On Thu, Nov 03, 2022 at 10:01:11AM -0700, Dixit, Ashutosh wrote:
On Wed, 02 Nov 2022 17:11:49 -0700, Umesh Nerlige Ramappa wrote:
Engine busyness samples around a 10ms period is failing with busyness
ranging approx. from 87% to 115%. The expected range is +/- 5% of the
sample period.
When determining busyness of active engine, the GuC based engine
busyness implementation relies on a 64 bit timestamp register read. The
latency incurred by this register read causes the failure.
On DG1, when the test fails, the observed latencies range from 900us -
1.5ms.
One solution tried was to reduce the latency between reg read and
CPU timestamp capture, but such optimization does not add value to user
since the CPU timestamp obtained here is only used for (1) selftest and
(2) i915 rps implementation specific to execlist scheduler. Also, this
solution only reduces the frequency of failure and does not eliminate
it.
In order to make the selftest more robust and account for such
latencies, increase the sample period to 100 ms.
Does it make sense, and also by way of documenting, to use 10 ms for
execlists and 100 ms for GuC? Maybe a comment in the code would be nice
too. Thanks.
I was hoping to keep the same logic for execlist/guc backends. I can add
it to the comments though.
sadly, this is the 2nd time we are bumping this up. This was originally
100us for execlists. With the GuC backend, there is a latency by design
since active busyness is calculated using GT timestamp register.
Execlists relied solely on ktime_get() to check for active busyness and
that seemed to have negligible latency. I see no robust option here.
Thanks,
Umesh
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@xxxxxxxxx>
---
drivers/gpu/drm/i915/gt/selftest_engine_pm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
index 0dcb3ed44a73..87c94314cf67 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
@@ -317,7 +317,7 @@ static int live_engine_busy_stats(void *arg)
ENGINE_TRACE(engine, "measuring busy time\n");
preempt_disable();
de = intel_engine_get_busy_time(engine, &t[0]);
- mdelay(10);
+ mdelay(100);
de = ktime_sub(intel_engine_get_busy_time(engine, &t[1]), de);
preempt_enable();
dt = ktime_sub(t[1], t[0]);
--
2.36.1
