On Sep 13, 11:13 am, "Richard B. Gilbert" <[EMAIL PROTECTED]> wrote: > Rick Jones wrote: > > I was wondering - is everyone confident enough that all these clients > > choosing the "best" servers won't eventually settle on the same small > > handfull of them? > > > rick jones > > The quality of time and therefore the "best" servers depends strongly on > the length of the network path between server and client.
>From my experience monitoring 1000+ servers several times an hour, I don't believe this is true. In the pool all 1381 "active" servers are "good enough", but clearly some are keeping better time than others. Eventually I'll get more and better monitoring stations setup around the world and we'll have more data... Having "smarts" in the client that would make them eventually pool towards the "best" servers should be a concern, considering the objective of the pool (spread out traffic so The Best Servers won't get hopelessly overloaded). - ask > The probability that "all these clients" will eventually select the same > servers is minimal. This assumes that the pool servers are NOT all > huddling in Peoria, Illinois or something like that. _______________________________________________ questions mailing list questions@lists.ntp.org https://lists.ntp.org/mailman/listinfo/questions
