LKM Timemark Driver
Stromeko at nexgo.de
Tue Aug 28 19:43:03 UTC 2018
Gary E. Miller via devel writes:
>> That doesn't really matter, it is still about three orders of
>> magnitude improvement over what we get today for the error that
> Ah no. Lukas says 200 ns. I can easily get under 1,000 ns. Sometimes
> down to 400 ns with care.
So do I, in fact I run between 140ns to 240ns of "average jitter" pretty
consistently across five machines (three different rasPi and two
TinkerBoard). The higher numbers are for the two machines that are
actually doing extra work (about one half to a single core on average w/
heavy interrupt load), the other three machines just run NTP and have no
extra tasks. However, those numbers are essentially useless, as I'm
quite certain that the true residual offset is at least 10…15µs and
plausibly into the 30µs range. I could tune out some of the offset by
comparing the average deviation as observed in a three-cornered-hat
configuration over long observation times, but that would still leave a
residual offset. Getting that residual offset down to roughly the same
figures, only in the nanosecond range instead of microseconds is what I
was talking about.
> That is 2x, maybe 5x, certinaly not three
> orders of magnitude. You'll have 3 orders of magnitude when you
> get to 1 ns jitter. No consumer GPS can do that.
Stop deluding yourself with meaningless numbers. Even if loopstat
started to tell you such low figures it would simply be a lie. To get
below 1ns you need a clock source that has significantly better ADEV
than 1e-9 @ tau=1s when free running.
>> We don't need to determine any interrupt latency when there's no such
>> latency involved because we don't go through an interrupt for doing
>> the measurement.
> No need to keep beating that dead horse.
Well, you were the one who saddled it up again, I was just shooting it
again to be sure it stays dead.
+<[Q+ Matrix-12 WAVE#46+305 Neuron microQkb Andromeda XTk Blofeld]>+
SD adaptations for KORG EX-800 and Poly-800MkII V0.9:
More information about the devel