[time] Accuracy goal of the pool

Tim Shoppa tshoppa
Mon Nov 13 12:18:15 UTC 2006


>>> Rob Janssen <rob at knoware.nl> 11/5/2006 5:13:08 AM >>>
> But that aside, I think the current monitoring server lacks the
capability
> to get good data on the offset of each server.  What it does is to
poll
> each server once every couple of hours, and put the single response
> that it gets (or does not get) into the statistics.  This means the
offset
> shown on the www.pool.ntp.org pages is more indicative of the random
> network delay between the polling server and the time servers in the
> pool, than of the actual accuracy of those servers.

And making it even less useful, only the absolute
value of the measured (I say "measured" to distinguish
it from "true") offset is being stored and graphed.

This is somewhat useful if you truly believe that all
offsets are randomly distributed between positive and
negative numbers (and thus only the magnitude of
the offset matters). But nobody who has been
doing this for more than a day would believe this.

It is a true reduction in the usefulness of the data to
server maintainers that they cannot see the direction
of the offset. This information would truly be useful to
someone trying to diagnose refclock or asymmetric
network delay issues.

Tim.




More information about the pool mailing list