some additional changes
> in the stat printout code to handle all metrics being on a single line.
> 
> One issue is that the column code doesn't know in advance what events
> are not supported by the CPU, and it would be hard to find out
> as this could change based on dynamic conditions. That causes
> empty columns in some cases.
> 
> The output can be fairly wide, often you may need more than 80 columns.
> 
> Example:
> 
> % perf stat -a -I 1000 --metric-only
>      1.001452803 frontend cycles idle insn per cycle       stalled cycles per insn branch-misses of all branches
>      1.001452803  158.91%               0.66                2.39                    2.92%
>      2.002192321  180.63%               0.76                2.08                    2.96%
>      3.003088282  150.59%               0.62                2.57                    2.84%
>      4.004369835  196.20%               0.98                1.62                    3.79%
>      5.005227314  231.98%               0.84                1.90                    4.71%

could you please also make a change to display some kind of warning
if there're no events to produce any metrics?

[jolsa@krava perf]$ sudo ./perf stat -a -I 1000 --metric-only -e cycles
     1.000172990 
     1.000172990 
     2.000448614 

this could be follow up patch

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


thanks,
jirka

[tip:perf/core] perf stat: Implement --metric-only mode

[tip-bot for Andi Kleen]

Commit-ID:  54b5091606c18f68a7fc8b4ab03ac4592c7d2922
Gitweb:     http://git.kernel.org/tip/54b5091606c18f68a7fc8b4ab03ac4592c7d2922
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Thu, 3 Mar 2016 15:57:36 -0800
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Thu, 10 Mar 2016 16:49:40 -0300

perf stat: Implement --metric-only mode

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

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

To avoiding having to hardcode all the metrics in the code it uses a two
pass approach: first compute dummy metrics and only print the headers in
the print_metric callback. Then use the callback to print the actual
values.

There are some additional changes in the stat printout code to handle
all metrics being on a single line.

One issue is that the column code doesn't know in advance what events
are not supported by the CPU, and it would be hard to find out as this
could change based on dynamic conditions. That causes empty columns in
some cases.

The output can be fairly wide, often you may need more than 80 columns.

Example:

% perf stat -a -I 1000 --metric-only
     1.001452803 frontend cycles idle insn per cycle       stalled cycles per insn branch-misses of all branches
     1.001452803  158.91%               0.66                2.39                    2.92%
     2.002192321  180.63%               0.76                2.08                    2.96%
     3.003088282  150.59%               0.62                2.57                    2.84%
     4.004369835  196.20%               0.98                1.62                    3.79%
     5.005227314  231.98%               0.84                1.90                    4.71%

v2: Lots of updates.
v3: Use slightly narrower columns
v4: Add comment

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1457049458-28956-6-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-stat.txt |   4 +
 tools/perf/builtin-stat.c              | 211 +++++++++++++++++++++++++++++++--
 2 files changed, 205 insertions(+), 10 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 8812d73..82f0951 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -147,6 +147,10 @@ Print count deltas every N milliseconds (minimum: 10ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+--metric-only::
+Only print computed metrics. Print them in a single line.
+Don't show any raw values. Not supported with -A or --per-thread.
+
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
 is a useful mode to detect imbalance between sockets.  To enable this mode,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index baa8207..74508c9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -122,6 +122,7 @@ static bool			sync_run			= false;
 static unsigned int		initial_delay			= 0;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
+static bool			metric_only			= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -827,6 +828,99 @@ static void print_metric_csv(void *ctx,
 	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
 }
 
+#define METRIC_ONLY_LEN 20
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	char buf[1024];
+	unsigned mlen = METRIC_ONLY_LEN;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (color)
+		n = color_fprintf(out, color, fmt, val);
+	else
+		n = fprintf(out, fmt, val);
+	if (n > METRIC_ONLY_LEN)
+		n = METRIC_ONLY_LEN;
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+	fprintf(out, "%*s", mlen - n, "");
+}
+
+static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, csv_sep);
+}
+
+static void new_line_metric(void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (csv_output)
+		fprintf(os->fh, "%s%s", unit, csv_sep);
+	else
+		fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -921,9 +1015,16 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	print_metric_t pm = print_metric_std;
 	void (*nl)(void *);
 
-	nl = new_line_std;
+	if (metric_only) {
+		nl = new_line_metric;
+		if (csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
 
-	if (csv_output) {
+	if (csv_output && !metric_only) {
 		static int aggr_fields[] = {
 			[AGGR_GLOBAL] = 0,
 			[AGGR_THREAD] = 1,
@@ -940,6 +1041,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 			os.nfields++;
 	}
 	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (metric_only) {
+			pm(&os, NULL, "", "", 0);
+			return;
+		}
 		aggr_printout(counter, id, nr);
 
 		fprintf(stat_config.output, "%*s%s",
@@ -968,7 +1073,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		return;
 	}
 
-	if (nsec_counter(counter))
+	if (metric_only)
+		/* nothing */;
+	else if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
@@ -977,7 +1084,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.new_line = nl;
 	out.ctx = &os;
 
-	if (csv_output) {
+	if (csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);
 	}
@@ -985,7 +1092,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	perf_stat__print_shadow_stats(counter, uval,
 				first_shadow_cpu(counter, id),
 				&out);
-	if (!csv_output) {
+	if (!csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);
 	}
@@ -1021,14 +1128,23 @@ static void print_aggr(char *prefix)
 	int cpu, s, s2, id, nr;
 	double uval;
 	u64 ena, run, val;
+	bool first;
 
 	if (!(aggr_map || aggr_get_id))
 		return;
 
 	aggr_update_shadow();
 
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
 	for (s = 0; s < aggr_map->nr; s++) {
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
 		id = aggr_map->map[s];
+		first = true;
 		evlist__for_each(evsel_list, counter) {
 			val = ena = run = 0;
 			nr = 0;
@@ -1041,13 +1157,20 @@ static void print_aggr(char *prefix)
 				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
-			if (prefix)
+			if (first && metric_only) {
+				first = false;
+				aggr_printout(counter, id, nr);
+			}
+			if (prefix && !metric_only)
 				fprintf(output, "%s", prefix);
 
 			uval = val * counter->scale;
 			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
-			fputc('\n', output);
+			if (!metric_only)
+				fputc('\n', output);
 		}
+		if (metric_only)
+			fputc('\n', output);
 	}
 }
 
@@ -1092,12 +1215,13 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	avg_enabled = avg_stats(&ps->res_stats[1]);
 	avg_running = avg_stats(&ps->res_stats[2]);
 
-	if (prefix)
+	if (prefix && !metric_only)
 		fprintf(output, "%s", prefix);
 
 	uval = avg * counter->scale;
 	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
-	fprintf(output, "\n");
+	if (!metric_only)
+		fprintf(output, "\n");
 }
 
 /*
@@ -1126,6 +1250,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 15,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
+
+static void print_metric_headers(char *prefix)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = stat_config.output
+	};
+
+	if (prefix)
+		fprintf(stat_config.output, "%s", prefix);
+
+	if (!csv_output)
+		fprintf(stat_config.output, "%*s",
+			aggr_header_lens[stat_config.aggr_mode], "");
+
+	/* Print metrics headers only */
+	evlist__for_each(evsel_list, counter) {
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(counter, 0,
+					      0,
+					      &out);
+	}
+	fputc('\n', stat_config.output);
+}
+
 static void print_interval(char *prefix, struct timespec *ts)
 {
 	FILE *output = stat_config.output;
@@ -1133,7 +1294,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output) {
+	if (num_print_interval == 0 && !csv_output && !metric_only) {
 		switch (stat_config.aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
@@ -1220,6 +1381,17 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	else
 		print_header(argc, argv);
 
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0)
+			print_metric_headers(prefix);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(stat_config.output, "%s", prefix);
+	}
+
 	switch (stat_config.aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
@@ -1232,6 +1404,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
+		if (metric_only)
+			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
 		evlist__for_each(evsel_list, counter)
@@ -1356,6 +1530,8 @@ static const struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
+	OPT_BOOLEAN(0, "metric-only", &metric_only,
+			"Only print computed metrics. No raw values"),
 	OPT_END()
 };
 
@@ -1997,6 +2173,21 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+		fprintf(stderr, "--metric-only is not supported with --per-thread\n");
+		goto out;
+	}
+
+	if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
+		fprintf(stderr, "--metric-only is not supported with -A\n");
+		goto out;
+	}
+
+	if (metric_only && run_count > 1) {
+		fprintf(stderr, "--metric-only is not supported with -r\n");
+		goto out;
+	}
+
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
 		parse_options_usage(stat_usage, stat_options, "log-fd", 0);

[PATCH 6/7] perf, tools, stat: Add --metric-only support for -A

[Andi Kleen]

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

Add metric only support for -A too. This requires a new print
function that prints the metrics in the right order.

v2: Fix manpage
v3: Simplify nrcpus computation
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt |  2 +-
 tools/perf/builtin-stat.c              | 45 ++++++++++++++++++++++++++++------
 2 files changed, 38 insertions(+), 9 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 88a27ca..26c6b1b 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -141,7 +141,7 @@ The overhead percentage could be high in some cases, for instance with small, su
 
 --metric-only::
 Only print computed metrics. Print them in a single line.
-Don't show any raw values. Not supported with -A or --per-thread.
+Don't show any raw values. Not supported with --per-thread.
 
