On la, 2016-11-05 at 18:35 +, Chris Wilson wrote:
> On Sat, Nov 05, 2016 at 10:35:59AM +0200, Imre Deak wrote:
> > There is a small race where a new request can be submitted and retired
> > after the idle worker started to run which leads to idling the GPU too
> > early. Fix this by deferring
On Sat, Nov 05, 2016 at 10:35:59AM +0200, Imre Deak wrote:
> There is a small race where a new request can be submitted and retired
> after the idle worker started to run which leads to idling the GPU too
> early. Fix this by deferring the idling to the pending instance of the
> worker.
>
> This
There is a small race where a new request can be submitted and retired
after the idle worker started to run which leads to idling the GPU too
early. Fix this by deferring the idling to the pending instance of the
worker.
This scenario was pointed out by Chris.
Cc: Chris Wilson