On 04/02/2019 08:41, Chris Wilson wrote:
Limit the NEWCLIENT boost to only give its small priority boost to fresh
clients only that have no dependencies.

Needs some actual explaining/documenting on why we would want this.

Signed-off-by: Chris Wilson <[email protected]>
---
  drivers/gpu/drm/i915/i915_request.c | 2 +-
  1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c 
b/drivers/gpu/drm/i915/i915_request.c
index 7968875d0bed..69bc549e95d8 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -979,7 +979,7 @@ void i915_request_add(struct i915_request *request)
                 * Allow interactive/synchronous clients to jump ahead of
                 * the bulk clients. (FQ_CODEL)
                 */
-               if (!prev || i915_request_completed(prev))
+               if (list_empty(&request->sched.signalers_list))

Why are the !prev and completed checks gone? Seems in disagreement with the commit message text - they wouldn't have to be new clients any more, just have no dependencies.

                        attr.priority |= I915_PRIORITY_NEWCLIENT;
engine->schedule(request, &attr);


Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Reply via email to