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0196fed..7fac514 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1250,10 +1250,40 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+static void print_no_aggr_metric(char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	nrcpus = evsel_list->cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, stat_config.output);
+		evlist__for_each(evsel_list, counter) {
+			if (first) {
+				aggr_printout(counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+		}
+		fputc('\n', stat_config.output);
+	}
+}
+
 static int aggr_header_lens[] = {
 	[AGGR_CORE] = 18,
 	[AGGR_SOCKET] = 12,
-	[AGGR_NONE] = 15,
+	[AGGR_NONE] = 6,
 	[AGGR_THREAD] = 24,
 	[AGGR_GLOBAL] = 0,
 };
@@ -1408,8 +1438,12 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
+		if (metric_only)
+			print_no_aggr_metric(prefix);
+		else {
+			evlist__for_each(evsel_list, counter)
+				print_counter(counter, prefix);
+		}
 		break;
 	case AGGR_UNSET:
 	default:
@@ -2177,11 +2211,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
-	if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
-		fprintf(stderr, "--metric-only is not supported with -A\n");
-		goto out;
-	}
-
 	if (metric_only && run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;
-- 
2.5.0

Re: [PATCH 6/7] perf, tools, stat: Add --metric-only support for -A

[Jiri Olsa]

On Thu, Mar 03, 2016 at 03:57:37PM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Add metric only support for -A too. This requires a new print
> function that prints the metrics in the right order.
> 
> v2: Fix manpage
> v3: Simplify nrcpus computation
> Signed-off-by: Andi Kleen <ak@linux.intel.com>

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

thanks,
jirka

[tip:perf/core] perf stat: Add --metric-only support for -A

[tip-bot for Andi Kleen]

Commit-ID:  206cab651d07563d766c7f4cb73f858c5df3dec5
Gitweb:     http://git.kernel.org/tip/206cab651d07563d766c7f4cb73f858c5df3dec5
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Thu, 3 Mar 2016 15:57:37 -0800
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Thu, 10 Mar 2016 16:50:47 -0300

perf stat: Add --metric-only support for -A

Add metric only support for -A too. This requires a new print function
that prints the metrics in the right order.

v2: Fix manpage
v3: Simplify nrcpus computation

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1457049458-28956-7-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-stat.txt |  2 +-
 tools/perf/builtin-stat.c              | 45 ++++++++++++++++++++++++++++------
 2 files changed, 38 insertions(+), 9 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 82f0951..04f23b4 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -149,7 +149,7 @@ The overhead percentage could be high in some cases, for instance with small, su
 
 --metric-only::
 Only print computed metrics. Print them in a single line.
-Don't show any raw values. Not supported with -A or --per-thread.
+Don't show any raw values. Not supported with --per-thread.
 
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 74508c9..1f19f2f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1250,10 +1250,40 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+static void print_no_aggr_metric(char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	nrcpus = evsel_list->cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, stat_config.output);
+		evlist__for_each(evsel_list, counter) {
+			if (first) {
+				aggr_printout(counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+		}
+		fputc('\n', stat_config.output);
+	}
+}
+
 static int aggr_header_lens[] = {
 	[AGGR_CORE] = 18,
 	[AGGR_SOCKET] = 12,
-	[AGGR_NONE] = 15,
+	[AGGR_NONE] = 6,
 	[AGGR_THREAD] = 24,
 	[AGGR_GLOBAL] = 0,
 };
@@ -1408,8 +1438,12 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
+		if (metric_only)
+			print_no_aggr_metric(prefix);
+		else {
+			evlist__for_each(evsel_list, counter)
+				print_counter(counter, prefix);
+		}
 		break;
 	case AGGR_UNSET:
 	default:
@@ -2178,11 +2212,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
-	if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
-		fprintf(stderr, "--metric-only is not supported with -A\n");
-		goto out;
-	}
-
 	if (metric_only && run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;

[PATCH 7/7] perf, tools, stat: Check for frontend stalled for metrics

[Andi Kleen]

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

Add an extra check for frontend stalled in the metrics.
This avoids an extra column for the --metric-only case
when the CPU does not support frontend stalled.

v2: Add separate init function
Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c     | 1 +
 tools/perf/util/stat-shadow.c | 9 ++++++++-
 tools/perf/util/stat.h        | 1 +
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7fac514..1f19f2f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2176,6 +2176,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
 					(const char **) stat_usage,
 					PARSE_OPT_STOP_AT_NON_OPTION);
+	perf_stat__init_shadow_stats();
 
 	if (csv_sep) {
 		csv_output = true;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 5e2d2e3..b33ffb2 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "stat.h"
 #include "color.h"
+#include "pmu.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -35,9 +36,15 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
 
+void perf_stat__init_shadow_stats(void)
+{
+	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+}
+
 static int evsel_context(struct perf_evsel *evsel)
 {
 	int ctx = 0;
@@ -323,7 +330,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			print_metric(ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
-		} else {
+		} else if (have_frontend_stalled) {
 			print_metric(ctxp, NULL, NULL,
 				     "stalled cycles per insn", 0);
 		}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index f02af68..0150e78 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -72,6 +72,7 @@ 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__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 				    int cpu);
-- 
2.5.0

