[PATCH v4 0/4] perf stat: Support overall statistics for interval mode

[PATCH v4 0/4] perf stat: Support overall statistics for interval mode

[Jin Yao]

Currently perf-stat supports to print counts at regular interval (-I),
but it's not very easy for user to get the overall statistics.

With this patchset, it supports to report the summary at the end of
interval output.

For example,

 root@kbl-ppc:~# perf stat -e cycles -I1000 --interval-count 2
 #           time             counts unit events
      1.000412064          2,281,114      cycles
      2.001383658          2,547,880      cycles

  Performance counter stats for 'system wide':

          4,828,994      cycles

        2.002860349 seconds time elapsed

 root@kbl-ppc:~# perf stat -e cycles,instructions -I1000 --interval-count 2
 #           time             counts unit events
      1.000389902          1,536,093      cycles
      1.000389902            420,226      instructions              #    0.27  insn per cycle
      2.001433453          2,213,952      cycles
      2.001433453            735,465      instructions              #    0.33  insn per cycle

  Performance counter stats for 'system wide':

          3,750,045      cycles
          1,155,691      instructions              #    0.31  insn per cycle

        2.003023361 seconds time elapsed

 root@kbl-ppc:~# perf stat -M CPI,IPC -I1000 --interval-count 2
 #           time             counts unit events
      1.000435121            905,303      inst_retired.any          #      2.9 CPI
      1.000435121          2,663,333      cycles
      1.000435121            914,702      inst_retired.any          #      0.3 IPC
      1.000435121          2,676,559      cpu_clk_unhalted.thread
      2.001615941          1,951,092      inst_retired.any          #      1.8 CPI
      2.001615941          3,551,357      cycles
      2.001615941          1,950,837      inst_retired.any          #      0.5 IPC
      2.001615941          3,551,044      cpu_clk_unhalted.thread

  Performance counter stats for 'system wide':

          2,856,395      inst_retired.any          #      2.2 CPI
          6,214,690      cycles
          2,865,539      inst_retired.any          #      0.5 IPC
          6,227,603      cpu_clk_unhalted.thread

        2.003403078 seconds time elapsed

 v4:
 ---
 1. Create runtime_stat_reset.

 2. Zero the aggr in perf_counts__reset and use it to reset
    prev_raw_counts.

 3. Move affinity setup and read_counter_cpu to a new function
    read_affinity_counters. It's only called when stat_config.summary
    is not set.

 v3:
 ---
 1. 'perf stat: Fix wrong per-thread runtime stat for interval mode'
    is a new patch which fixes an existing issue found in test.

 2. We use the prev_raw_counts for summary counts. Drop the summary_counts in v2.

 3. Fix some issues.

 v2:
 ---
 Rebase to perf/core branch

Jin Yao (4):
  perf stat: Fix wrong per-thread runtime stat for interval mode
  perf counts: Reset prev_raw_counts counts
  perf stat: Copy counts from prev_raw_counts to evsel->counts
  perf stat: Report summary for interval mode

 tools/perf/builtin-stat.c | 97 ++++++++++++++++++++++++++-------------
 tools/perf/util/counts.c  |  4 +-
 tools/perf/util/counts.h  |  1 +
 tools/perf/util/evsel.c   |  1 +
 tools/perf/util/stat.c    | 33 ++++++++++---
 tools/perf/util/stat.h    |  2 +
 6 files changed, 99 insertions(+), 39 deletions(-)

-- 
2.17.1

[PATCH v4 1/4] perf stat: Fix wrong per-thread runtime stat for interval mode

[Jin Yao]

root@kbl-ppc:~# perf stat --per-thread -e cycles,instructions -I1000 --interval-count 2
     1.004171683             perf-3696              8,747,311      cycles
        ...
     1.004171683             perf-3696                691,730      instructions              #    0.08  insn per cycle
        ...
     2.006490373             perf-3696              1,749,936      cycles
        ...
     2.006490373             perf-3696              1,484,582      instructions              #    0.28  insn per cycle
        ...

Let's see interval 2.006490373

perf-3696              1,749,936      cycles
perf-3696              1,484,582      instructions              #    0.28  insn per cycle

insn per cycle = 1,484,582 / 1,749,936 = 0.85.
But now it's 0.28, that's not correct.

stat_config.stats[] records the per-thread runtime stat. But for interval
mode, it should be reset for each interval.

