diff mbox series

[i-g-t,2/2] tests/xe_pmu: Add frequency test

Message ID 20250402013912.2981094-3-vinay.belgaumkar@intel.com (mailing list archive)
State New
Headers show
Series Add PMU tests for GT frequency | expand

Commit Message

Vinay Belgaumkar April 2, 2025, 1:39 a.m. UTC 
Add a basic test that uses PMU to read GT actual and requested
frequencies while running a workload.

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
---
 tests/intel/xe_pmu.c | 93 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 93 insertions(+)

Comments

Riana Tauro April 3, 2025, 10:39 a.m. UTC | #1 
Hi Vinay

VF igt patches were merged so this will need a rebase

On 4/2/2025 7:09 AM, Vinay Belgaumkar wrote:
> Add a basic test that uses PMU to read GT actual and requested
> frequencies while running a workload.
> 
> Cc: Lucas De Marchi <lucas.demarchi@intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
> ---
>   tests/intel/xe_pmu.c | 93 ++++++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 93 insertions(+)
> 
> diff --git a/tests/intel/xe_pmu.c b/tests/intel/xe_pmu.c
> index 66edf24ad..43085b4d0 100644
> --- a/tests/intel/xe_pmu.c
> +++ b/tests/intel/xe_pmu.c
> @@ -226,6 +226,95 @@ static void test_gt_c6_idle(int xe, unsigned int gt)
>   	close(pmu_fd);
>   }
>   
> +/**
> + * SUBTEST: gt-frequency
> + * Description: Validate we can collect accurate frequency PMU stats
> + *		while running a workload.
> + */
> +static void test_gt_frequency(int fd, struct drm_xe_engine_class_instance *eci)
> +{
> +	struct xe_cork *cork = NULL;
> +	uint64_t end[2], start[2];
> +	unsigned long config_rq_freq, config_act_freq;
> +	double min[2], max[2];
> +	uint32_t gt = eci->gt_id;
> +	uint32_t orig_min = xe_gt_get_freq(fd, eci->gt_id, "min");
> +	uint32_t orig_max = xe_gt_get_freq(fd, eci->gt_id, "max");
> +	uint32_t vm;
> +	int pmu_fd[2];
> +
> +	config_rq_freq = get_event_config(fd, gt, NULL, "gt-requested-frequency");
> +	pmu_fd[0] = open_group(fd, config_rq_freq, -1);
> +
> +	config_act_freq = get_event_config(fd, gt, NULL, "gt-actual-frequency");
> +	pmu_fd[1] = open_group(fd, config_act_freq, pmu_fd[0]);
> +
> +	vm = xe_vm_create(fd, 0, 0);
> +
> +	cork = xe_cork_create_opts(fd, eci, vm, 1, 1);
> +	xe_cork_sync_start(fd, cork);
> +
> +	/*
> +	 * Set GPU to min frequency and read PMU counters.
> +	 */
> +	igt_assert(xe_gt_set_freq(fd, gt, "max", orig_min) > 0);
> +	igt_assert(xe_gt_get_freq(fd, gt, "max") == orig_min);
> +
> +	pmu_read_multi(pmu_fd[0], 2, start);
> +	usleep(SLEEP_DURATION * USEC_PER_SEC);
> +	pmu_read_multi(pmu_fd[0], 2, end);
> +
> +	min[0] = (end[0] - start[0]);
> +	min[1] = (end[1] - start[1]);
> +
> +	/*
> +	 * Set GPU to max frequency and read PMU counters.
> +	 */
> +	igt_assert(xe_gt_set_freq(fd, gt, "max", orig_max) > 0);
> +	igt_assert(xe_gt_get_freq(fd, gt, "max") == orig_max);
> +	igt_assert(xe_gt_set_freq(fd, gt, "min", orig_max) > 0);
> +	igt_assert(xe_gt_get_freq(fd, gt, "min") == orig_max);
Should a exit handler be added to restore frequencies in case of assert 
failure?> +
> +	pmu_read_multi(pmu_fd[0], 2, start);
> +	usleep(SLEEP_DURATION * USEC_PER_SEC);
> +	pmu_read_multi(pmu_fd[0], 2, end);
> +
> +	max[0] = (end[0] - start[0]);
> +	max[1] = (end[1] - start[1]);
> +
> +	if (!cork->ended)This can be removed. The engine activity had a trailing idle case which
ended the cork before. The lib already has this check> +	 
xe_cork_sync_end(fd, cork);
> +
> +	/*
> +	 * Restore min/max.
> +	 */
> +	igt_assert(xe_gt_set_freq(fd, gt, "min", orig_min) > 0);
> +	igt_assert(xe_gt_get_freq(fd, gt, "min") == orig_min);
> +
> +	igt_info("Minimum frequency: requested %.1f, actual %.1f\n",
> +		 min[0], min[1]);
> +	igt_info("Maximum frequency: requested %.1f, actual %.1f\n",
> +		 max[0], max[1]);
> +
> +	close(pmu_fd[0]);
> +	close(pmu_fd[1]);
> +
> +	if (cork)
> +		xe_cork_destroy(fd, cork);
> +
> +	xe_vm_destroy(fd, vm);
> +
> +	close(pmu_fd[0]);
> +	close(pmu_fd[1]);
> +
> +	assert_within_epsilon(min[0], orig_min, tolerance);
> +	/*
> +	 * On thermally throttled devices we cannot be sure maximum frequency
> +	 * can be reached so use larger tolerance downwards.
> +	 */
> +	assert_within_epsilon_up_down(max[0], orig_max, tolerance, 0.15f);
> +}
> +
>   igt_main
>   {
>   	int fd, gt;
> @@ -254,6 +343,10 @@ igt_main
>   	test_each_engine("engine-activity-load", fd, eci)
>   		engine_activity(fd, eci, TEST_LOAD);
>   
> +	igt_describe("Validate PMU GT freq measured is within the tolerance");Can't we have this per-gt instead of engine?

