Re: [Intel-gfx] [PATCH igt 01/16] igt/gem_sync: Exercise and measure idle requests

2018-03-05 Thread Chris Wilson
Quoting Joonas Lahtinen (2018-03-05 13:43:33)
> For some reason, I've reviewed these from the middle of the series
> (maybe transport delay?). Are the rest still applicable or refreshed
> somewhere?

Virtually all, baring a couple have landed. The current unreviewed pile
now has 7 patches, so in the meantime another 5 have been added...
-Chris
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx


Re: [Intel-gfx] [PATCH igt 01/16] igt/gem_sync: Exercise and measure idle requests

2018-03-05 Thread Joonas Lahtinen
For some reason, I've reviewed these from the middle of the series
(maybe transport delay?). Are the rest still applicable or refreshed
somewhere?

Regards, Joonas
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx


[Intel-gfx] [PATCH igt 01/16] igt/gem_sync: Exercise and measure idle requests

2018-02-20 Thread Chris Wilson
Don't just wait for the batch to be completed, wait for the system to
idle! Then wake it up and do it again.

Signed-off-by: Chris Wilson 
---
 tests/gem_sync.c | 41 +
 1 file changed, 41 insertions(+)

diff --git a/tests/gem_sync.c b/tests/gem_sync.c
index ad43b1a3..d70515ea 100644
--- a/tests/gem_sync.c
+++ b/tests/gem_sync.c
@@ -152,6 +152,45 @@ sync_ring(int fd, unsigned ring, int num_children, int 
timeout)
igt_assert_eq(intel_detect_and_clear_missed_interrupts(fd), 0);
 }
 
+static void
+idle_ring(int fd, unsigned ring, int timeout)
+{
+   const uint32_t bbe = MI_BATCH_BUFFER_END;
+   struct drm_i915_gem_exec_object2 object;
+   struct drm_i915_gem_execbuffer2 execbuf;
+   double start, elapsed;
+   unsigned long cycles;
+
+   gem_require_ring(fd, ring);
+
+   memset(, 0, sizeof(object));
+   object.handle = gem_create(fd, 4096);
+   gem_write(fd, object.handle, 0, , sizeof(bbe));
+
+   memset(, 0, sizeof(execbuf));
+   execbuf.buffers_ptr = to_user_pointer();
+   execbuf.buffer_count = 1;
+   execbuf.flags = ring;
+   gem_execbuf(fd, );
+   gem_sync(fd, object.handle);
+
+   intel_detect_and_clear_missed_interrupts(fd);
+   start = gettime();
+   cycles = 0;
+   do {
+   do {
+   gem_execbuf(fd, );
+   gem_quiescent_gpu(fd);
+   } while (++cycles & 1023);
+   } while ((elapsed = gettime() - start) < timeout);
+   igt_assert_eq(intel_detect_and_clear_missed_interrupts(fd), 0);
+
+   igt_info("Completed %ld cycles: %.3f us\n",
+cycles, elapsed*1e6/cycles);
+
+   gem_close(fd, object.handle);
+}
+
 static void
 store_ring(int fd, unsigned ring, int num_children, int timeout)
 {
@@ -802,6 +841,8 @@ igt_main
for (e = intel_execution_engines; e->name; e++) {
igt_subtest_f("%s", e->name)
sync_ring(fd, e->exec_id | e->flags, 1, 150);
+   igt_subtest_f("idle-%s", e->name)
+   idle_ring(fd, e->exec_id | e->flags, 150);
igt_subtest_f("store-%s", e->name)
store_ring(fd, e->exec_id | e->flags, 1, 150);
igt_subtest_f("many-%s", e->name)
-- 
2.16.1

___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx