Received-SPF: pass (google.com: domain of linux-kernel+bounces-100935-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: weilin.wang@intel.com
To: weilin.wang@intel.com,
	Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	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>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Kan Liang <kan.liang@linux.intel.com>
Cc: linux-perf-users@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	Perry Taylor <perry.taylor@intel.com>,
	Samantha Alt <samantha.alt@intel.com>,
	Caleb Biggers <caleb.biggers@intel.com>
Subject: [RFC PATCH v4 5/6] perf stat: Add retire latency print functions to print out at the very end of print out
Date: Tue, 12 Mar 2024 19:49:20 -0400
Message-ID: <20240312234921.812685-6-weilin.wang@intel.com>
In-Reply-To: <20240312234921.812685-1-weilin.wang@intel.com>
References: <20240312234921.812685-1-weilin.wang@intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Weilin Wang <weilin.wang@intel.com>

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

Example output:
In this simple example, there is no MEM_INST_RETIRED.STLB_HIT_STORES sample.
Therefore, the MEM_INST_RETIRED.STLB_HIT_STORES:p retire_latency value, count
and sum are all 0.

 Performance counter stats for 'system wide':

       181,047,168      cpu_core/TOPDOWN.SLOTS/          #      0.6 %  tma_dtlb_store
         3,195,608      cpu_core/topdown-retiring/
        40,156,649      cpu_core/topdown-mem-bound/
         3,550,925      cpu_core/topdown-bad-spec/
       117,571,818      cpu_core/topdown-fe-bound/
        57,118,087      cpu_core/topdown-be-bound/
            69,179      cpu_core/EXE_ACTIVITY.BOUND_ON_STORES/
             4,582      cpu_core/MEM_INST_RETIRED.STLB_HIT_STORES/
        30,183,104      cpu_core/CPU_CLK_UNHALTED.DISTRIBUTED/
        30,556,790      cpu_core/CPU_CLK_UNHALTED.THREAD/
           168,486      cpu_core/DTLB_STORE_MISSES.WALK_ACTIVE/
              0.00 MEM_INST_RETIRED.STLB_HIT_STORES:p       0        0

       1.003105924 seconds time elapsed

Signed-off-by: Weilin Wang <weilin.wang@intel.com>
---
 tools/perf/util/stat-display.c | 65 ++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index bfc1d705f437..e2996ba67bfe 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 "metricgroup.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 +428,67 @@ 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 %-*s", COUNTS_LEN, t->val, EVNAME_LEN, t->name);
+		fprintf(out, "%*ld %*d\n", RETIRE_LEN, t->count,
+			 RETIRE_LEN, t->sum);
+	}
+}
+
+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->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, "\"event-name\" : \"%s\"", t->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 +1672,8 @@ 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