[RFC PATCH v8 5/7] perf stat: Add retire latency print functions to print out at the very end of print out

weilin.wang@intel.com posted 7 patches 1 year, 9 months ago
There is a newer version of this series
[RFC PATCH v8 5/7] perf stat: Add retire latency print functions to print out at the very end of print out
Posted by weilin.wang@intel.com 1 year, 9 months ago
From: Weilin Wang <weilin.wang@intel.com>

Add print out functions so that users could read retire latency values.

Example output:

 Performance counter stats for 'system wide':

            25,717      MEM_INST_RETIRED.SPLIT_STORES    #      2.2 %  tma_split_stores
        28,365,080      CPU_CLK_UNHALTED.THREAD
             24.00      MEM_INST_RETIRED.SPLIT_STORES:R  #       96        4

       2.054365083 seconds time elapsed

This output of retire latency data is in format:
 <val> <event-name:R> # <sum> <count>.

Signed-off-by: Weilin Wang <weilin.wang@intel.com>
Reviewed-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/stat-display.c | 69 ++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index bfc1d705f437..b9c3978cc99c 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -21,6 +21,7 @@
 #include "iostat.h"
 #include "pmu.h"
 #include "pmus.h"
+#include "intel-tpebs.h"
 
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
@@ -34,6 +35,7 @@
 #define COMM_LEN     16
 #define PID_LEN       7
 #define CPUS_LEN      4
+#define RETIRE_LEN    8
 
 static int aggr_header_lens[] = {
 	[AGGR_CORE] 	= 18,
@@ -426,6 +428,71 @@ static void print_metric_std(struct perf_stat_config *config,
 	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
 }
 
+static void print_retire_lat_std(struct perf_stat_config *config,
+				 struct outstate *os)
+{
+	FILE *out = os->fh;
+	bool newline = os->newline;
+	struct tpebs_retire_lat *t;
+	struct list_head *retire_lats = &config->tpebs_results;
+
+	list_for_each_entry(t, retire_lats, nd) {
+		if (newline)
+			do_new_line_std(config, os);
+		fprintf(out, "%'*.2f ", COUNTS_LEN, t->val);
+		/* For print alignment */
+		fprintf(out, "%-*s ", config->unit_width, "");
+		fprintf(out, "%-*s", EVNAME_LEN, t->tpebs_name);
+		fprintf(out, " # ");
+		fprintf(out, "%*d %*ld\n", RETIRE_LEN, t->sum,
+			 RETIRE_LEN, t->count);
+	}
+}
+
+static void print_retire_lat_csv(struct perf_stat_config *config,
+				 struct outstate *os)
+{
+	FILE *out = os->fh;
+	struct tpebs_retire_lat *t;
+	struct list_head *retire_lats = &config->tpebs_results;
+	const char *sep = config->csv_sep;
+
+	list_for_each_entry(t, retire_lats, nd) {
+		fprintf(out, "%f%s%s%s%s%ld%s%d\n", t->val, sep, sep, t->tpebs_name, sep,
+			t->count, sep, t->sum);
+	}
+}
+
+static void print_retire_lat_json(struct perf_stat_config *config,
+				  struct outstate *os)
+{
+	FILE *out = os->fh;
+	struct tpebs_retire_lat *t;
+	struct list_head *retire_lats = &config->tpebs_results;
+
+	fprintf(out, "{");
+	list_for_each_entry(t, retire_lats, nd) {
+		fprintf(out, "\"retire_latency-value\" : \"%f\", ", t->val);
+		fprintf(out, "\"name\" : \"%s\"", t->tpebs_name);
+		fprintf(out, "\"sample-counts\" : \"%ld\"", t->count);
+		fprintf(out, "\"retire_latency-sum\" : \"%d\"", t->sum);
+	}
+	fprintf(out, "}");
+}
+
+static void print_retire_lat(struct perf_stat_config *config,
+			     struct outstate *os)
+{
+	if (!&config->tpebs_results)
+		return;
+	if (config->json_output)
+		print_retire_lat_json(config, os);
+	else if (config->csv_output)
+		print_retire_lat_csv(config, os);
+	else
+		print_retire_lat_std(config, os);
+}
+
 static void new_line_csv(struct perf_stat_config *config, void *ctx)
 {
 	struct outstate *os = ctx;
@@ -1609,6 +1676,8 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf
 		break;
 	}
 
