[time] Accuracy goal of the pool
Mon Nov 13 22:29:48 UTC 2006
On 13-11-06 13:18, Tim Shoppa wrote:
>>>> Rob Janssen <rob at knoware.nl> 11/5/2006 5:13:08 AM >>>
>> 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.
The usefulness of the monitor should be related to its primary goal: drop
"really bad" servers from the pool. It is doing that job well (I guess).
If you want to examine the performance of your server (or want a good time
reference) then don't use the pool, but find a good timeserver nearby. AFAIK
the pool (and it's monitor) is to provide reasonable time to the masses and
to reduce the load of the high quality professional time servers. (Well,
something like that ;-) )
Let's first continue on evenly spreading the load(*) before taking the road
to a high precision pool again.
(*) I had to change my settings to a low connection speed so I'm not in the
global pool anymore. My (NAT-)router could not handle the peak load. The
bottleneck is the number of different IP-addresses connecting in a short
time; not the amount of traffic.
More information about the pool