RE: iFCP

["KRUEGER,MARJORIE (HP-Roseville,ex1)" <marjorie_krueger@hp.com>]

With my HP hat off :-)

> -----Original Message-----
> From: John Hufferd [mailto:hufferd@us.ibm.com]
> Sent: Monday, November 20, 2000 5:51 PM
> To: ips@ece.cmu.edu
> Subject: iFCP
..snip..
> In this FC SAN to FC SAN environment, the thing that I find  interesting
is
> that the iFCP protocol will Encapsulate each FC "Session" separately
> instead of Tunneling all the "Sessions" that arrive on a single FC cable
to
> a single remote Target.  This means that Each "Session" can 
> be individually routed by normal IP routing techniques.
> 
> The reason I think this is interesting is that SAN Edge 
> connect Devices (Gateways) when used with Tunneling requires (n*(n-1))
Edge 
> Connects, where n is the number of SANs being interconnected.  That is, 2
SAN 
> needs 2  Edge Connects (ECs), 3 SANs need 6 ECs, 4 SANs need 12 ECs, 5
need 
> 20 ECs, etc.  The Encapsulation techniques of iFCP, on the other 
> hand, require only "n"  ECs.  (A significant difference).   This maybe
very 
> useful for companies that have a lot of distributed FC based systems.

Please explain how you've arrived at this notion of tunneling (FCoverIP)
requiring n*(n-1) "edge connects" and what you mean by "edge connects".

Implementation experience is a pair of "edge devices" (FCoverIP switching
devices) for a WAN link between remote SANs.  This is a proximity
requirement only - ie, you have to have a physical device at a location to
connect to the local physical wiring(s).  So if there are several SANs at a
physical location, it still requires only one FCoverIP device (with N FC
ports) to handle the WAN connection.


Marjorie Krueger
Networked Storage Architecture
Hewlett-Packard Storage Organization
tel: +1 916 785 2656
fax: +1 916 785 0391
email: marjorie_krueger@hp.com