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

[Jiri Olsa]

On Thu, Mar 03, 2016 at 03:57:31PM -0800, Andi Kleen wrote:

SNIP

> 
> % perf stat -x, --metric-only  -a -I 1000
>      1.001381652,frontend cycles idle,insn per cycle,stalled cycles per insn,branch-misses of all branches,
>      1.001381652,173.32,0.83,2.09,1.73,
>      2.002073343,199.47,1.07,1.60,2.14,
>      3.002875524,109.52,0.22,7.83,1.63,
>      4.003970059,132.10,0.17,10.85,1.51,
>      5.004818754,181.60,0.22,8.87,2.22,
> 
> 
> Available in
> git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-21

this branch contains old version of:
  perf, tools, stat: Add --metric-only support for -A

thanks,
jirka

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

[Andi Kleen]

On Mon, Mar 07, 2016 at 11:08:42AM +0100, Jiri Olsa wrote:
> On Thu, Mar 03, 2016 at 03:57:31PM -0800, Andi Kleen wrote:
> 
> SNIP
> 
> > 
> > % perf stat -x, --metric-only  -a -I 1000
> >      1.001381652,frontend cycles idle,insn per cycle,stalled cycles per insn,branch-misses of all branches,
> >      1.001381652,173.32,0.83,2.09,1.73,
> >      2.002073343,199.47,1.07,1.60,2.14,
> >      3.002875524,109.52,0.22,7.83,1.63,
> >      4.003970059,132.10,0.17,10.85,1.51,
> >      5.004818754,181.60,0.22,8.87,2.22,
> > 
> > 
> > Available in
> > git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-21
> 
> this branch contains old version of:
>   perf, tools, stat: Add --metric-only support for -A

Old in what way? Looks correct to me.


commit e26ba80593023c24c8276ad9853acd7e56ca92ed
Author: Andi Kleen <ak@linux.intel.com>
Date:   Sat Dec 19 11:22:55 2015 -0800

    perf, tools, stat: Add --metric-only support for -A
    
    Add metric only support for -A too. This requires a new print
    function that prints the metrics in the right order.
    
    v2: Fix manpage
    v3: Simplify nrcpus computation
    Signed-off-by: Andi Kleen <ak@linux.intel.com>

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

[Jiri Olsa]

On Mon, Mar 07, 2016 at 07:22:27PM +0100, Andi Kleen wrote:
> On Mon, Mar 07, 2016 at 11:08:42AM +0100, Jiri Olsa wrote:
> > On Thu, Mar 03, 2016 at 03:57:31PM -0800, Andi Kleen wrote:
> > 
> > SNIP
> > 
> > > 
> > > % perf stat -x, --metric-only  -a -I 1000
> > >      1.001381652,frontend cycles idle,insn per cycle,stalled cycles per insn,branch-misses of all branches,
> > >      1.001381652,173.32,0.83,2.09,1.73,
> > >      2.002073343,199.47,1.07,1.60,2.14,
> > >      3.002875524,109.52,0.22,7.83,1.63,
> > >      4.003970059,132.10,0.17,10.85,1.51,
> > >      5.004818754,181.60,0.22,8.87,2.22,
> > > 
> > > 
> > > Available in
> > > git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-21
> > 
> > this branch contains old version of:
> >   perf, tools, stat: Add --metric-only support for -A
> 
> Old in what way? Looks correct to me.
> 
> 
> commit e26ba80593023c24c8276ad9853acd7e56ca92ed
> Author: Andi Kleen <ak@linux.intel.com>
> Date:   Sat Dec 19 11:22:55 2015 -0800
> 
>     perf, tools, stat: Add --metric-only support for -A
>     
>     Add metric only support for -A too. This requires a new print
>     function that prints the metrics in the right order.
>     
>     v2: Fix manpage
>     v3: Simplify nrcpus computation
>     Signed-off-by: Andi Kleen <ak@linux.intel.com>

I did not see the change for print_no_aggr_metric function
in commit:
   perf, tools, stat: Add --metric-only support for -A

which I saw in the email..

however now im confused, I did not noticed I had a wrong tree,
however git can't resolve the git tree you mentioned:

> Available in
> git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-21

	[jolsa@krava perf]$ git remote add ak1 git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 
	[jolsa@krava perf]$ git remote update ak1
	Fetching ak1
	fatal: remote error: access denied or repository not exported: /pub/scm/linux/kernel/git/ak/linux-misc-2.6
	error: Could not fetch ak1

so I guess the one I have is the correct one:
	git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc

however:
	[jolsa@krava perf]$ git remote update ak
	Fetching ak
	[jolsa@krava perf]$ git branch -r | grep stat-metrics-21
	[jolsa@krava perf]$

jirka

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

[Andi Kleen]

