iFCP

["John Hufferd" <hufferd@us.ibm.com>]

With my TC Hat way off:

I have found the Draft submitted by  Charles Monia, and Joshua Tseng, to be
quite interesting as it applies to Gateway to Gateway protocols between
Fibre Channel SANs.  I believe this draft is intended as an alternative to
the drafts that are currently being looked at on the FCoverIP tract.

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.
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.




.
.
.
John L. Hufferd
Senior Technical Staff Member (STSM)
IBM/SSG San Jose Ca
(408) 256-0403, Tie: 276-0403
Internet address: hufferd@us.ibm.com