+	print_retire_lat(config, &os);
+
 	print_footer(config);
 
 	fflush(config->output);
-- 
2.43.0
Re: [RFC PATCH v8 5/7] perf stat: Add retire latency print functions to print out at the very end of print out
Posted by Ian Rogers 1 year, 9 months ago
On Tue, May 14, 2024 at 10:44 PM <weilin.wang@intel.com> wrote:
>
> From: Weilin Wang <weilin.wang@intel.com>
>
> Add print out functions so that users could read retire latency values.
>
> Example output:
>
>  Performance counter stats for 'system wide':
>
>             25,717      MEM_INST_RETIRED.SPLIT_STORES    #      2.2 %  tma_split_stores
>         28,365,080      CPU_CLK_UNHALTED.THREAD
>              24.00      MEM_INST_RETIRED.SPLIT_STORES:R  #       96        4
>
>        2.054365083 seconds time elapsed
>
> This output of retire latency data is in format:
>  <val> <event-name:R> # <sum> <count>.
>
> Signed-off-by: Weilin Wang <weilin.wang@intel.com>
> Reviewed-by: Ian Rogers <irogers@google.com>

My usual complaint that I hate the stat-display spaghetti code. We
keep putting more spaghetti on the plate and this change does this
too. In the evsel approach:
https://lore.kernel.org/lkml/20240428053616.1125891-1-irogers@google.com/
retirement latency events just update the counts for the event and so
we don't need to special case tpebs events like this. I'd prefer we
went that route. My reviewed-by no longer stands.

Thanks,
Ian

> ---
>  tools/perf/util/stat-display.c | 69 ++++++++++++++++++++++++++++++++++
>  1 file changed, 69 insertions(+)
>
> diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
> index bfc1d705f437..b9c3978cc99c 100644
> --- a/tools/perf/util/stat-display.c
> +++ b/tools/perf/util/stat-display.c
> @@ -21,6 +21,7 @@
>  #include "iostat.h"
>  #include "pmu.h"
>  #include "pmus.h"
> +#include "intel-tpebs.h"
>
>  #define CNTR_NOT_SUPPORTED     "<not supported>"
>  #define CNTR_NOT_COUNTED       "<not counted>"
> @@ -34,6 +35,7 @@
>  #define COMM_LEN     16
>  #define PID_LEN       7
>  #define CPUS_LEN      4
> +#define RETIRE_LEN    8
>
>  static int aggr_header_lens[] = {
>         [AGGR_CORE]     = 18,
> @@ -426,6 +428,71 @@ static void print_metric_std(struct perf_stat_config *config,
>         fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
>  }
>
> +static void print_retire_lat_std(struct perf_stat_config *config,
> +                                struct outstate *os)
> +{
> +       FILE *out = os->fh;
> +       bool newline = os->newline;
> +       struct tpebs_retire_lat *t;
> +       struct list_head *retire_lats = &config->tpebs_results;
> +
> +       list_for_each_entry(t, retire_lats, nd) {
> +               if (newline)
> +                       do_new_line_std(config, os);
> +               fprintf(out, "%'*.2f ", COUNTS_LEN, t->val);
> +               /* For print alignment */
> +               fprintf(out, "%-*s ", config->unit_width, "");
> +               fprintf(out, "%-*s", EVNAME_LEN, t->tpebs_name);
> +               fprintf(out, " # ");
> +               fprintf(out, "%*d %*ld\n", RETIRE_LEN, t->sum,
> +                        RETIRE_LEN, t->count);
> +       }
> +}
> +
> +static void print_retire_lat_csv(struct perf_stat_config *config,
> +                                struct outstate *os)
> +{
> +       FILE *out = os->fh;
> +       struct tpebs_retire_lat *t;
> +       struct list_head *retire_lats = &config->tpebs_results;
> +       const char *sep = config->csv_sep;
> +
> +       list_for_each_entry(t, retire_lats, nd) {
> +               fprintf(out, "%f%s%s%s%s%ld%s%d\n", t->val, sep, sep, t->tpebs_name, sep,
> +                       t->count, sep, t->sum);
> +       }
> +}
> +
> +static void print_retire_lat_json(struct perf_stat_config *config,
> +                                 struct outstate *os)
> +{
> +       FILE *out = os->fh;
> +       struct tpebs_retire_lat *t;
> +       struct list_head *retire_lats = &config->tpebs_results;
> +
> +       fprintf(out, "{");
> +       list_for_each_entry(t, retire_lats, nd) {
> +               fprintf(out, "\"retire_latency-value\" : \"%f\", ", t->val);
> +               fprintf(out, "\"name\" : \"%s\"", t->tpebs_name);
> +               fprintf(out, "\"sample-counts\" : \"%ld\"", t->count);
> +               fprintf(out, "\"retire_latency-sum\" : \"%d\"", t->sum);
> +       }
> +       fprintf(out, "}");
> +}
> +
> +static void print_retire_lat(struct perf_stat_config *config,
> +                            struct outstate *os)
> +{
> +       if (!&config->tpebs_results)
> +               return;
> +       if (config->json_output)
> +               print_retire_lat_json(config, os);
> +       else if (config->csv_output)
> +               print_retire_lat_csv(config, os);
> +       else
> +               print_retire_lat_std(config, os);
> +}
> +
>  static void new_line_csv(struct perf_stat_config *config, void *ctx)
>  {
>         struct outstate *os = ctx;
> @@ -1609,6 +1676,8 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf
>                 break;
>         }
>
> +       print_retire_lat(config, &os);
> +
>         print_footer(config);
>
>         fflush(config->output);
> --
> 2.43.0
>
RE: [RFC PATCH v8 5/7] perf stat: Add retire latency print functions to print out at the very end of print out
Posted by Wang, Weilin 1 year, 9 months ago

