[ntp:questions] NTP absolute accuracy?

Jason Rabel jason at extremeoverclocking.com
Sat Jun 30 16:01:08 UTC 2007


You can't really give an "absolute" number when there is so much uncertainty
and variety in every NTP implementation. Factors such as system hardware,
software, and everything network related, eliminate any possibility of doing
apples to apples comparisons. Even the smallest change can mean large
differences in performance numbers.

Keep in mind only a couple platforms will support a PPS signal.

Read up on Root Dispersion, I think that number might lead you in the right
direction on your quest.

> Hi,
> Does anyone know any survey or paper measuring absolute time accuracy over

> NTP? I saw statistics about offsets, RTT, and dispersion but am not sure
> well those parameters reflect or are correlated with absolute accuracy of 
> each NTP servers and clients.
> To my mind, the only way to measure the absolute accuracy (difference from

> UTC or GPS time) would be to physically bring a GPS receiver to each NTP 
> clients and compare the timing bases. It is certainly not feasible for a 
> large scale survey but I guess there should have been someone who've done 
> this before. Let me know if there is.
> Thanks,
> Juyong 

More information about the questions mailing list