[Intel-gfx] [PATCH 3/3] drm/i915: Remove wait priority boosting

[Chris Wilson]

Quoting Chris Wilson (2020-05-07 16:23:38)
> Upon waiting a request (when asked), we gave that request a small
> priority boost, not enough for it to cause preemption, but enough for it
> to be scheduled next before all equals. We also used that bit to give
> new clients a small priority boost, similar to FQ_CODEL, such that we
> favoured short interactive tasks ahead of long running streams.
> 
> However, this is causing lots of complications with timeslicing where we
> both want to honour the boost and yet ignore it. Those complications
> cause unexpected user behaviour (tasks not being timesliced and run
> concurrently as epxected), and the easiest way to resolve that is to
> remove the boost. Hopefully, we can find a compromise again if we need
> to, but in theory timeslicing itself and future more advanced schedulers
> should give us the interactivity boost we seek.

Fwiw, initial results show that it would be possible to remove
the NOSEMA handling as well now. Previously gem_wsim -r busy would be
hurt due to the inopportune semaphores and slow timeslicing. Touch wood,
that pain seems to be gone. But that will take a few days to get solid
numbers.
-Chris