> -----Original Message-----
> From: Ian Rogers <irogers@google.com>
> Sent: Thursday, May 16, 2024 9:47 AM
> To: Wang, Weilin <weilin.wang@intel.com>
> Cc: Namhyung Kim <namhyung@kernel.org>; Arnaldo Carvalho de Melo
> <acme@kernel.org>; Peter Zijlstra <peterz@infradead.org>; Ingo Molnar
> <mingo@redhat.com>; Alexander Shishkin
> <alexander.shishkin@linux.intel.com>; Jiri Olsa <jolsa@kernel.org>; Hunter,
> Adrian <adrian.hunter@intel.com>; Kan Liang <kan.liang@linux.intel.com>;
> linux-perf-users@vger.kernel.org; linux-kernel@vger.kernel.org; Taylor, Perry
> <perry.taylor@intel.com>; Alt, Samantha <samantha.alt@intel.com>; Biggers,
> Caleb <caleb.biggers@intel.com>
> Subject: Re: [RFC PATCH v8 5/7] perf stat: Add retire latency print functions to
> print out at the very end of print out
> 
> On Tue, May 14, 2024 at 10:44 PM <weilin.wang@intel.com> wrote:
> >
> > From: Weilin Wang <weilin.wang@intel.com>
> >
> > Add print out functions so that users could read retire latency values.
> >
> > Example output:
> >
> >  Performance counter stats for 'system wide':
> >
> >             25,717      MEM_INST_RETIRED.SPLIT_STORES    #      2.2 %
> tma_split_stores
> >         28,365,080      CPU_CLK_UNHALTED.THREAD
> >              24.00      MEM_INST_RETIRED.SPLIT_STORES:R  #       96        4
> >
> >        2.054365083 seconds time elapsed
> >
> > This output of retire latency data is in format:
> >  <val> <event-name:R> # <sum> <count>.
> >
> > Signed-off-by: Weilin Wang <weilin.wang@intel.com>
> > Reviewed-by: Ian Rogers <irogers@google.com>
> 
> My usual complaint that I hate the stat-display spaghetti code. We
> keep putting more spaghetti on the plate and this change does this
> too. In the evsel approach:
> https://lore.kernel.org/lkml/20240428053616.1125891-1-
> irogers@google.com/
> retirement latency events just update the counts for the event and so
> we don't need to special case tpebs events like this. I'd prefer we
> went that route. My reviewed-by no longer stands.
>
Based on the current stat-display code and the original TPEBS counting 
code, I believe the code in this commit and last commit was the best way to
do the metric calculation and printout. 

