Re: [RFC v4 02/16] drm/sched: Add some more scheduling quality unit tests

["Christian König" <christian.koenig@amd.com>]

On 4/25/25 12:20, Tvrtko Ursulin wrote:
> This time round we explore the rate of submitted job queue processing
> with multiple identical parallel clients.
> 
> Example test output:
> 
> 3 clients:
>         t               cycle:     min  avg max : ...
>         +     0ms                   0    0    0 :   0   0   0
>         +   102ms                   2    2    2 :   2   2   2
>         +   208ms                   5    6    6 :   6   5   5
>         +   310ms                   8    9    9 :   9   9   8
> ...
>         +  2616ms                  82   83   83 :  83  83  82
>         +  2717ms                  83   83   83 :  83  83  83
>     avg_max_min_delta(x100)=60
> 
> Every 100ms for the duration of the test test logs how many jobs each
> client had completed, prefixed by minimum, average and maximum numbers.
> When finished overall average delta between max and min is output as a
> rough indicator to scheduling fairness.
> 
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> Cc: Christian König <christian.koenig@amd.com>
> Cc: Danilo Krummrich <dakr@kernel.org>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Philipp Stanner <phasta@kernel.org>
> Cc: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>

Acked-by: Christian König <christian.koenig@amd.com>

> ---
>  .../gpu/drm/scheduler/tests/tests_scheduler.c | 186 +++++++++++++++++-
>  1 file changed, 185 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/scheduler/tests/tests_scheduler.c b/drivers/gpu/drm/scheduler/tests/tests_scheduler.c
> index b66321ef7abe..d70b47d7bf7a 100644
> --- a/drivers/gpu/drm/scheduler/tests/tests_scheduler.c
> +++ b/drivers/gpu/drm/scheduler/tests/tests_scheduler.c
> @@ -181,6 +181,7 @@ struct drm_sched_client_params {
>  
>  struct drm_sched_test_params {
>  	const char *description;
> +	unsigned int num_clients;
>  	struct drm_sched_client_params client[2];
>  };
>  
> @@ -626,6 +627,189 @@ static struct kunit_suite drm_sched_scheduler_two_clients2 = {
>  	.test_cases = drm_sched_scheduler_two_clients_tests,
>  };
>  
> +
> +static const struct drm_sched_test_params drm_sched_many_cases[] = {
> +	{
> +		.description = "2 clients",
> +		.num_clients = 2,
> +		.client[0] = {
> +			.priority = DRM_SCHED_PRIORITY_NORMAL,
> +			.job_cnt = 4,
> +			.job_us = 1000,
> +			.wait_us = 0,
> +			.sync = true,
> +		},
> +	},
> +	{
> +		.description = "3 clients",
> +		.num_clients = 3,
> +		.client[0] = {
> +			.priority = DRM_SCHED_PRIORITY_NORMAL,
> +			.job_cnt = 4,
> +			.job_us = 1000,
> +			.wait_us = 0,
> +			.sync = true,
> +		},
> +	},
> +	{
> +		.description = "7 clients",
> +		.num_clients = 7,
> +		.client[0] = {
> +			.priority = DRM_SCHED_PRIORITY_NORMAL,
> +			.job_cnt = 4,
> +			.job_us = 1000,
> +			.wait_us = 0,
> +			.sync = true,
> +		},
> +	},
> +	{
> +		.description = "13 clients",
> +		.num_clients = 13,
> +		.client[0] = {
> +			.priority = DRM_SCHED_PRIORITY_NORMAL,
> +			.job_cnt = 4,
> +			.job_us = 1000,
> +			.wait_us = 0,
> +			.sync = true,
> +		},
> +	},
> +	{
> +		.description = "31 clients",
> +		.num_clients = 31,
> +		.client[0] = {
> +			.priority = DRM_SCHED_PRIORITY_NORMAL,
> +			.job_cnt = 2,
> +			.job_us = 1000,
> +			.wait_us = 0,
> +			.sync = true,
> +		},
> +	},
> +};
> +
> +KUNIT_ARRAY_PARAM(drm_sched_scheduler_many_clients,
> +		  drm_sched_many_cases,
> +		  drm_sched_desc);
> +
> +static void drm_sched_scheduler_many_clients_test(struct kunit *test)
> +{
> +	const struct drm_sched_test_params *params = test->param_value;
