[time-nuts] new year crashes
magnus at rubidium.dyndns.org
Mon Jan 2 18:26:02 EST 2017
The number for the fiber is accurate.
However, fiber isn't laid straight path. I add at least 40% as a
precaution, as if laid on the sides of a square, where the original path
is the diagonal. This is however a very conservative measure to real world.
However, equipment delays can be much larger, and if you now have
buffers they can cause much much higher delays. How well the network is
managed controls the additional delay and it's variations.
You milage may vary, indeed.
These are among the things I need to know after half a bottle of wine.
On 01/02/2017 05:58 PM, Mark Spencer wrote:
> In my prior experience (from approx 5 to 20 years ago) actual wide area net work links delivered over fiber from commercial providers could have latencies of at least several times those figures. I seem to recall efforts were made to lower latencies for applications such as stock trading but I never had any exposure to those connections.
> Best regards
> Mark Spencer
>> How can they get a delay that long? Satellite link?
>> Fiber is 5 microseconds per km. So 1000 km is 5 ms.
>> These are my opinions. I hate spam.
>> time-nuts mailing list -- time-nuts at febo.com
>> To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts
>> and follow the instructions there.
> time-nuts mailing list -- time-nuts at febo.com
> To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts
> and follow the instructions there.
More information about the time-nuts