Re: Equalization and benefits of Parallel Optics (skew correction)
Sorry that I have not replied sooner.
You've got several questions in here, but they seem orthogonal to
the 10 Gig E standards effort. I'll answer them, but I recommend that
we let this thread die after this point, since I certainly am NOT
proposing anything in HIPPI-6400 as a basis for 10 GigEthernet. I
merely wanted to point out that skew is relatively easy to resolve as
a limiting factor in supportable distances for parallel implementations.
You are correct that the PERCENTAGE of cable length required to
create a skew problem is fairly low. But it must be fairly easy to create
a process that avoids stuffing an extra 2 meters of glass into one
fiber versus another in a 300 meter run. Every parallel fiber company
we've ever talked to easily meets these skew requirements. We've
tested cables to 800 meters with no problems. And most companies
have an option for "low-skew" fiber available which we have never
needed to use.
As for HIPPI-6400, we use 12 (or even 23 fibers in some configurations)
in each direction. Our MAC/Link protocol only supports up to one
kilometer at full rate (since we use a credit-based flow control scheme).
As for the cost, it's expensive. I don't have a clue as to the real in-quantity
pricing, but in ones/twos, a 10 meter/12 channel cable is just under
300 bucks (and you need two of them for a link). Again, NONE of these features/
characteristics/costs should be extrapolated to a 10 GigE solution.
----- Original Message -----
From: "Joe Gwinn" <email@example.com>
To: "Roger Ronald" <firstname.lastname@example.org>
Sent: Friday, July 28, 2000 5:34 PM
Subject: Re: Equalization and benefits of Parallel Optics (skew correction)
> At 12:19 PM 0/7/28, Roger Ronald wrote:
> >It is quite possible to get rid of skew between fibers as a factor that limits
> >distance. I speak with some authority here, since our standards committee
> >(NCITS T11.1) has a 12-channel parallel 6.4 Gbit networking standard
> >(HIPPI-6400) that can compensate for up to 10 nanoseconds of skew.
> >This is done dynamically, with timing adjusted every 10 usecs.
> >Works great. We don't care much about skew any more. Jitter is our big
> >distance limiter since we have a discreet clock and our jitter budget must be
> >divided between two signals (clock and data).
> Hmm. Ten nanoseconds maximum skew corresponds to (10*10^-9
> sec)(2/3)(3*10^8 m/s)= 2.0 meters of fiber, so in a 300-meter
> parallel-fiber cable, the optical lengths of all fibers in the cable would
> need to agree to within 2/300= 0.7%, if fiber mismatch is allowed to take
> the entire skew budget. If the link is limited to 100 meters, then the
> fiber optical lengths must agree to within 2/100= 2%. These accuracies
> seem a bit tight for field installations. One would probably have to use
> an OTDR, and trim each fiber to fit.
> How many fibers are in parallel? What's the maximum length of a HIPPI-6400
> cable? What does such a HIPPI cable cost, as a ratio to say a typical
> duplex fiber cable of the same length?
> Joe Gwinn