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

Joe Gwinn joegwinn at comcast.net
Tue Mar 18 00:07:53 UTC 2014


In article
<CAKyJ6kanOL-pbM8d+KFCoCeYa6yi0chWPHWGaLxAB8GoWcG+qg at mail.gmail.com>,
Paul <tik-tok at bodosom.net> wrote:

> On Mon, Mar 17, 2014 at 8:50 AM, Joe Gwinn <joegwinn at comcast.net> wrote:
> 
> > Yes.  My question is basically a query about the current state of the
> > art.
> >
> 
> Some NTP offsets (output may look funny if formatted) clock1 looking at
> clock2 and clock3 (a Raspberry Pi).  This suggests it can be as good as
> your IRIG system.
> 
> Gig ethernet to Gig ethernet.  ~22 days:
>     N           Min           Max        Median           Avg        Stddev
>  244059  -0.098741335   0.019727433     9.586e-06  4.814598e-06
> 0.00038621792
> 
> Gig to Fast ~10 days
>     N           Min           Max        Median           Avg        Stddev
>  112254  -0.000516264   0.000453913     1.127e-06 6.8736914e-06
> 4.2248166e-05

People are also lusting after sub-microsecond sync.

It isn't enough to have good averages; the excursions also matter - the
19.7 millisecond max would be a killer.

I've gotten NTPv3 to sync two slow Solaris boxes over 10 Mbit thicknet
to about 7 microseconds rms, but it was in a isolated lab setup.  The
slightest random load in the Solaris boxes would have gotten us back to
millisecond scale.

But my question is about the state of the art in PTP systems, not
systems in general.

Joe Gwinn



More information about the questions mailing list