Danny,
It's not the network latency that dominates the delay, but the FIFOs in
the gigabit Ethernet chip (PCNET, etc.), which can hold several packets.
This distorts the timestamps in both the transmit and receive sides.
This is one of the things the interleaved modes were designed to cope
with, but the fact not every packet generates an interrupt distorts even
more. In some machines, specially Sunses, there can be an additional
input delay of up to 2 microseconds.
Dave
Danny Mayer wrote:
Frans Grotepass wrote:
Hi all,
Sorry for abusing my membership to this forum for this question.
We are busy with building an embedded application that must retrieve data very
fast. The choice is to either have the data locally or go to a central
server(pool) that contains the data.
In evaluating the network option, I thought that the people here could
possibly help me with the expected network latency for a Gb network via a
switch. My gut feeling says that with increased load, the switch will bundle
the traffic to the different nodes more and this will result in higher latency.
If you are asking a non-NTP question then this really is the wrong
place. Our discussions of network latency are around the effects that it
has on NTP calculations and the error budget.
My only other comment is that local data is always faster (unless you
have really slow disk drives) so why are you asking in the first place?
It can't be just about the network latency.
Danny
_______________________________________________
questions mailing list
questions@lists.ntp.org
http://lists.ntp.org/listinfo/questions
_______________________________________________
questions mailing list
questions@lists.ntp.org
http://lists.ntp.org/listinfo/questions
