[Intel-gfx] [PATCH 2/2] drm/i915/gt: Suppress internal I915_PRIORITY_WAIT for timeslicing

Chris Wilson chris at chris-wilson.co.uk
Wed May 6 14:46:00 UTC 2020

Quoting Chris Wilson (2020-05-06 15:36:16)
> Make sure we ignore the I915_PRIORITY_WAIT hint when looking at
> timeslicing, as we do not treat it as a preemption request but as a soft
> ordering hint. If we apply the hint, then when we recompute the ordering
> after unwinding for the timeslice, we will often leave the order
> unchanged due to the soft-hint. However, if we apply it to all those we
> unwind, then the two equivalent levels may be reordered, and since the
> dependencies will be replayed in order, we will not change the order of
> dependencies.
> There is a small issue with the lack of cross-engine priority bumping on
> unwind, leaving the total graph slightly unordered; but that will not
> result in any misordering of rendering on remote machines as any
> signalers will also be live. Though there may be a danger that this will
> upset our sanitychecks.
> Why keep the I915_PRIORITY_WAIT soft-hint, I hear Tvrtko ask? Despite
> the many hairy tricks we play to have the hint and then ignore it, I
> still like the concept of codel and the promise that it gives for low
> latency of independent queues!

Tvrtko is warned not to ask when we replace strict priorities with
isoschronous and psuedo-deadline scheduling.

More information about the Intel-gfx mailing list