> +	struct drm_mock_scheduler *sched = test->priv;
> +	const unsigned int clients = params->num_clients;
> +	unsigned int i, j, delta_total = 0, loops = 0;
> +	struct test_client *client;
> +	unsigned int *prev_cycle;
> +	ktime_t start;
> +	char *buf;
> +
> +	/*
> +	 * Many clients with deep-ish async queues.
> +	 */
> +
> +	buf = kunit_kmalloc(test, PAGE_SIZE, GFP_KERNEL);
> +	client = kunit_kcalloc(test, clients, sizeof(*client), GFP_KERNEL);
> +	prev_cycle = kunit_kcalloc(test, clients, sizeof(*prev_cycle),
> +				   GFP_KERNEL);
> +
> +	for (i = 0; i < clients; i++)
> +		client[i].entity =
> +			drm_mock_sched_entity_new(test,
> +						  DRM_SCHED_PRIORITY_NORMAL,
> +						  sched);
> +
> +	for (i = 0; i < clients; i++) {
> +		client[i].test = test;
> +		client[i].id = i;
> +		client[i].params = params->client[0];
> +		client[i].duration = ms_to_ktime(1000 / clients);
> +		client[i].cycle_time.min_us = ~0UL;
> +		client[i].latency_time.min_us = ~0UL;
> +		client[i].worker =
> +			kthread_create_worker(0, "%s-%u", __func__, i);
> +		if (IS_ERR(client[i].worker)) {
> +			for (j = 0; j < i; j++)
> +				kthread_destroy_worker(client[j].worker);
> +			KUNIT_FAIL(test, "Failed to create worker!\n");
> +		}
> +
> +		kthread_init_work(&client[i].work, drm_sched_client_work);
> +	}
> +
> +	for (i = 0; i < clients; i++)
> +		kthread_queue_work(client[i].worker, &client[i].work);
> +
> +	start = ktime_get();
> +	pr_info("%u clients:\n\tt\t\tcycle:\t  min    avg    max : ...\n", clients);
> +	for (;;) {
> +		unsigned int min = ~0;
> +		unsigned int max = 0;
> +		unsigned int total = 0;
> +		bool done = true;
> +		char pbuf[16];
> +
> +		memset(buf, 0, PAGE_SIZE);
> +		for (i = 0; i < clients; i++) {
> +			unsigned int cycle, cycles;
> +
> +			cycle = READ_ONCE(client[i].cycle);
> +			cycles = READ_ONCE(client[i].cycles);
> +
> +			snprintf(pbuf, sizeof(pbuf), " %3d", cycle);
> +			strncat(buf, pbuf, PAGE_SIZE);
> +
> +			total += cycle;
> +			if (cycle < min)
> +				min = cycle;
> +			if (cycle > max)
> +				max = cycle;
> +
> +			if (!min || (cycle + 1) < cycles)
> +				done = false;
> +		}
> +
> +		loops++;
> +		delta_total += max - min;
> +
> +		pr_info("\t+%6lldms\t\t  %3u  %3u  %3u :%s\n",
> +			ktime_to_ms(ktime_sub(ktime_get(), start)),
> +			min, DIV_ROUND_UP(total, clients), max, buf);
> +
> +		if (done)
> +			break;
> +
> +		msleep(100);
> +	}
> +
> +	pr_info("    avg_max_min_delta(x100)=%u\n",
> +		loops ? DIV_ROUND_UP(delta_total * 100, loops) : 0);
> +
> +	for (i = 0; i < clients; i++) {
> +		kthread_flush_work(&client[i].work);
> +		kthread_destroy_worker(client[i].worker);
> +	}
> +
> +	for (i = 0; i < clients; i++)
> +		drm_mock_sched_entity_free(client[i].entity);
> +}
> +
> +static const struct kunit_attributes drm_sched_scheduler_many_clients_attr = {
> +	.speed = KUNIT_SPEED_SLOW,
> +};
> +
> +static struct kunit_case drm_sched_scheduler_many_clients_tests[] = {
> +	KUNIT_CASE_PARAM_ATTR(drm_sched_scheduler_many_clients_test,
> +			      drm_sched_scheduler_many_clients_gen_params,
> +			      drm_sched_scheduler_many_clients_attr),
> +	{}
> +};
> +
> +static struct kunit_suite drm_sched_scheduler_many_clients = {
> +	.name = "drm_sched_scheduler_many_clients_tests",
> +	.init = drm_sched_scheduler_init2,
> +	.exit = drm_sched_scheduler_exit,
> +	.test_cases = drm_sched_scheduler_many_clients_tests,
> +};
> +
>  kunit_test_suites(&drm_sched_scheduler_overhead,
>  		  &drm_sched_scheduler_two_clients1,
> -		  &drm_sched_scheduler_two_clients2);
> +		  &drm_sched_scheduler_two_clients2,
> +		  &drm_sched_scheduler_many_clients);