So now, with this patch,

root@kbl-ppc:~# perf stat --per-thread -e cycles,instructions -I1000 --interval-count 2
     1.005818121             perf-8633              9,898,045      cycles
        ...
     1.005818121             perf-8633                693,298      instructions              #    0.07  insn per cycle
        ...
     2.007863743             perf-8633              1,551,619      cycles
        ...
     2.007863743             perf-8633              1,317,514      instructions              #    0.85  insn per cycle
        ...

Let's check interval 2.007863743.

insn per cycle = 1,317,514 / 1,551,619 = 0.85. It's correct.

This patch creates runtime_stat_reset, places it next to
untime_stat_new/runtime_stat_delete and moves all runtime_stat
functions before process_interval.

 v4:
 ---
 Create runtime_stat_reset.

Fixes: commit 14e72a21c783 ("perf stat: Update or print per-thread stats")
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
---
 tools/perf/builtin-stat.c | 70 +++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 29 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e0c1ad23c768..f3b3a59ac7d2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -351,6 +351,46 @@ static void read_counters(struct timespec *rs)
 	}
 }
 
+static int runtime_stat_new(struct perf_stat_config *config, int nthreads)
+{
+	int i;
+
+	config->stats = calloc(nthreads, sizeof(struct runtime_stat));
+	if (!config->stats)
+		return -1;
+
+	config->stats_num = nthreads;
+
+	for (i = 0; i < nthreads; i++)
+		runtime_stat__init(&config->stats[i]);
+
+	return 0;
+}
+
+static void runtime_stat_delete(struct perf_stat_config *config)
+{
+	int i;
+
+	if (!config->stats)
+		return;
+
+	for (i = 0; i < config->stats_num; i++)
+		runtime_stat__exit(&config->stats[i]);
+
+	zfree(&config->stats);
+}
+
+static void runtime_stat_reset(struct perf_stat_config *config)
+{
+	int i;
+
+	if (!config->stats)
+		return;
+
+	for (i = 0; i < config->stats_num; i++)
+		perf_stat__reset_shadow_per_stat(&config->stats[i]);
+}
+
 static void process_interval(void)
 {
 	struct timespec ts, rs;
@@ -359,6 +399,7 @@ static void process_interval(void)
 	diff_timespec(&rs, &ts, &ref_time);
 
 	perf_stat__reset_shadow_per_stat(&rt_stat);
+	runtime_stat_reset(&stat_config);
 	read_counters(&rs);
 
 	if (STAT_RECORD) {
@@ -1737,35 +1778,6 @@ int process_cpu_map_event(struct perf_session *session,
 	return set_maps(st);
 }
 
-static int runtime_stat_new(struct perf_stat_config *config, int nthreads)
-{
-	int i;
-
-	config->stats = calloc(nthreads, sizeof(struct runtime_stat));
-	if (!config->stats)
-		return -1;
-
-	config->stats_num = nthreads;
-
-	for (i = 0; i < nthreads; i++)
-		runtime_stat__init(&config->stats[i]);
-
-	return 0;
-}
-
-static void runtime_stat_delete(struct perf_stat_config *config)
-{
-	int i;
-
-	if (!config->stats)
-		return;
-
-	for (i = 0; i < config->stats_num; i++)
-		runtime_stat__exit(&config->stats[i]);
-
-	zfree(&config->stats);
-}
-
 static const char * const stat_report_usage[] = {
 	"perf stat report [<options>]",
 	NULL,
-- 
2.17.1

[PATCH v4 2/4] perf counts: Reset prev_raw_counts counts

[Jin Yao]

When we want to reset the evsel->prev_raw_counts, zeroing the aggr
is not enough, we need to reset the perf_counts too.

