NTPsec leap second experience

[Achim Gratz]

Eric S. Raymond writes:
> However, what I *do* take away is that our drastic reduction surgery
> on the rest of the suite apparently has not accidentally damaged the
> PLL nor screwed up its convergence properties. I find that very
> reassuring.

While that was not in fact my point in my previous posts, the NTP loop
indeed seems to be working as designed and doesn't seem to have picked
up any defects from the code changes in NTPsec.

What I was getting at was that I've had quite good holdover performance
(<1ms over 47 hours) that I wasn't really expecting to see from
something as cheap as the rasPi and my improvised "ovenization" (which
really is just a cardboard box and some bubble wrap plus running
sha512sum on two of the rasPi cores to keep it at the desired
temperature).  If NTP would have had some feedforward loop to keep the
frequency offset adjusted during holdover that might have resulted in
<30µs deviation over that same period of time.  In general I'd expect
that feedforward compensation could improve NTP performance by about one
order of magnitude.


Regards,
Achim.
-- 
+<[Q+ Matrix-12 WAVE#46+305 Neuron microQkb Andromeda XTk Blofeld]>+

DIY Stuff:
http://Synth.Stromeko.net/DIY.html