AHA2790UW has speed-limit problems ?

[Matthew Jacob]

Sure- but a single-initiator/single-target system is handled well w/o
even going to Ultra right now. I suppose LVD handles a longer wire,
but with current cabling w/o Ultra you're good for 5 meters or so.

It's the case where you want 10-20 drives per 'initiator' and 4-8
'initiators' per system where it gets very useful.

And I look at from a system integrators point of view- the cost
of a SE/LVD card from adaptec may be the same  to me as a FC card.


On Fri, 14 Aug 1998, Justin T. Gibbs wrote:

> >
> >It's exactly this kind of discussion that has encouraged me to think
> >that Fibre Channel is a better technology when you're getting to these
> >speeds. The cost differential between this and parallel SCSI is getting
> >to be pretty small.
> 
> I wish IBM hadn't botched the marketing of SSA.  It's so much nicer than
> Fiber Channel.  The concern we have here at Pluto about Fiber Channel is
> the power cost.  We couldn't put 20 fiber channel drives into our system
> without bumping up to much more expensive, larger capacity, power supplies.
> There is also the fault tolerance issue and expense.  We're single target/
> single initiator so we can "play to air" even if a drive hangs on the wire.
>  With SE/LVD SCSI, we can do this for ~$20 per SCSI HA chip.  SSA would
> have solved this problem with it's dual port nature without forcing us to a
> single controller per drive configuration, but with fiber channel, you have
> no choice.  I can't imagine being able to build a cost effective single
> initiator/single target system with fiber channel.  The tranceiver cost
> alone would kill us.
> 
> --
> Justin
> 
> 


To Unsubscribe: send mail to majordomo at FreeBSD.org
with "unsubscribe aic7xxx" in the body of the message