[ntp:questions] Can NTP sync within 1ms

William Unruh unruh at invalid.ca
Sun Apr 27 15:57:50 UTC 2014

On 2014-04-27, Jason Rabel <jason at extremeoverclocking.com> wrote:
>> First, we sync all machines to locally connected GPS receivers with
>> PPS output.  We use ntpd and kernel PPS.  This is wellknown territory.
>> In the ntpq -p stats this appears to bring the systems within 10us,
>> often within 2us, of the PPS signal.  We still have to find out if this
>> is reality or just output of a program.
> You need to look up the specs of your GPS units to see what the PPS performance is spec'ed for. That uncertainty needs to be
> factored into your final figure.
> Likewise, are you inputting surveyed antenna coordinates at each location or just letting the receiver auto-survey? If the "assumed"
> position is off that is another source of time error.

2nano sec per meter, max. And the gps units are going to self survey to
within 10m. which is 20ns max. Why in the world would they be worrying
about that when interrupt latencies are are at the microsecond level?
If you are going to be timing neutrinos from Cern to Grand Sasso, your
concern is certainly valid. But you would not be using interrupts on a commodity 
computer for that. 

More information about the questions mailing list