[Intel-gfx] [PATCH i-g-t] igt/gem_ctx_switch: Show the combined ctx-switch latency

[Chris Wilson]

Since we submit from several processes to the same engine for the forked
tests, the total number of context switches is the sum of each process
and needs to be combined together to compute the individual cs latency.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 tests/gem_ctx_switch.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tests/gem_ctx_switch.c b/tests/gem_ctx_switch.c
index 6770e001f..58b9bfd3e 100644
--- a/tests/gem_ctx_switch.c
+++ b/tests/gem_ctx_switch.c
@@ -94,8 +94,15 @@ static void single(int fd, uint32_t handle,
 	struct drm_i915_gem_exec_object2 obj;
 	struct drm_i915_gem_relocation_entry reloc;
 	uint32_t contexts[64];
+	struct {
+		double elapsed;
+		unsigned long count;
+	} *shared;
 	int n;
 
+	shared = mmap(NULL, 4096, PROT_WRITE, MAP_SHARED | MAP_ANON, -1, 0);
+	igt_assert(shared != MAP_FAILED);
+
 	gem_require_ring(fd, e->exec_id | e->flags);
 
 	for (n = 0; n < 64; n++) {
@@ -163,11 +170,31 @@ static void single(int fd, uint32_t handle,
 		igt_info("[%d] %s: %'u cycles: %.3fus%s\n",
 			 child, e->name, count, elapsed(&start, &now)*1e6 / count,
 			 flags & INTERRUPTIBLE ? " (interruptible)" : "");
+
+		shared[child].elapsed = elapsed(&start, &now);
+		shared[child].count = count;
 	}
 	igt_waitchildren();
 
+	if (ncpus > 1) {
+		unsigned long total;
+		double max = 0;
+
+		for (n = 0; n < ncpus; n++) {
+			total += shared[n].count;
+			if (shared[n].elapsed > max)
+				max = shared[n].elapsed;
+		}
+
+		igt_info("Total %s: %'lu cycles: %.3fus%s\n",
+			 e->name, total, max*1e6 / total,
+			 flags & INTERRUPTIBLE ? " (interruptible)" : "");
+	}
+
 	for (n = 0; n < 64; n++)
 		gem_context_destroy(fd, contexts[n]);
+
+	munmap(shared, 4096);
 }
 
 static void all(int fd, uint32_t handle, unsigned flags, int timeout)
-- 
2.18.0