The perf_counts__reset zeros the perf_counts, and it should zero
the aggr too. This patch changes perf_counts__reset to non-static,
and calls it in evsel__reset_prev_raw_counts to reset the
prev_raw_counts.

 v4:
 ---
 Zeroing the aggr in perf_counts__reset and use it to reset
 prev_raw_counts.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
---
 tools/perf/util/counts.c | 4 +++-
 tools/perf/util/counts.h | 1 +
 tools/perf/util/stat.c   | 7 ++-----
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index 615c9f3e95cb..582f3aeaf5e4 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <stdlib.h>
+#include <string.h>
 #include "evsel.h"
 #include "counts.h"
 #include <linux/zalloc.h>
@@ -42,10 +43,11 @@ void perf_counts__delete(struct perf_counts *counts)
 	}
 }
 
-static void perf_counts__reset(struct perf_counts *counts)
+void perf_counts__reset(struct perf_counts *counts)
 {
 	xyarray__reset(counts->loaded);
 	xyarray__reset(counts->values);
+	memset(&counts->aggr, 0, sizeof(struct perf_counts_values));
 }
 
 void evsel__reset_counts(struct evsel *evsel)
diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 8f556c6d98fa..7ff36bf6d644 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -37,6 +37,7 @@ perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool lo
 
 struct perf_counts *perf_counts__new(int ncpus, int nthreads);
 void perf_counts__delete(struct perf_counts *counts);
+void perf_counts__reset(struct perf_counts *counts);
 
 void evsel__reset_counts(struct evsel *evsel);
 int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index f4a44df9b221..e397815f0dfb 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -163,11 +163,8 @@ static void evsel__free_prev_raw_counts(struct evsel *evsel)
 
 static void evsel__reset_prev_raw_counts(struct evsel *evsel)
 {
-	if (evsel->prev_raw_counts) {
-		evsel->prev_raw_counts->aggr.val = 0;
-		evsel->prev_raw_counts->aggr.ena = 0;
-		evsel->prev_raw_counts->aggr.run = 0;
-       }
+	if (evsel->prev_raw_counts)
+		perf_counts__reset(evsel->prev_raw_counts);
 }
 
 static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
-- 
2.17.1

[PATCH v4 3/4] perf stat: Copy counts from prev_raw_counts to evsel->counts

[Jin Yao]

It would be useful to support the overall statistics for perf-stat
interval mode. For example, report the summary at the end of
"perf-stat -I" output.

But since perf-stat can support many aggregation modes, such as
--per-thread, --per-socket, -M and etc, we need a solution which
doesn't bring much complexity.

The idea is to use 'evsel->prev_raw_counts' which is updated in
each interval and it's saved with the latest counts. Before reporting
the summary, we copy the counts from evsel->prev_raw_counts to
evsel->counts, and next we just follow non-interval processing.

In evsel__compute_deltas, this patch saves counts to the member
[cpu0,thread0] of perf_counts for AGGR_GLOBAL.

That's because after copying evsel->prev_raw_counts to evsel->counts,
perf_counts(evsel->counts, cpu, thread) are all 0 for AGGR_GLOBAL.
Once we go to process_counter_maps again, all members of perf_counts
are 0.

So this patch uses a trick that saves the previous aggr value to
the member [cpu0,thread0] of perf_counts, then aggr calculation
in process_counter_values can work correctly.

 v4:
 ---
 Change the commit message.
 No functional change.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
---
 tools/perf/util/evsel.c |  1 +
 tools/perf/util/stat.c  | 24 ++++++++++++++++++++++++
 tools/perf/util/stat.h  |  1 +
 3 files changed, 26 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 28683b0eb738..6fae1ec28886 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1283,6 +1283,7 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
 	if (cpu == -1) {
 		tmp = evsel->prev_raw_counts->aggr;
 		evsel->prev_raw_counts->aggr = *count;
+		*perf_counts(evsel->prev_raw_counts, 0, 0) = *count;
 	} else {
 		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
 		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index e397815f0dfb..aadc723ce871 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -225,6 +225,30 @@ void perf_evlist__reset_prev_raw_counts(struct evlist *evlist)
 		evsel__reset_prev_raw_counts(evsel);
 }
 