But I totally agree with you that if we could get evsel with retire latency work,
this code is not necessary.

I was thinking to plugin the retire latency value into evsel so that I could delete 
this and last commit. Do you think that would be a solution?

Thanks,
Weilin

> Thanks,
> Ian
> 
> > ---
> >  tools/perf/util/stat-display.c | 69
> ++++++++++++++++++++++++++++++++++
> >  1 file changed, 69 insertions(+)
> >
> > diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
> > index bfc1d705f437..b9c3978cc99c 100644
> > --- a/tools/perf/util/stat-display.c
> > +++ b/tools/perf/util/stat-display.c
> > @@ -21,6 +21,7 @@
> >  #include "iostat.h"
> >  #include "pmu.h"
> >  #include "pmus.h"
> > +#include "intel-tpebs.h"
> >
> >  #define CNTR_NOT_SUPPORTED     "<not supported>"
> >  #define CNTR_NOT_COUNTED       "<not counted>"
> > @@ -34,6 +35,7 @@
> >  #define COMM_LEN     16
> >  #define PID_LEN       7
> >  #define CPUS_LEN      4
> > +#define RETIRE_LEN    8
> >
> >  static int aggr_header_lens[] = {
> >         [AGGR_CORE]     = 18,
> > @@ -426,6 +428,71 @@ static void print_metric_std(struct
> perf_stat_config *config,
> >         fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
> >  }
> >
> > +static void print_retire_lat_std(struct perf_stat_config *config,
> > +                                struct outstate *os)
> > +{
> > +       FILE *out = os->fh;
> > +       bool newline = os->newline;
> > +       struct tpebs_retire_lat *t;
> > +       struct list_head *retire_lats = &config->tpebs_results;
> > +
> > +       list_for_each_entry(t, retire_lats, nd) {
> > +               if (newline)
> > +                       do_new_line_std(config, os);
> > +               fprintf(out, "%'*.2f ", COUNTS_LEN, t->val);
> > +               /* For print alignment */
> > +               fprintf(out, "%-*s ", config->unit_width, "");
> > +               fprintf(out, "%-*s", EVNAME_LEN, t->tpebs_name);
> > +               fprintf(out, " # ");
> > +               fprintf(out, "%*d %*ld\n", RETIRE_LEN, t->sum,
> > +                        RETIRE_LEN, t->count);
> > +       }
> > +}
> > +
> > +static void print_retire_lat_csv(struct perf_stat_config *config,
> > +                                struct outstate *os)
> > +{
> > +       FILE *out = os->fh;
> > +       struct tpebs_retire_lat *t;
> > +       struct list_head *retire_lats = &config->tpebs_results;
> > +       const char *sep = config->csv_sep;
> > +
> > +       list_for_each_entry(t, retire_lats, nd) {
> > +               fprintf(out, "%f%s%s%s%s%ld%s%d\n", t->val, sep, sep, t-
> >tpebs_name, sep,
> > +                       t->count, sep, t->sum);
> > +       }
> > +}
> > +
> > +static void print_retire_lat_json(struct perf_stat_config *config,
> > +                                 struct outstate *os)
> > +{
> > +       FILE *out = os->fh;
> > +       struct tpebs_retire_lat *t;
> > +       struct list_head *retire_lats = &config->tpebs_results;
> > +
> > +       fprintf(out, "{");
> > +       list_for_each_entry(t, retire_lats, nd) {
> > +               fprintf(out, "\"retire_latency-value\" : \"%f\", ", t->val);
> > +               fprintf(out, "\"name\" : \"%s\"", t->tpebs_name);
> > +               fprintf(out, "\"sample-counts\" : \"%ld\"", t->count);
> > +               fprintf(out, "\"retire_latency-sum\" : \"%d\"", t->sum);
> > +       }
> > +       fprintf(out, "}");
> > +}
> > +
> > +static void print_retire_lat(struct perf_stat_config *config,
> > +                            struct outstate *os)
> > +{
