Which way is it going to go?
iSCSI vs. FC? In my opinion, every technology that went up against IP came second mainly due to costs, complexity, interoperability and available skills. Would FC go the same way against SCSI over IP or FC/IP?

    Requires Free Membership to View

    Login

    When you register for SearchStorage.com, you’ll also receive targeted emails from my team of award-winning editorial writers. Our goal is to keep you informed on the hottest topics, the latest news and the biggest challenges you face as a storage professional today.

    Rich Castagna, Editorial Director

    By submitting your registration information to SearchStorage.com you agree to receive email communications from TechTarget and TechTarget partners. We encourage you to read our Privacy Policy which contains important disclosures about how we collect and use your registration and other information. If you reside outside of the United States, by submitting this registration information you consent to having your personal data transferred to and processed in the United States. Your use of SearchStorage.com is governed by our Terms of Use. You may contact us at webmaster@TechTarget.com.

I believe it is very difficult for an insurgent technology like FC to prevail against an entrenched infrastructure technology like TCP/IP. However, there are a few points worth making in regard to your question.

1) FC/IP and FC are complimentary, not competitive.

2) FC really competes with Gigabit Ethernet, not TCP/IP. TCP/IP is also supported on top of FC. It is probably ridiculous to suggest it, but iSCSI could run on top of FC as well as GbE.

3) Token Ring, FDDI and other network technologies competed with Ethernet as data networking technologies that connect systems together. FC is not trying to eat into Ethernet's market, it is creating a new one. It's just not clear that a new technology is needed for a new market opportunity.

4) Contrary to popular belief, FC fabric technology was not developed for storage, it was developed as a backbone network although it does not compete as such. FC loops were developed for storage and they have pretty much disappeared from the planet as a SAN topology.

5) FC, Ethernet and TCP/IP are not optimized for storage. If they were, they would provide routing algorithms that participate in storage pathing - with systems being active participants in route selection. The FC industry had a chance to give themselves a real advantage but blew it by taking the easy way out and adopting IP routing technology (OSPF).

6) SCSI has pretty much outlasted its usefulness but there is nothing else coming along to take its place. Protocol changes will be driven by the need to "tighten up" error recovery beyond SCSI's sloppy timeouts.

As for my opinion about ISCSI and FC: I believe the number of people who know, support, develop and install TCP/IP networks all play in iSCSI's favor. The iSCSI industry needs to see real leadership emerge however, instead of relying on Cisco to lead by default.

Regards,
Marc

Editor's note: Do you agree with this expert's response? If you have more to share, post it in one of our .bphAaR2qhqA^0@/searchstorage>discussion forums.


This was first published in June 2002