On Mon, Mar 07, 2016 at 07:48:39PM +0100, Jiri Olsa wrote:
> On Mon, Mar 07, 2016 at 07:22:27PM +0100, Andi Kleen wrote:
> > On Mon, Mar 07, 2016 at 11:08:42AM +0100, Jiri Olsa wrote:
> > > On Thu, Mar 03, 2016 at 03:57:31PM -0800, Andi Kleen wrote:
> > > 
> > > SNIP
> > > 
> > > > 
> > > > % perf stat -x, --metric-only  -a -I 1000
> > > >      1.001381652,frontend cycles idle,insn per cycle,stalled cycles per insn,branch-misses of all branches,
> > > >      1.001381652,173.32,0.83,2.09,1.73,
> > > >      2.002073343,199.47,1.07,1.60,2.14,
> > > >      3.002875524,109.52,0.22,7.83,1.63,
> > > >      4.003970059,132.10,0.17,10.85,1.51,
> > > >      5.004818754,181.60,0.22,8.87,2.22,
> > > > 
> > > > 
> > > > Available in
> > > > git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-21
> > > 
> > > this branch contains old version of:
> > >   perf, tools, stat: Add --metric-only support for -A
> > 
> > Old in what way? Looks correct to me.
> > 
> > 
> > commit e26ba80593023c24c8276ad9853acd7e56ca92ed
> > Author: Andi Kleen <ak@linux.intel.com>
> > Date:   Sat Dec 19 11:22:55 2015 -0800
> > 
> >     perf, tools, stat: Add --metric-only support for -A
> >     
> >     Add metric only support for -A too. This requires a new print
> >     function that prints the metrics in the right order.
> >     
> >     v2: Fix manpage
> >     v3: Simplify nrcpus computation
> >     Signed-off-by: Andi Kleen <ak@linux.intel.com>
> 
> I did not see the change for print_no_aggr_metric function
> in commit:
>    perf, tools, stat: Add --metric-only support for -A
> 
> which I saw in the email..
> 
> however now im confused, I did not noticed I had a wrong tree,
> however git can't resolve the git tree you mentioned:

I pushed again. Can you try again? Probably I made some mistake with
git.

-Andi

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

[Jiri Olsa]

On Mon, Mar 07, 2016 at 10:11:43PM +0100, Andi Kleen wrote:

SNIP

> > 
> > I did not see the change for print_no_aggr_metric function
> > in commit:
> >    perf, tools, stat: Add --metric-only support for -A
> > 
> > which I saw in the email..
> > 
> > however now im confused, I did not noticed I had a wrong tree,
> > however git can't resolve the git tree you mentioned:
> 
> I pushed again. Can you try again? Probably I made some mistake with
> git.

I rebased your branch on top of current Arlnaldo's perf/core
and only 3 patches were missing.. I just ack-ed them

thanks,
jirka

perf, tools: Refactor and support interval and CSV metrics

[Andi Kleen]

Fixed even more last feedback.

[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.]
[v7: Reorder and merge two patches to avoid a bisect hole where unsupported was
printed as 0]
[v8: Minor fixes for review feedback. See changelog in patches.]
[v9: Fix newline bug. Add support for -A for --metric-only]
[v10: Remove extra "noise" printing (Jiri)
      Fix fields in documentation (Jiri)]
[v11: Fix manpage again. Avoid extra metric output in CSV mode.]
[v12: Move CSV metrics fields to after running/enabled/variance.
      Minor fixes.]
[v13: Address review comments. Now probe for stalled events 
      in advance to avoid empty columns or lines. Fix -A shadowing.
      Various minor changes. Drop merged patches.]
[v14: Fix empty lines with CSV metrics. Avoid one more empty column
      in metric-only.]
[v15: Add missing fields in manpage. Use extra init function 
      for frontend event. Various smaller fixes. Add acked-by.]
[v16: Fix manpage again. Merge --per-thread crash patch.
      Add comments to --metric-only.]

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,
and finally a --metric-only 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
     1.000982778,12006.549977,,task-clock,12006547787,100.00,,,,
     1.000982778,12822,,context-switches,12007100604,100.00,0.001,M/sec
     1.000982778,175,,cpu-migrations,12007180306,100.00,0.015,K/sec
     1.000982778,3404,,page-faults,12007185482,100.00,0.284,K/sec
     1.000982778,1930307489,,cycles,12007018233,100.00,0.161,GHz
     1.000982778,6971803638,,stalled-cycles-frontend,12006902870,100.00,361.18,frontend cycles idle
     1.000982778,464493941,,instructions,12006873327,100.00,0.24,insn per cycle
     1.000982778,,,,,,15.01,stalled cycles per insn
     1.000982778,86548409,,branches,12006758420,100.00,7.208,M/sec
     1.000982778,4933638,,branch-misses,12006648104,100.00,5.70,of all branches

Now includes metrics

Metric only mode:

