[ntp:questions] IEEE 1588 (PTP) at the nanosecond level?

Terje Mathisen terje.mathisen at tmsw.no
Mon Mar 17 17:35:43 UTC 2014

William Unruh wrote:
> On 2014-03-17, Martin Burnicki <martin.burnicki at meinberg.de> wrote:
>> If you have a counter chain clocked by 20 MHz then the timestamps
>> captured when PTP packets are going out or are coming in have a
>> resolution of 50 ns.
> I am not saying that a computer or a piece of hardware cannot have a 1
> ns resoltuion. I am saying that imagining that I can sychronize two such
> clocks over the network or via gps is.

At this point I think you are simply wrong:

The UTC ensemble clock is published every month, it is a paper clock 
determined by a weighted vote between all the highest quality reference 
clocks in national laboratories, right?

The way they compare all these clocks, in order to do the voting, is 
mostly by common view GPS observation.

I.e. they can use gps to sync clocks at very small fractions of a ns.

- <Terje.Mathisen at tmsw.no>
"almost all programming can be viewed as an exercise in caching"

More information about the questions mailing list