[ntp:questions] what happens when sys.peer turns stratum 16?

Bill Unruh unruh at physics.ubc.ca
Mon May 31 20:49:33 UTC 2010


References: <4eea00b1-966a-4f39-a6cc-265ce959c14a at s4g2000prh.googlegroups.com> <slrni06c22.l1a.unruh at wormhole.physics.ubc.ca> <uo3cd7-9231.ln1 at ntp.tmsw.no>

On 2010-05-31, Terje Mathisen <"terje.mathisen at tmsw.no"> wrote:
> unruh wrote:
>> Note, that this is one of the reasons why your customers should never
>> use 2 servers. You have no way to know which one is crazy. Use 3 or 5.
>> (4 can be as bad as 2 if two of the servers go nuts in exactly the same
>> way-- eg they are both tied to a single server which has gone nuts).
>
> This is simply wrong:
>
> The number of immediate peers don't matter, it is the number of 
> _independent_ servers that you should count.
Maybe. But that is not what you can count.
>
> Using multiple (say) S2 servers which all depend on a single S1 just 
> means that you've (intentionally or not) outsmarted the ntpd voting 
> algorithm. :-(

Using the pool, you have no control over who the root servers are of the
systems you get assigned and I am willing to bet that a large fraction
of them use the same S0 at the end of the day. ( and if you count GPS,
which could go haywire, I suspect that a very large fraction of the
total use the same ultimate time source.)
But even if you do not use servers with the same root, it is still
possible that two servers could go out in thesame way, leaving to blocks
with equal numbers. This is why committees have odd numbers of members.
I agree that if the servers you use are realy independent then the
probability of such equal blocks is verysmall. Unfortunately that
independence is far from guarenteed.


By the way, what was it you are saying is "simply wrong"? That ntp would
be confused if there were two equal voting blocks? That four sources
could produce two equal voting blocks?
>
> Terje
>

-- 




More information about the questions mailing list