[igt-dev] [PATCH i-g-t] tests/xe_create: Unthread create-execqueues tests

[Jonathan Cavitt]

The inclusion of igt_fork in the test is designed to improve performance
by multithreading the process of execqueue creation.  However, after
each execqueue is created on a thread, a context switch appears to occur,
causing all the execqueues created for that thread to be stored in memory
and all the execqueues for the other thread to be loaded.  At scale, the
delays caused by repeated memory loads and unloads actually cause a
reduction in performance, and as such it's actually more performant to
create the execqueues serially rather than rely on forking.

Signed-off-by: Jonathan Cavitt <jonathan.cavitt at intel.com>
CC: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>
CC: Kamil Konieczny <kamil.konieczny at linux.intel.com>
CC: Lucas de Marchi <lucas.demarchi at intel.com>
CC: Niranjana Vishwanathapura <niranjana.vishwanathapura at intel.com>
---
 tests/intel/xe_create.c | 51 +++++++++++++++++------------------------
 1 file changed, 21 insertions(+), 30 deletions(-)

diff --git a/tests/intel/xe_create.c b/tests/intel/xe_create.c
index bbdddc7c9b..f4a80aa155 100644
--- a/tests/intel/xe_create.c
+++ b/tests/intel/xe_create.c
@@ -136,47 +136,38 @@ static uint32_t __xe_exec_queue_create(int fd, uint32_t vm,
 static void create_execqueues(int fd, enum exec_queue_destroy ed)
 {
 	struct timespec tv = { };
-	uint32_t num_engines, exec_queues_per_process, vm;
-	int nproc = sysconf(_SC_NPROCESSORS_ONLN), seconds;
+	struct drm_xe_engine *engine;
+	uint32_t num_engines, vm;
+	int idx, err, i, seconds;
+	uint32_t exec_queue, exec_queues[MAXEXECQUEUES];
 
 	fd = drm_reopen_driver(fd);
 	num_engines = xe_number_engines(fd);
 	vm = xe_vm_create(fd, DRM_XE_VM_CREATE_FLAG_ASYNC_DEFAULT, 0);
 
-	exec_queues_per_process = max_t(uint32_t, 1, MAXEXECQUEUES / nproc);
-	igt_debug("nproc: %u, exec_queues per process: %u\n", nproc, exec_queues_per_process);
 
 	igt_nsec_elapsed(&tv);
 
-	igt_fork(n, nproc) {
-		struct drm_xe_engine *engine;
-		uint32_t exec_queue, exec_queues[exec_queues_per_process];
-		int idx, err, i;
-
-		srandom(n);
-
-		for (i = 0; i < exec_queues_per_process; i++) {
-			idx = rand() % num_engines;
-			engine = xe_engine(fd, idx);
-			err = __xe_exec_queue_create(fd, vm, &engine->instance,
-						     0, &exec_queue);
-			igt_debug("[%2d] Create exec_queue: err=%d, exec_queue=%u [idx = %d]\n",
-				  n, err, exec_queue, i);
-			if (err)
-				break;
-
-			if (ed == NOLEAK)
-				exec_queues[i] = exec_queue;
-		}
+	for (i = 0; i < MAXEXECQUEUES; i++) {
+		idx = rand() % num_engines;
+		engine = xe_engine(fd, idx);
+		err = __xe_exec_queue_create(fd, vm, &engine->instance,
+					     0, &exec_queue);
+		igt_debug("Create exec_queue: err=%d, exec_queue=%u [idx = %d]\n",
+			  err, exec_queue, i);
+		if (err)
+			break;
+
+		if (ed == NOLEAK)
+			exec_queues[i] = exec_queue;
+	}
 
-		if (ed == NOLEAK) {
-			while (--i >= 0) {
-				igt_debug("[%2d] Destroy exec_queue: %u\n", n, exec_queues[i]);
-				xe_exec_queue_destroy(fd, exec_queues[i]);
-			}
+	if (ed == NOLEAK) {
+		while (--i >= 0) {
+			igt_debug("Destroy exec_queue: %u\n", exec_queues[i]);
+			xe_exec_queue_destroy(fd, exec_queues[i]);
 		}
 	}
-	igt_waitchildren();
 
 	xe_vm_destroy(fd, vm);
 	drm_close_driver(fd);
-- 
2.25.1