> > +       if (!&config->tpebs_results)
> > +               return;
> > +       if (config->json_output)
> > +               print_retire_lat_json(config, os);
> > +       else if (config->csv_output)
> > +               print_retire_lat_csv(config, os);
> > +       else
> > +               print_retire_lat_std(config, os);
> > +}
> > +
> >  static void new_line_csv(struct perf_stat_config *config, void *ctx)
> >  {
> >         struct outstate *os = ctx;
> > @@ -1609,6 +1676,8 @@ void evlist__print_counters(struct evlist *evlist,
> struct perf_stat_config *conf
> >                 break;
> >         }
> >
> > +       print_retire_lat(config, &os);
> > +
> >         print_footer(config);
> >
> >         fflush(config->output);
> > --
> > 2.43.0
> >
Re: [RFC PATCH v8 5/7] perf stat: Add retire latency print functions to print out at the very end of print out
Posted by Ian Rogers 1 year, 9 months ago
On Thu, May 16, 2024 at 10:52 AM Wang, Weilin <weilin.wang@intel.com> wrote:
>
>
>
> > -----Original Message-----
> > From: Ian Rogers <irogers@google.com>
> > Sent: Thursday, May 16, 2024 9:47 AM
> > To: Wang, Weilin <weilin.wang@intel.com>
> > Cc: Namhyung Kim <namhyung@kernel.org>; Arnaldo Carvalho de Melo
> > <acme@kernel.org>; Peter Zijlstra <peterz@infradead.org>; Ingo Molnar
> > <mingo@redhat.com>; Alexander Shishkin
> > <alexander.shishkin@linux.intel.com>; Jiri Olsa <jolsa@kernel.org>; Hunter,
> > Adrian <adrian.hunter@intel.com>; Kan Liang <kan.liang@linux.intel.com>;
> > linux-perf-users@vger.kernel.org; linux-kernel@vger.kernel.org; Taylor, Perry
> > <perry.taylor@intel.com>; Alt, Samantha <samantha.alt@intel.com>; Biggers,
> > Caleb <caleb.biggers@intel.com>
> > Subject: Re: [RFC PATCH v8 5/7] perf stat: Add retire latency print functions to
> > print out at the very end of print out
> >
> > On Tue, May 14, 2024 at 10:44 PM <weilin.wang@intel.com> wrote:
> > >
> > > From: Weilin Wang <weilin.wang@intel.com>
> > >
> > > Add print out functions so that users could read retire latency values.
> > >
> > > Example output:
> > >
> > >  Performance counter stats for 'system wide':
> > >
> > >             25,717      MEM_INST_RETIRED.SPLIT_STORES    #      2.2 %
> > tma_split_stores
> > >         28,365,080      CPU_CLK_UNHALTED.THREAD
> > >              24.00      MEM_INST_RETIRED.SPLIT_STORES:R  #       96        4
> > >
> > >        2.054365083 seconds time elapsed
> > >
> > > This output of retire latency data is in format:
> > >  <val> <event-name:R> # <sum> <count>.
> > >
> > > Signed-off-by: Weilin Wang <weilin.wang@intel.com>
> > > Reviewed-by: Ian Rogers <irogers@google.com>
> >
> > My usual complaint that I hate the stat-display spaghetti code. We
> > keep putting more spaghetti on the plate and this change does this
> > too. In the evsel approach:
> > https://lore.kernel.org/lkml/20240428053616.1125891-1-
> > irogers@google.com/
> > retirement latency events just update the counts for the event and so
> > we don't need to special case tpebs events like this. I'd prefer we
> > went that route. My reviewed-by no longer stands.
> >
> Based on the current stat-display code and the original TPEBS counting
> code, I believe the code in this commit and last commit was the best way to
> do the metric calculation and printout.
>
> But I totally agree with you that if we could get evsel with retire latency work,
> this code is not necessary.
>
> I was thinking to plugin the retire latency value into evsel so that I could delete
> this and last commit. Do you think that would be a solution?