+static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel)
+{
+	int ncpus = evsel__nr_cpus(evsel);
+	int nthreads = perf_thread_map__nr(evsel->core.threads);
+
+	for (int thread = 0; thread < nthreads; thread++) {
+		for (int cpu = 0; cpu < ncpus; cpu++) {
+			*perf_counts(evsel->counts, cpu, thread) =
+				*perf_counts(evsel->prev_raw_counts, cpu,
+					     thread);
+		}
+	}
+
+	evsel->counts->aggr = evsel->prev_raw_counts->aggr;
+}
+
+void perf_evlist__copy_prev_raw_counts(struct evlist *evlist)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		perf_evsel__copy_prev_raw_counts(evsel);
+}
+
 static void zero_per_pkg(struct evsel *counter)
 {
 	if (counter->per_pkg_mask)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index b4fdfaa7f2c0..62cf72c71869 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -198,6 +198,7 @@ int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct evlist *evlist);
 void perf_evlist__reset_stats(struct evlist *evlist);
 void perf_evlist__reset_prev_raw_counts(struct evlist *evlist);
+void perf_evlist__copy_prev_raw_counts(struct evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct evsel *counter);
-- 
2.17.1

Re: [PATCH v4 3/4] perf stat: Copy counts from prev_raw_counts to evsel->counts

[Jiri Olsa]

On Fri, May 08, 2020 at 03:58:16PM +0800, Jin Yao wrote:
> It would be useful to support the overall statistics for perf-stat
> interval mode. For example, report the summary at the end of
> "perf-stat -I" output.
> 
> But since perf-stat can support many aggregation modes, such as
> --per-thread, --per-socket, -M and etc, we need a solution which
> doesn't bring much complexity.
> 
> The idea is to use 'evsel->prev_raw_counts' which is updated in
> each interval and it's saved with the latest counts. Before reporting
> the summary, we copy the counts from evsel->prev_raw_counts to
> evsel->counts, and next we just follow non-interval processing.
> 
> In evsel__compute_deltas, this patch saves counts to the member
> [cpu0,thread0] of perf_counts for AGGR_GLOBAL.
> 
> That's because after copying evsel->prev_raw_counts to evsel->counts,
> perf_counts(evsel->counts, cpu, thread) are all 0 for AGGR_GLOBAL.
> Once we go to process_counter_maps again, all members of perf_counts
> are 0.
> 
> So this patch uses a trick that saves the previous aggr value to
> the member [cpu0,thread0] of perf_counts, then aggr calculation
> in process_counter_values can work correctly.
> 
>  v4:
>  ---
>  Change the commit message.
>  No functional change.
> 
> Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
> ---
>  tools/perf/util/evsel.c |  1 +
>  tools/perf/util/stat.c  | 24 ++++++++++++++++++++++++
>  tools/perf/util/stat.h  |  1 +
>  3 files changed, 26 insertions(+)
> 
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 28683b0eb738..6fae1ec28886 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1283,6 +1283,7 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
>  	if (cpu == -1) {
>  		tmp = evsel->prev_raw_counts->aggr;
>  		evsel->prev_raw_counts->aggr = *count;
> +		*perf_counts(evsel->prev_raw_counts, 0, 0) = *count;

ok, I think I understand that now.. it's only for AGGR_GLOBAL mode,
because the perf_stat_process_counter will create aggr values from
per cpu values

but why do we need to do that all the time? can't we just set it up
before you zero prev_raw_counts in next patch?


        if (interval) {
                stat_config.interval = 0;
                stat_config.summary = true;
                perf_evlist__copy_prev_raw_counts(evsel_list);

	-> for AGGR_GLOBAL set the counts[0,0] to prev_raw_counts->aggr

                perf_evlist__reset_prev_raw_counts(evsel_list);
                runtime_stat_reset(&stat_config);
                perf_stat__reset_shadow_per_stat(&rt_stat);
        }


thanks,
jirka

Re: [PATCH v4 3/4] perf stat: Copy counts from prev_raw_counts to evsel->counts

[Jin, Yao]

