[ntp:questions] long linear network, time accuracy, and ntp strata

unruh unruh at wormhole.physics.ubc.ca
Wed Oct 20 15:04:13 UTC 2010

On 2010-10-19, Miernik, Jerzy (Jerzy) <jerzy.miernik at alcatel-lucent.com> wrote:
> Unruh and Terje, thank you for replying. 
> What if we complicated networking somewhat, such that at times node50 acquires GPS capability while node1 may looses it? Actually, to make the problem general, any one node (possibly only one) may have GPS and remain at an extremity of the network, where indeed the traffic between 'outer' nodes must be routed through all other 48 nodes forming a chain of 49 hops. So, sometimes node2 may have GPS too, like this:
> Node2 --- node3 --- node1 --- node4 --- .... --- node49 --- node50
> Or nodes node1, node2, node3, node4 have GPS in some kind of a 'normal' network of four, with a long tail (like in a kite) of 46 nodes attached to one of the four. 

That is I am afraid a terrible routing model. You will never get good
timing from it. GPS or no GPS. "I want to drive from New Yourk to San
Francisco as quicly as possible, but my car has one wheel locked by a
police boot, and the somebody put water into my gas tank. How can I get
from New York to SF?"
You do not and you cannot get good timing with your routing model.
And if your servers keep popping in and out of existence, it is even
worse. Is this some homework assignment?

> How best could we write ntp.conf, to synchronize time in such special networks?

> Warm regards,
> Jerzy.
> -----Original Message-----
> From: questions-bounces+jerzy.miernik=alcatel-lucent.com at lists.ntp.org [mailto:questions-bounces+jerzy.miernik=alcatel-lucent.com at lists.ntp.org] On Behalf Of unruh
> Sent: Tuesday, October 19, 2010 7:37 AM
> To: questions at lists.ntp.org
> Subject: Re: long linear network, time accuracy, and ntp strata
> On 2010-10-18, Miernik, Jerzy (Jerzy) <jerzy.miernik at alcatel-lucent.com> wrote:
>> I have a question about how to use ntp in a long linear network. Assume there are 50 nodes with the one most in the West having GPS, and every node running ntpd:
>>   node1 --- node2 --- node3 --- ... --- node50
>>   GPS
> What does "long linear network" mean? Does it really mean that all
> network traffic between node 1 and node 50 must pass through eachof the
> other machines ( eg because all have two network cards and the only
> connection from node i to i-1 is via one card and from i to i+1 is via
> the other network card on machine i?)
> If so, you will have a horribly slow network no matter what you do. 
> Almost always direct connection is more accurate-- the outbound and
> inbound network times are measured for each packet. Not assumed.
> But as said by others, you want each of those nodes requesting time
> directly from node 1. ( also note that a chain of 50 machines each
> asking time from the previous one exhauses the possible stratum numbers
> and it will not work. )
>> Which approach to synchronization would be better in terms of the time accuracy in nodes:
>> 1. configure 'server node1 ...' in nodes 2, 3, ..., 50; or
>> 2. use manycast for automatic client / server self-organization?
>> Approach 1 seems to me to lead to inferior accuracy due to increasing distance between a client in nodex and server in node1, where routing in nodes node2, node3, ..., node(x-1) would add to jitter. Yet we would have one node stratum1 and all others stratum2, it would seem...
>> I would think approach 2 with manycast would end up in smaller offsets (if any) between clocks, but would lead to clocks of stratum 16, 17, ..., 50, and I am not sure how ntpd would react in node16, node17, ..., node50. 
>> Could an expert please offer a comment on which approach would be preferable? 
>> Sincerely,
>> Jerzy.
> _______________________________________________
> questions mailing list
> questions at lists.ntp.org
> http://lists.ntp.org/listinfo/questions

More information about the questions mailing list