Yep, I think that'd be good.

Thanks,
Ian

> Thanks,
> Weilin
>
> > Thanks,
> > Ian
> >
> > > ---
> > >  tools/perf/util/stat-display.c | 69
> > ++++++++++++++++++++++++++++++++++
> > >  1 file changed, 69 insertions(+)
> > >
> > > diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
> > > index bfc1d705f437..b9c3978cc99c 100644
> > > --- a/tools/perf/util/stat-display.c
> > > +++ b/tools/perf/util/stat-display.c
> > > @@ -21,6 +21,7 @@
> > >  #include "iostat.h"
> > >  #include "pmu.h"
> > >  #include "pmus.h"
> > > +#include "intel-tpebs.h"
> > >
> > >  #define CNTR_NOT_SUPPORTED     "<not supported>"
> > >  #define CNTR_NOT_COUNTED       "<not counted>"
> > > @@ -34,6 +35,7 @@
> > >  #define COMM_LEN     16
> > >  #define PID_LEN       7
> > >  #define CPUS_LEN      4
> > > +#define RETIRE_LEN    8
> > >
> > >  static int aggr_header_lens[] = {
> > >         [AGGR_CORE]     = 18,
> > > @@ -426,6 +428,71 @@ static void print_metric_std(struct
> > perf_stat_config *config,
> > >         fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
> > >  }
> > >
> > > +static void print_retire_lat_std(struct perf_stat_config *config,
> > > +                                struct outstate *os)
> > > +{
> > > +       FILE *out = os->fh;
> > > +       bool newline = os->newline;
> > > +       struct tpebs_retire_lat *t;
> > > +       struct list_head *retire_lats = &config->tpebs_results;
> > > +
> > > +       list_for_each_entry(t, retire_lats, nd) {
> > > +               if (newline)
> > > +                       do_new_line_std(config, os);
> > > +               fprintf(out, "%'*.2f ", COUNTS_LEN, t->val);
> > > +               /* For print alignment */
> > > +               fprintf(out, "%-*s ", config->unit_width, "");
> > > +               fprintf(out, "%-*s", EVNAME_LEN, t->tpebs_name);
> > > +               fprintf(out, " # ");
> > > +               fprintf(out, "%*d %*ld\n", RETIRE_LEN, t->sum,
> > > +                        RETIRE_LEN, t->count);
> > > +       }
> > > +}
> > > +
> > > +static void print_retire_lat_csv(struct perf_stat_config *config,
> > > +                                struct outstate *os)
> > > +{
> > > +       FILE *out = os->fh;
> > > +       struct tpebs_retire_lat *t;
> > > +       struct list_head *retire_lats = &config->tpebs_results;
> > > +       const char *sep = config->csv_sep;
> > > +
> > > +       list_for_each_entry(t, retire_lats, nd) {
> > > +               fprintf(out, "%f%s%s%s%s%ld%s%d\n", t->val, sep, sep, t-
> > >tpebs_name, sep,
> > > +                       t->count, sep, t->sum);
> > > +       }
> > > +}
> > > +
> > > +static void print_retire_lat_json(struct perf_stat_config *config,
> > > +                                 struct outstate *os)
> > > +{
> > > +       FILE *out = os->fh;
> > > +       struct tpebs_retire_lat *t;
> > > +       struct list_head *retire_lats = &config->tpebs_results;
> > > +
> > > +       fprintf(out, "{");
> > > +       list_for_each_entry(t, retire_lats, nd) {
> > > +               fprintf(out, "\"retire_latency-value\" : \"%f\", ", t->val);
> > > +               fprintf(out, "\"name\" : \"%s\"", t->tpebs_name);
> > > +               fprintf(out, "\"sample-counts\" : \"%ld\"", t->count);
> > > +               fprintf(out, "\"retire_latency-sum\" : \"%d\"", t->sum);
> > > +       }
> > > +       fprintf(out, "}");
> > > +}
> > > +
> > > +static void print_retire_lat(struct perf_stat_config *config,
> > > +                            struct outstate *os)
> > > +{
> > > +       if (!&config->tpebs_results)
> > > +               return;
> > > +       if (config->json_output)
> > > +               print_retire_lat_json(config, os);
> > > +       else if (config->csv_output)
> > > +               print_retire_lat_csv(config, os);
> > > +       else
> > > +               print_retire_lat_std(config, os);
> > > +}
> > > +
> > >  static void new_line_csv(struct perf_stat_config *config, void *ctx)
> > >  {
> > >         struct outstate *os = ctx;
> > > @@ -1609,6 +1676,8 @@ void evlist__print_counters(struct evlist *evlist,
> > struct perf_stat_config *conf
> > >                 break;
> > >         }
> > >
> > > +       print_retire_lat(config, &os);
> > > +
> > >         print_footer(config);
> > >
> > >         fflush(config->output);
> > > --
> > > 2.43.0
> > >