linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: lkml <linux-kernel@vger.kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Michael Petlan <mpetlan@redhat.com>,
	Ian Rogers <irogers@google.com>,
	Stephane Eranian <eranian@google.com>,
	Andi Kleen <ak@linux.intel.com>
Subject: [PATCH 14/14] perf tests: Add parse metric test for frontend metric
Date: Mon, 25 May 2020 00:42:19 +0200	[thread overview]
Message-ID: <20200524224219.234847-15-jolsa@kernel.org> (raw)
In-Reply-To: <20200524224219.234847-1-jolsa@kernel.org>

Adding new metri test for frontend metric. It's stolen
from x86 pmu events.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/tests/parse-metric.c | 46 +++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index 3005d27c5c48..38f20850bba3 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -15,6 +15,11 @@ static struct pmu_event pme_test[] = {
 	.metric_expr	= "inst_retired.any / cpu_clk_unhalted.thread",
 	.metric_name	= "IPC",
 },
+{
+	.metric_expr	= "idq_uops_not_delivered.core / (4 * (( ( cpu_clk_unhalted.thread / 2 ) * "
+			  "( 1 + cpu_clk_unhalted.one_thread_active / cpu_clk_unhalted.ref_xclk ) )))",
+	.metric_name	= "Frontend_Bound_SMT",
+},
 };
 
 static struct pmu_events_map map = {
@@ -110,8 +115,49 @@ static int test_ipc(void)
 	return 0;
 }
 
+static int test_frontend(void)
+{
+	double ratio;
+	struct rblist metric_events = { 0 };
+	struct evlist *evlist;
+	struct evsel *evsel;
+	struct value vals[] = {
+		{ .event = "idq_uops_not_delivered.core",        .val = 300 },
+		{ .event = "cpu_clk_unhalted.thread",            .val = 200 },
+		{ .event = "cpu_clk_unhalted.one_thread_active", .val = 400 },
+		{ .event = "cpu_clk_unhalted.ref_xclk",          .val = 600 },
+		{ 0 },
+	};
+	struct runtime_stat st;
+	int err;
+
+	evlist = evlist__new();
+	if (!evlist)
+		return -1;
+
+	err = metricgroup__parse_groups_test(evlist, &map,
+					     "Frontend_Bound_SMT",
+					     false, false,
+					     &metric_events);
+
+	TEST_ASSERT_VAL("failed to parse metrics", err == 0);
+
+	runtime_stat__init(&st);
+	load_runtime_stat(&st, evlist, vals);
+
+	evsel = evlist__first(evlist);
+	ratio = compute_single(&metric_events, evsel, &st);
+
+	TEST_ASSERT_VAL("Frontend_Bound_SMT failed, wrong ratio", ratio == 0.45);
+
+	runtime_stat__exit(&st);
+	evlist__delete(evlist);
+	return 0;
+}
+
 int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("IPC failed", test_ipc() == 0);
+	TEST_ASSERT_VAL("frontend failed", test_frontend() == 0);
 	return 0;
 }
-- 
2.25.4


  parent reply	other threads:[~2020-05-24 22:43 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-24 22:42 [RFC 00/14] perf tests: Check on subtest for user specified test Jiri Olsa
2020-05-24 22:42 ` [PATCH 01/14] " Jiri Olsa
2020-05-24 22:42 ` [PATCH 02/14] perf tools: Do not pass avg to generic_metric Jiri Olsa
2020-05-24 22:42 ` [PATCH 03/14] perf tools: Add struct parse_events_state pointer to scanner Jiri Olsa
2020-05-24 22:42 ` [PATCH 04/14] perf tools: Add fake pmu support Jiri Olsa
2020-06-01  7:22   ` Ian Rogers
2020-06-01  9:06     ` Jiri Olsa
2020-05-24 22:42 ` [PATCH 05/14] perf tools: Add parse_events_fake interface Jiri Olsa
2020-06-01  7:28   ` Ian Rogers
2020-06-01  9:08     ` Jiri Olsa
2020-06-01 15:04       ` Arnaldo Carvalho de Melo
2020-06-01 15:49         ` Jiri Olsa
2020-05-24 22:42 ` [PATCH 06/14] perf tests: Add another pmu-events tests Jiri Olsa
2020-06-01  7:44   ` Ian Rogers
2020-06-01 13:21     ` Jiri Olsa
2020-06-01 16:23       ` Ian Rogers
2020-05-24 22:42 ` [PATCH 07/14] perf tools: Factor out parse_groups function Jiri Olsa
2020-05-24 22:42 ` [PATCH 08/14] perf tools: Add metricgroup__parse_groups_test function Jiri Olsa
2020-05-24 22:42 ` [PATCH 09/14] perf tools: Add fake_pmu to parse_events function Jiri Olsa
2020-05-24 22:42 ` [PATCH 10/14] perf tools: Add map " Jiri Olsa
2020-05-24 22:42 ` [PATCH 11/14] perf tools: Factor out prepare_metric function Jiri Olsa
2020-05-24 22:42 ` [PATCH 12/14] perf tools: Add test_generic_metric function Jiri Olsa
2020-05-24 22:42 ` [PATCH 13/14] perf tests: Add parse metric test for ipc metric Jiri Olsa
2020-06-01  7:55   ` Ian Rogers
2020-06-01 13:09     ` Jiri Olsa
2020-06-01 16:12       ` Ian Rogers
2020-06-01 15:08     ` Arnaldo Carvalho de Melo
2020-06-01 15:49       ` Jiri Olsa
2020-05-24 22:42 ` Jiri Olsa [this message]
2020-06-01  8:06   ` [PATCH 14/14] perf tests: Add parse metric test for frontend metric Ian Rogers
2020-06-01 15:08     ` Arnaldo Carvalho de Melo
2020-05-25 12:06 ` [RFC 00/14] perf tests: Check on subtest for user specified test Michael Petlan
2020-05-25 12:35   ` Jiri Olsa
2020-05-25 14:23 ` Arnaldo Carvalho de Melo
2020-05-26 11:15   ` Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200524224219.234847-15-jolsa@kernel.org \
    --to=jolsa@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=mpetlan@redhat.com \
    --cc=namhyung@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).