]> git.baikalelectronics.ru Git - kernel.git/commit
drm/i915: Priority boost for new clients
authorChris Wilson <chris@chris-wilson.co.uk>
Mon, 1 Oct 2018 14:47:53 +0000 (15:47 +0100)
committerChris Wilson <chris@chris-wilson.co.uk>
Mon, 1 Oct 2018 19:34:19 +0000 (20:34 +0100)
commit52e6295bf066362d81dac4e4d9708cf30e374494
tree4d40534af04067fbe590fbc25e0d6d221e3f7aa3
parent56e2d6964f083b3b81005bd1604a3262eb8977ce
drm/i915: Priority boost for new clients

Taken from an idea used for FQ_CODEL, we give the first request of a
new request flows a small priority boost. These flows are likely to
correspond with short, interactive tasks and so be more latency sensitive
than the longer free running queues. As soon as the client has more than
one request in the queue, further requests are not boosted and it settles
down into ordinary steady state behaviour.  Such small kicks dramatically
help combat the starvation issue, by allowing each client the opportunity
to run even when the system is under heavy throughput load (within the
constraints of the user selected priority).

v2: Mark the preempted request as the start of a new flow, to prevent a
single client being continually gazumped by its peers.

Testcase: igt/benchmarks/rrul
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181001144755.7978-1-chris@chris-wilson.co.uk
drivers/gpu/drm/i915/i915_request.c
drivers/gpu/drm/i915/i915_scheduler.h
drivers/gpu/drm/i915/intel_lrc.c