Concicse information if you only care about computed metrics, not raw values

% perf stat --metric-only  -a -I 1000
         1.001452803 frontend cycles idle insn per cycle       stalled cycles per insn branch-misses of all branches
         1.001452803  158.91%               0.66                2.39                    2.92%
         2.002192321  180.63%               0.76                2.08                    2.96%
         3.003088282  150.59%               0.62                2.57                    2.84%
         4.004369835  196.20%               0.98                1.62                    3.79%
         5.005227314  231.98%               0.84                1.90                    4.71%


Metric only mode in CSV (flat format, easy to plot and analyze in statistical tools like JMP, R, pandas, gnuplot):

% perf stat -x, --metric-only  -a -I 1000
     1.001381652,frontend cycles idle,insn per cycle,stalled cycles per insn,branch-misses of all branches,
     1.001381652,173.32,0.83,2.09,1.73,
     2.002073343,199.47,1.07,1.60,2.14,
     3.002875524,109.52,0.22,7.83,1.63,
     4.003970059,132.10,0.17,10.85,1.51,
     5.004818754,181.60,0.22,8.87,2.22,


Available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-20

[PATCH 6/7] perf, tools, stat: Add --metric-only support for -A

[Andi Kleen]

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

Add metric only support for -A too. This requires a new print
function that prints the metrics in the right order.

v2: Fix manpage
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt |  2 +-
 tools/perf/builtin-stat.c              | 48 ++++++++++++++++++++++++++++------
 2 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 271f71d..341757a 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -141,7 +141,7 @@ The overhead percentage could be high in some cases, for instance with small, su
 
 --metric-only::
 Only print computed metrics. Print them in a single line.
-Don't show any raw values. Not supported with -A or --per-thread.
+Don't show any raw values. Not supported with --per-thread.
 
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0196fed..42975ae 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1250,10 +1250,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+static void print_no_aggr_metric(char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	evlist__for_each(evsel_list, counter) {
+		nrcpus = perf_evsel__nr_cpus(counter);
+		break;
+	}
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, stat_config.output);
+		evlist__for_each(evsel_list, counter) {
+			if (first) {
+				aggr_printout(counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+		}
+		fputc('\n', stat_config.output);
+	}
+}
+
 static int aggr_header_lens[] = {
 	[AGGR_CORE] = 18,
 	[AGGR_SOCKET] = 12,
-	[AGGR_NONE] = 15,
+	[AGGR_NONE] = 6,
 	[AGGR_THREAD] = 24,
 	[AGGR_GLOBAL] = 0,
 };
@@ -1408,8 +1441,12 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
+		if (metric_only)
+			print_no_aggr_metric(prefix);
+		else {
+			evlist__for_each(evsel_list, counter)
+				print_counter(counter, prefix);
+		}
 		break;
 	case AGGR_UNSET:
 	default:
@@ -2177,11 +2214,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
-	if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
-		fprintf(stderr, "--metric-only is not supported with -A\n");
-		goto out;
-	}
-
 	if (metric_only && run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;
-- 
2.5.0

Re: [PATCH 6/7] perf, tools, stat: Add --metric-only support for -A

[Jiri Olsa]

On Wed, Mar 02, 2016 at 04:24:57PM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Add metric only support for -A too. This requires a new print
> function that prints the metrics in the right order.
> 
> v2: Fix manpage
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  tools/perf/Documentation/perf-stat.txt |  2 +-
>  tools/perf/builtin-stat.c              | 48 ++++++++++++++++++++++++++++------
>  2 files changed, 41 insertions(+), 9 deletions(-)
> 
> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
> index 271f71d..341757a 100644
> --- a/tools/perf/Documentation/perf-stat.txt
> +++ b/tools/perf/Documentation/perf-stat.txt
> @@ -141,7 +141,7 @@ The overhead percentage could be high in some cases, for instance with small, su
>  
>  --metric-only::
>  Only print computed metrics. Print them in a single line.
> -Don't show any raw values. Not supported with -A or --per-thread.
> +Don't show any raw values. Not supported with --per-thread.
>  
>  --per-socket::
>  Aggregate counts per processor socket for system-wide mode measurements.  This
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 0196fed..42975ae 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -1250,10 +1250,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
>  	}
>  }
>  
> +static void print_no_aggr_metric(char *prefix)
> +{
> +	int cpu;
> +	int nrcpus = 0;
> +	struct perf_evsel *counter;
> +	u64 ena, run, val;
> +	double uval;
> +
> +	evlist__for_each(evsel_list, counter) {
> +		nrcpus = perf_evsel__nr_cpus(counter);
> +		break;
> +	}

what's the loop for? why can't you use evsel_list->cpus ?

jirka

perf, tools: Refactor and support interval and CSV metrics

[Andi Kleen]

Fixed even more last feedback.