Hi Jiri,

On 5/13/2020 11:31 PM, Jiri Olsa wrote:
> On Fri, May 08, 2020 at 03:58:16PM +0800, Jin Yao wrote:
>> It would be useful to support the overall statistics for perf-stat
>> interval mode. For example, report the summary at the end of
>> "perf-stat -I" output.
>>
>> But since perf-stat can support many aggregation modes, such as
>> --per-thread, --per-socket, -M and etc, we need a solution which
>> doesn't bring much complexity.
>>
>> The idea is to use 'evsel->prev_raw_counts' which is updated in
>> each interval and it's saved with the latest counts. Before reporting
>> the summary, we copy the counts from evsel->prev_raw_counts to
>> evsel->counts, and next we just follow non-interval processing.
>>
>> In evsel__compute_deltas, this patch saves counts to the member
>> [cpu0,thread0] of perf_counts for AGGR_GLOBAL.
>>
>> That's because after copying evsel->prev_raw_counts to evsel->counts,
>> perf_counts(evsel->counts, cpu, thread) are all 0 for AGGR_GLOBAL.
>> Once we go to process_counter_maps again, all members of perf_counts
>> are 0.
>>
>> So this patch uses a trick that saves the previous aggr value to
>> the member [cpu0,thread0] of perf_counts, then aggr calculation
>> in process_counter_values can work correctly.
>>
>>   v4:
>>   ---
>>   Change the commit message.
>>   No functional change.
>>
>> Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
>> ---
>>   tools/perf/util/evsel.c |  1 +
>>   tools/perf/util/stat.c  | 24 ++++++++++++++++++++++++
>>   tools/perf/util/stat.h  |  1 +
>>   3 files changed, 26 insertions(+)
>>
>> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
>> index 28683b0eb738..6fae1ec28886 100644
>> --- a/tools/perf/util/evsel.c
>> +++ b/tools/perf/util/evsel.c
>> @@ -1283,6 +1283,7 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
>>   	if (cpu == -1) {
>>   		tmp = evsel->prev_raw_counts->aggr;
>>   		evsel->prev_raw_counts->aggr = *count;
>> +		*perf_counts(evsel->prev_raw_counts, 0, 0) = *count;
> 
> ok, I think I understand that now.. it's only for AGGR_GLOBAL mode,
> because the perf_stat_process_counter will create aggr values from
> per cpu values
> 
> but why do we need to do that all the time? can't we just set it up
> before you zero prev_raw_counts in next patch?
> 
> 
>          if (interval) {
>                  stat_config.interval = 0;
>                  stat_config.summary = true;
>                  perf_evlist__copy_prev_raw_counts(evsel_list);
> 
> 	-> for AGGR_GLOBAL set the counts[0,0] to prev_raw_counts->aggr
> 
>                  perf_evlist__reset_prev_raw_counts(evsel_list);
>                  runtime_stat_reset(&stat_config);
>                  perf_stat__reset_shadow_per_stat(&rt_stat);
>          }
>


Yes, I think that's a good idea.

Now in v5, I create a new patch "perf stat: Save aggr value to first member of 
prev_raw_counts" to save aggr value to first member of prev_raw_counts for 
AGGR_GLOBAL. Then next, perf_stat_process_counter can create aggr values from 
per cpu values successfully.

Thanks
Jin Yao

> 
> thanks,
> jirka
> 

[PATCH v4 4/4] perf stat: Report summary for interval mode

[Jin Yao]

Currently perf-stat supports to print counts at regular interval (-I),
but it's not very easy for user to get the overall statistics.

The patch uses 'evsel->prev_raw_counts' to get counts for summary.
Copy the counts to 'evsel->counts' after printing the interval results.
Next, we just follow the non-interval processing.

Let's see some examples,

 root@kbl-ppc:~# perf stat -e cycles -I1000 --interval-count 2
 #           time             counts unit events
      1.000412064          2,281,114      cycles
      2.001383658          2,547,880      cycles

  Performance counter stats for 'system wide':

          4,828,994      cycles

        2.002860349 seconds time elapsed

 root@kbl-ppc:~# perf stat -e cycles,instructions -I1000 --interval-count 2
 #           time             counts unit events
      1.000389902          1,536,093      cycles
      1.000389902            420,226      instructions              #    0.27  insn per cycle
      2.001433453          2,213,952      cycles
      2.001433453            735,465      instructions              #    0.33  insn per cycle

  Performance counter stats for 'system wide':

          3,750,045      cycles
          1,155,691      instructions              #    0.31  insn per cycle

