On Mon, 2008-11-03 at 11:49 +0800, Xiaofan Chen wrote:
> It seems quite confusing.
> http://en.wikipedia.org/wiki/Latency_(engineering)
> 
> I have read quite some articles about these three words
> now in the context of industrial control network. Ethernet
> is clearly gaining popularity. Various CAN based network
> protocols (CANopen/DeviceNet/etc) are still quite popular
> as well. But both seems to suffer from the latency issue.
> 
> Reference:
> http://www.embeddedrelated.com/usenet/embedded/show/16093-1.php
> 
> Quote:
> "CAN has no particular advantage in latency --- it has one in
> *determinism*, i.e. its latencies won't vary as wildly as those of an
> Ethernet at the same throughput load relative to their respective
> capacities."
> 
> So it seems to me that determinism is measured with the
> jitter (variation of the latency). Is this correct?

Determinism is much more the latency.

At a basic level, if a network is deterministic that means that there
are a set of specs you can rely on with regards to what happens when you
send something.

Usually the most important spec is the "it will get there within this
amount of time". Note that beyond just latency, jitter and things like
that, this can also cover things like error recovery, the order packets
arrive, etc.

TTYL

-- 
http://www.piclist.com PIC/SX FAQ & list archive
View/change your membership options at
http://mailman.mit.edu/mailman/listinfo/piclist