[Bug 102250] [CI] igt at pm_rps@* - fail - Test assertion failure function waitboost - Failed assertion: *_freqs[CUR] [==|<] *_freqs[*]

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=102250

--- Comment #25 from Chris Wilson <chris at chris-wilson.co.uk> ---
A "light" load:

(pm_rps:1331) DEBUG: Apply low load again...
(pm_rps:1331) DEBUG: gt freq (MHz):  cur=900  min=300  max=900  RP0=900 
RP1=300  RPn=300  boost=900
(pm_rps:1331) DEBUG: gt freq (MHz):  cur=900  min=300  max=900  RP0=900 
RP1=300  RPn=300  boost=900
(pm_rps:1331) igt_debugfs-DEBUG: Opening debugfs directory
'/sys/kernel/debug/dri/0'
(pm_rps:1331) igt_debugfs-DEBUG: i915_rps_boost_info:
RPS enabled? 1
GPU busy? yes [1 requests]
CPU waiting? 0
Boosts outstanding? 0
Interactive? 0
Frequency requested 900
  min hard:300, soft:300; max soft:900, hard:900
  idle:300, efficient:300, boost:900
pm_rps [1331]: 1 boosts
pm_rps [1331]: 0 boosts
Kernel (anonymous) boosts: 0

RPS Autotuning (current "high power" window):
  Avg. up: 99% [above threshold? 85%]
  Avg. down: 99% [below threshold? 60%]

where the HW thinks it is 100% busy over the course of an EI. That's a test
bug.

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
You are on the CC list for the bug.
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20180904/3ebb2e86/attachment.html>