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

Paul tik-tok at bodosom.net
Thu Mar 20 20:06:17 UTC 2014


On Thu, Mar 20, 2014 at 1:35 PM, Rob <nomail at example.com> wrote:

> Paul <tik-tok at bodosom.net> wrote:
> > Sure.  My point is I haven't seen a use case in this thread for
> nanosecond
> > *accuracy* relative to the TAI paper clock.
>
> It is not for timestamping the moment of clicking in an online auction
> or stock trade?
>

The original question was about the capability of PTP as an improvement
over NTP possibly based on IRIG time transfer.   Given such a vague
question one might simply say if you spend enough money you can do better
than the noted O(1ms).  Eventually *this* thread drifted off the rails into
the realm of national lab scale transfers.  Since Joe Gwinn didn't say
there was a need for such a degree of *fidelity* (truth as opposed to
precision or accuracy, I should have made that more clear) I don't yet know
why the issue came up.


More information about the questions mailing list