Best practices question

[Paul Theodoropoulos]

On 6/26/19 11:22, Paul Theodoropoulos wrote:
> wow, fascinating - I set my c-ntpsec PPS min/maxpoll to 2. The RMS 
> time jitter rose a fairly significant amount, from hovering around 
> 0.6µs  to now 1.0µs  -- while the RMS frequency jitter plummeted from 
> hovering around 4ppb down to, well, barely discernably above 0ppb on 
> the graph.
>
> eh, saying it just doesn't tell the story -
>
> Time jitter: https://i.imgur.com/jNlaAAj.png
>
> Frequency jitter: https://i.imgur.com/wAF2nu9.png
>
I think maybe I'm  hitting a bug or I'm just not understanding (usually 
the latter), as it doesn't seem possible:

https://i.imgur.com/LorPR2F.png

jitter fluctuating between 400 parts per trillion and 800 ppt?? From a 
Raspberry Pi running at 1.4Ghz?

That said, I switched to min/maxpoll 1 for PPS, and saw a corresponding 
change - so Time jitter appears to be inversely correlated to Frequency 
jitter - less frequency jitter, more time jitter, and vice-versa. This 
is all fascinating.


-- 
Paul Theodoropoulos
www.anastrophe.com

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.ntpsec.org/pipermail/users/attachments/20190626/6ccdfc98/attachment.htm>