Thanks
Riana> +	test_each_engine("gt-frequency", fd, eci)
> +		test_gt_frequency(fd, eci);
> +
>   	igt_fixture {
>   		close(fd);
>   	}
diff mbox series

Patch

diff --git a/tests/intel/xe_pmu.c b/tests/intel/xe_pmu.c
index 66edf24ad..43085b4d0 100644
--- a/tests/intel/xe_pmu.c
+++ b/tests/intel/xe_pmu.c
@@ -226,6 +226,95 @@  static void test_gt_c6_idle(int xe, unsigned int gt)
 	close(pmu_fd);
 }
 
+/**
+ * SUBTEST: gt-frequency
+ * Description: Validate we can collect accurate frequency PMU stats
+ *		while running a workload.
+ */
+static void test_gt_frequency(int fd, struct drm_xe_engine_class_instance *eci)
+{
+	struct xe_cork *cork = NULL;
+	uint64_t end[2], start[2];
+	unsigned long config_rq_freq, config_act_freq;
+	double min[2], max[2];
+	uint32_t gt = eci->gt_id;
+	uint32_t orig_min = xe_gt_get_freq(fd, eci->gt_id, "min");
+	uint32_t orig_max = xe_gt_get_freq(fd, eci->gt_id, "max");
+	uint32_t vm;
+	int pmu_fd[2];
+
+	config_rq_freq = get_event_config(fd, gt, NULL, "gt-requested-frequency");
+	pmu_fd[0] = open_group(fd, config_rq_freq, -1);
+
+	config_act_freq = get_event_config(fd, gt, NULL, "gt-actual-frequency");
+	pmu_fd[1] = open_group(fd, config_act_freq, pmu_fd[0]);
+
+	vm = xe_vm_create(fd, 0, 0);
+
+	cork = xe_cork_create_opts(fd, eci, vm, 1, 1);
+	xe_cork_sync_start(fd, cork);
+
+	/*
+	 * Set GPU to min frequency and read PMU counters.
+	 */
+	igt_assert(xe_gt_set_freq(fd, gt, "max", orig_min) > 0);
+	igt_assert(xe_gt_get_freq(fd, gt, "max") == orig_min);
+
+	pmu_read_multi(pmu_fd[0], 2, start);
+	usleep(SLEEP_DURATION * USEC_PER_SEC);
+	pmu_read_multi(pmu_fd[0], 2, end);
+
+	min[0] = (end[0] - start[0]);
+	min[1] = (end[1] - start[1]);
+
+	/*
+	 * Set GPU to max frequency and read PMU counters.
+	 */
+	igt_assert(xe_gt_set_freq(fd, gt, "max", orig_max) > 0);
+	igt_assert(xe_gt_get_freq(fd, gt, "max") == orig_max);
+	igt_assert(xe_gt_set_freq(fd, gt, "min", orig_max) > 0);
+	igt_assert(xe_gt_get_freq(fd, gt, "min") == orig_max);
+
+	pmu_read_multi(pmu_fd[0], 2, start);
+	usleep(SLEEP_DURATION * USEC_PER_SEC);
+	pmu_read_multi(pmu_fd[0], 2, end);
+
+	max[0] = (end[0] - start[0]);
+	max[1] = (end[1] - start[1]);
+
+	if (!cork->ended)
+		xe_cork_sync_end(fd, cork);
+
+	/*
+	 * Restore min/max.
+	 */
+	igt_assert(xe_gt_set_freq(fd, gt, "min", orig_min) > 0);
+	igt_assert(xe_gt_get_freq(fd, gt, "min") == orig_min);
+
+	igt_info("Minimum frequency: requested %.1f, actual %.1f\n",
+		 min[0], min[1]);
+	igt_info("Maximum frequency: requested %.1f, actual %.1f\n",
+		 max[0], max[1]);
+
+	close(pmu_fd[0]);
+	close(pmu_fd[1]);
+
+	if (cork)
+		xe_cork_destroy(fd, cork);
+
+	xe_vm_destroy(fd, vm);
+
+	close(pmu_fd[0]);
+	close(pmu_fd[1]);
+
+	assert_within_epsilon(min[0], orig_min, tolerance);
+	/*
+	 * On thermally throttled devices we cannot be sure maximum frequency
+	 * can be reached so use larger tolerance downwards.
+	 */
+	assert_within_epsilon_up_down(max[0], orig_max, tolerance, 0.15f);
+}
+
 igt_main
 {
 	int fd, gt;
@@ -254,6 +343,10 @@  igt_main
 	test_each_engine("engine-activity-load", fd, eci)
 		engine_activity(fd, eci, TEST_LOAD);
 
+	igt_describe("Validate PMU GT freq measured is within the tolerance");
+	test_each_engine("gt-frequency", fd, eci)
+		test_gt_frequency(fd, eci);
+
 	igt_fixture {
 		close(fd);
 	}