[ntp:questions] Frequently asked question about error bounds?
david at ex.djwhome.demon.invalid
Sun Nov 1 11:12:02 UTC 2009
> 1) In the documentation for RFC1305 p. 102 it can be read that the
> true offset between
> client and server must lie somewhere in the correctness interval,
> defined by
> I=[theta - delta/2 - epsilon, theta + delta/2 + epsilon]
This is (more) correct. I'm not sure if it fully accounts for some of
the details of the intersection algorithm. One would need to double
check whether it was valid during startup transients and in the light of
the averaging of multiple sources that is actually used to estimate the
> 2) And in threads and websites I usuallly see the statement that the
> error is bounded with half the roundtrip. And it sure look like that
> when scatter diagram(wedge plots) with offset as a function rtt are
This is an oversimplification that is quite often valid in cases where
the error is significant, as delay tends to dominate dispersion and most
of the delay, and in particular, nearly all its asymmetry, is associated
with the "retail" hop.
Another factor, I think is that the RFC attempts to be a mathematical
treatise, and the use of lots of Greek letters, rather than spelling out
what they mean, turns people off, so very few users can actually read
and understand the RFC.
Please note that RFC 1305 is de facto obsolete, and current versions of
NTP actually correspond with a new, draft, RFC.
Also note that this is not a frequently asked question, although maybe
it should be.
More information about the questions