[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.]
[v7: Reorder and merge two patches to avoid a bisect hole where unsupported was
printed as 0]
[v8: Minor fixes for review feedback. See changelog in patches.]
[v9: Fix newline bug. Add support for -A for --metric-only]
[v10: Remove extra "noise" printing (Jiri)
      Fix fields in documentation (Jiri)]
[v11: Fix manpage again. Avoid extra metric output in CSV mode.]
[v12: Move CSV metrics fields to after running/enabled/variance.
      Minor fixes.]
[v13: Address review comments. Now probe for stalled events 
      in advance to avoid empty columns or lines. Fix -A shadowing.
      Various minor changes. Drop merged patches.]
[v14: Fix empty lines with CSV metrics. Avoid one more empty column
      in metric-only.]
[v15: Add missing fields in manpage. Use extra init function 
      for frontend event. Various smaller fixes. Add acked-by.]

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,
and finally a --metric-only 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
     1.000982778,12006.549977,,task-clock,12006547787,100.00,,,,
     1.000982778,12822,,context-switches,12007100604,100.00,0.001,M/sec
     1.000982778,175,,cpu-migrations,12007180306,100.00,0.015,K/sec
     1.000982778,3404,,page-faults,12007185482,100.00,0.284,K/sec
     1.000982778,1930307489,,cycles,12007018233,100.00,0.161,GHz
     1.000982778,6971803638,,stalled-cycles-frontend,12006902870,100.00,361.18,frontend cycles idle
     1.000982778,464493941,,instructions,12006873327,100.00,0.24,insn per cycle
     1.000982778,,,,,,15.01,stalled cycles per insn
     1.000982778,86548409,,branches,12006758420,100.00,7.208,M/sec
     1.000982778,4933638,,branch-misses,12006648104,100.00,5.70,of all branches

Now includes metrics

Metric only mode:

Concicse information if you only care about computed metrics, not raw values

% perf stat --metric-only  -a -I 1000
         1.001452803 frontend cycles idle insn per cycle       stalled cycles per insn branch-misses of all branches
         1.001452803  158.91%               0.66                2.39                    2.92%
         2.002192321  180.63%               0.76                2.08                    2.96%
         3.003088282  150.59%               0.62                2.57                    2.84%
         4.004369835  196.20%               0.98                1.62                    3.79%
         5.005227314  231.98%               0.84                1.90                    4.71%


Metric only mode in CSV (flat format, easy to plot and analyze in statistical tools like JMP, R, pandas, gnuplot):

% perf stat -x, --metric-only  -a -I 1000
     1.001381652,frontend cycles idle,insn per cycle,stalled cycles per insn,branch-misses of all branches,
     1.001381652,173.32,0.83,2.09,1.73,
     2.002073343,199.47,1.07,1.60,2.14,
     3.002875524,109.52,0.22,7.83,1.63,
     4.003970059,132.10,0.17,10.85,1.51,
     5.004818754,181.60,0.22,8.87,2.22,


Available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-19

[PATCH 6/7] perf, tools, stat: Add --metric-only support for -A

[Andi Kleen]

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

Add metric only support for -A too. This requires a new print
function that prints the metrics in the right order.

v2: Fix manpage
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt |  2 +-
 tools/perf/builtin-stat.c              | 48 ++++++++++++++++++++++++++++------
 2 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 60ef33d..1591a1a 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -141,7 +141,7 @@ The overhead percentage could be high in some cases, for instance with small, su
 
 --metric-only::
 Only print computed metrics. Print them in a single line.
-Don't show any raw values. Not supported with -A or --per-thread.
+Don't show any raw values. Not supported with --per-thread.
 
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 30bb0ac..78a4205 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1243,10 +1243,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+static void print_no_aggr_metric(char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	evlist__for_each(evsel_list, counter) {
+		nrcpus = perf_evsel__nr_cpus(counter);
+		break;
+	}
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, stat_config.output);
+		evlist__for_each(evsel_list, counter) {
+			if (first) {
+				aggr_printout(counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+		}
+		fputc('\n', stat_config.output);
+	}
+}
+
 static int aggr_header_lens[] = {
 	[AGGR_CORE] = 18,
 	[AGGR_SOCKET] = 12,
-	[AGGR_NONE] = 15,
+	[AGGR_NONE] = 6,
 	[AGGR_THREAD] = 24,
 	[AGGR_GLOBAL] = 0,
 };
@@ -1401,8 +1434,12 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
+		if (metric_only)
+			print_no_aggr_metric(prefix);
+		else {
+			evlist__for_each(evsel_list, counter)
+				print_counter(counter, prefix);
+		}
 		break;
 	case AGGR_UNSET:
 	default:
@@ -2170,11 +2207,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
-	if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
-		fprintf(stderr, "--metric-only is not supported with -A\n");
-		goto out;
-	}
-
 	if (metric_only && run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;
-- 
2.5.0

perf, tools: Refactor and support interval and CSV metrics

[Andi Kleen]

Fixed last feedback.