        2.003023361 seconds time elapsed

 root@kbl-ppc:~# perf stat -M CPI,IPC -I1000 --interval-count 2
 #           time             counts unit events
      1.000435121            905,303      inst_retired.any          #      2.9 CPI
      1.000435121          2,663,333      cycles
      1.000435121            914,702      inst_retired.any          #      0.3 IPC
      1.000435121          2,676,559      cpu_clk_unhalted.thread
      2.001615941          1,951,092      inst_retired.any          #      1.8 CPI
      2.001615941          3,551,357      cycles
      2.001615941          1,950,837      inst_retired.any          #      0.5 IPC
      2.001615941          3,551,044      cpu_clk_unhalted.thread

  Performance counter stats for 'system wide':

          2,856,395      inst_retired.any          #      2.2 CPI
          6,214,690      cycles
          2,865,539      inst_retired.any          #      0.5 IPC
          6,227,603      cpu_clk_unhalted.thread

        2.003403078 seconds time elapsed

 v4:
 ---
 Move affinity setup and read_counter_cpu to a new function
 read_affinity_counters. It's only called when stat_config.summary
 is not set.

 v3:
 ---
 Use evsel->prev_raw_counts for summary counts

 v2:
 ---
 Rebase to perf/core branch

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
---
 tools/perf/builtin-stat.c | 27 ++++++++++++++++++++++++---
 tools/perf/util/stat.c    |  2 +-
 tools/perf/util/stat.h    |  1 +
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f3b3a59ac7d2..d6a6aa6b997d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -314,14 +314,14 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 	return 0;
 }
 
-static void read_counters(struct timespec *rs)
+static int read_affinity_counters(struct timespec *rs)
 {
 	struct evsel *counter;
 	struct affinity affinity;
 	int i, ncpus, cpu;
 
 	if (affinity__setup(&affinity) < 0)
-		return;
+		return -1;
 
 	ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
 	if (!target__has_cpu(&target) || target__has_per_thread(&target))
@@ -341,6 +341,15 @@ static void read_counters(struct timespec *rs)
 		}
 	}
 	affinity__cleanup(&affinity);
+	return 0;
+}
+
+static void read_counters(struct timespec *rs)
+{
+	struct evsel *counter;
+
+	if (!stat_config.summary && (read_affinity_counters(rs) < 0))
+		return;
 
 	evlist__for_each_entry(evsel_list, counter) {
 		if (counter->err)
@@ -394,6 +403,7 @@ static void runtime_stat_reset(struct perf_stat_config *config)
 static void process_interval(void)
 {
 	struct timespec ts, rs;
+	struct stats walltime_nsecs_stats_bak;
 
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
@@ -407,9 +417,11 @@ static void process_interval(void)
 			pr_err("failed to write stat round event\n");
 	}
 
+	walltime_nsecs_stats_bak = walltime_nsecs_stats;
 	init_stats(&walltime_nsecs_stats);
 	update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000);
 	print_counters(&rs, 0, NULL);
+	walltime_nsecs_stats = walltime_nsecs_stats_bak;
 }
 
 static void enable_counters(void)
@@ -765,6 +777,15 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
+	if (interval) {
+		stat_config.interval = 0;
+		stat_config.summary = true;
+		perf_evlist__copy_prev_raw_counts(evsel_list);
+		perf_evlist__reset_prev_raw_counts(evsel_list);
+		runtime_stat_reset(&stat_config);
+		perf_stat__reset_shadow_per_stat(&rt_stat);
+	}
+
 	/*
 	 * Closing a group leader splits the group, and as we only disable
 	 * group leaders, results in remaining events becoming enabled. To
@@ -2159,7 +2180,7 @@ int cmd_stat(int argc, const char **argv)
 		}
 	}
 
-	if (!forever && status != -1 && !interval)
+	if (!forever && status != -1 && (!interval || stat_config.summary))
 		print_counters(NULL, argc, argv);
 
 	if (STAT_RECORD) {
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index aadc723ce871..49e832a9c109 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -388,7 +388,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	 * interval mode, otherwise overall avg running
 	 * averages will be shown for each interval.
 	 */
-	if (config->interval) {
+	if (config->interval || config->summary) {
 		for (i = 0; i < 3; i++)
 			init_stats(&ps->res_stats[i]);
 	}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 62cf72c71869..c60e9e5d6474 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -110,6 +110,7 @@ struct perf_stat_config {
 	bool			 all_kernel;
 	bool			 all_user;
 	bool			 percore_show_thread;
+	bool			 summary;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-- 
2.17.1