[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.]
[v7: Reorder and merge two patches to avoid a bisect hole where unsupported was
printed as 0]
[v8: Minor fixes for review feedback. See changelog in patches.]
[v9: Fix newline bug. Add support for -A for --metric-only]
[v10: Remove extra "noise" printing (Jiri)
      Fix fields in documentation (Jiri)]
[v11: Fix manpage again. Avoid extra metric output in CSV mode.]
[v12: Move CSV metrics fields to after running/enabled/variance.
      Minor fixes.]
[v13: Address review comments. Now probe for stalled events 
      in advance to avoid empty columns or lines. Fix -A shadowing.
      Various minor changes. Drop merged patches.]
[v14: Fix empty lines with CSV metrics. Avoid one more empty column
      in metric-only.]

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,
and finally a --metric-only 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
     1.000982778,12006.549977,,task-clock,12006547787,100.00,,,,
     1.000982778,12822,,context-switches,12007100604,100.00,0.001,M/sec
     1.000982778,175,,cpu-migrations,12007180306,100.00,0.015,K/sec
     1.000982778,3404,,page-faults,12007185482,100.00,0.284,K/sec
     1.000982778,1930307489,,cycles,12007018233,100.00,0.161,GHz
     1.000982778,6971803638,,stalled-cycles-frontend,12006902870,100.00,361.18,frontend cycles idle
     1.000982778,464493941,,instructions,12006873327,100.00,0.24,insn per cycle
     1.000982778,,,,,,15.01,stalled cycles per insn
     1.000982778,86548409,,branches,12006758420,100.00,7.208,M/sec
     1.000982778,4933638,,branch-misses,12006648104,100.00,5.70,of all branches

Now includes metrics

Metric only mode:

Concicse information if you only care about computed metrics, not raw values

% perf stat --metric-only  -a -I 1000
         1.001452803 frontend cycles idle insn per cycle       stalled cycles per insn branch-misses of all branches
         1.001452803  158.91%               0.66                2.39                    2.92%
         2.002192321  180.63%               0.76                2.08                    2.96%
         3.003088282  150.59%               0.62                2.57                    2.84%
         4.004369835  196.20%               0.98                1.62                    3.79%
         5.005227314  231.98%               0.84                1.90                    4.71%


Metric only mode in CSV (flat format, easy to plot and analyze in statistical tools like JMP, R, pandas, gnuplot):

% perf stat -x, --metric-only  -a -I 1000
     1.001381652,frontend cycles idle,insn per cycle,stalled cycles per insn,branch-misses of all branches,
     1.001381652,173.32,0.83,2.09,1.73,
     2.002073343,199.47,1.07,1.60,2.14,
     3.002875524,109.52,0.22,7.83,1.63,
     4.003970059,132.10,0.17,10.85,1.51,
     5.004818754,181.60,0.22,8.87,2.22,


Available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc-2.6 perf/stat-metrics-18

[PATCH 6/7] perf, tools, stat: Add --metric-only support for -A

[Andi Kleen]

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

Add metric only support for -A too. This requires a new print
function that prints the metrics in the right order.

v2: Fix manpage
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt |  2 +-
 tools/perf/builtin-stat.c              | 48 ++++++++++++++++++++++++++++------
 2 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 3929ab0..44095cd 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -141,7 +141,7 @@ The overhead percentage could be high in some cases, for instance with small, su
 
 --metric-only::
 Only print computed metrics. Print them in a single line.
-Don't show any raw values. Not supported with -A or --per-thread.
+Don't show any raw values. Not supported with --per-thread.
 
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 30bb0ac..78a4205 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1243,10 +1243,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
+static void print_no_aggr_metric(char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	evlist__for_each(evsel_list, counter) {
+		nrcpus = perf_evsel__nr_cpus(counter);
+		break;
+	}
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, stat_config.output);
+		evlist__for_each(evsel_list, counter) {
+			if (first) {
+				aggr_printout(counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+		}
+		fputc('\n', stat_config.output);
+	}
+}
+
 static int aggr_header_lens[] = {
 	[AGGR_CORE] = 18,
 	[AGGR_SOCKET] = 12,
-	[AGGR_NONE] = 15,
+	[AGGR_NONE] = 6,
 	[AGGR_THREAD] = 24,
 	[AGGR_GLOBAL] = 0,
 };
@@ -1401,8 +1434,12 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
+		if (metric_only)
+			print_no_aggr_metric(prefix);
+		else {
+			evlist__for_each(evsel_list, counter)
+				print_counter(counter, prefix);
+		}
 		break;
 	case AGGR_UNSET:
 	default:
@@ -2170,11 +2207,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
-	if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
-		fprintf(stderr, "--metric-only is not supported with -A\n");
-		goto out;
-	}
-
 	if (metric_only && run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;
-- 
2.5.0