Random thought on iSCSI vs FC

I read Jeff Hengesbach‘s blog every day, and I’m fairly sure that if you like my blog, you’ll love his. He recently started it, and every post so far has been really interesting. You should check it out.

Anyway, today Jeff wrote about iSCSI SANs. If you’re unfamiliar with the concept, here is a great introduction. You should also know that there are two competing standards, iSCSI (where the storage is accessed over standard ethernet) and Fibre Channel (where the storage is accessed over fiber optics cables). There’s some more in-depth explanation here, but it all boils down to speed and expense.

Among the in-the-know people (AKA: not me), it seems to be a sort of common knowledge that we’re going to be using iSCSI in the future, what with 10Gb ethernet being the standard just-around-the-corner. The current best-of-breed is 8Gb/s FibreChannel from IBM, but 10Gb would trump that, and the added bonus of using tried and true ethernet is very appealing to a lot of people.

Regardless of whether or not we end up with iSCSI I’m not convinced that copper will last us much longer in the grand scheme of things. I suspect that, maybe by the time 100Gb rolls around, we’ll be using ethernet-over-fiber for that stuff. The theoretical bandwidth of optical is just too high to ignore in the long-term. If you want to get all sci-fi, scientists have recently began working on entirely optical versions of most basic integrated circuits.

Just a random observation to spark discussion. What do you see happening in the future of SANs?

  • Anonymous

    In the future, data will be stored in hyperdimensional space, and will be retrieved by wormholes-on-demand, eliminating the need for both bulky computers and complicated wiring.


  • JeffHengesbach

    Thanks for the linkback Matt. Regardless of the underlying technology, SANs have such a natural tie in with virtualization I think their use will follow right along with virtualization’s increase in use.

    Like all things that become more common, the setup, use and management will be streamlined enough for low/moderately savvy admins. In fact, I haven’t seen a marketing push for one yet, but I’d bet the farm on seeing turnkey solutions for a starter SAN / Virtualization environment package tailered for drop-in and run situations.


  • Matt


    You’re welcome. You’re also right. As SAN/Virtualization really becomes commonplace instead of cutting edge (if it’s even that now. Certainly not bleeding edge, anyway), more technologies that we’re just seeing the push for will take it’s place. Storage virtualization, for instance. Very cool idea, even though I don’t have enough storage systems to take advantage of it (or a networking infrastructure to handle it even if I did).

    It’s going to be an exciting next-5-years

  • Jeffrey Brady

    I faced this choice recently. I had 2 vendors fighting for my business. I required a VMWare certified solution, one vendor presented an iSCSI solution & the other Fibre Channel. The difference in price was small and I went with the Fibre Channel solution. I am currently configuring our SAN with VMWare, and while there is a learning curve with FC, I can also say it is very fast. Something to watch for in the next 2 years is going to be FCoE (Fibre Channel over Ethernet).

    Interesting times my fellow standalone sysadmins!

  • Anonymous

    I’ve been hearing how iSCSI is going to take over FC for years now, and it never happens. Now all the big players are abandoning iSCSI for FCoE. Some (like Dell)would tell you it’s because they want to keep those huge profit margins, but that’s simply not true.

    The plain truth is FC was built for storage, TCP/IP was not. It means alot when a company like SUN says they will not build a TCP/IP based storage solution.

    You go look at the big players in the FC market, and I’m talking banks and financial institutions, and they will never replace their FC solutions with iSCSI.

    Also you’re wrong when you say 10GB Ethernet will trump 8GB Fiber Channel. CEE is a rip an replace solution, and it will be a long time before it’s fully implemented, plus you cannot guarantee lossless traffic over extentions. Once you’re on the WAN it’s anyone’s game. Plus there are way cheaper IP solutions than iSCSI that guarantee routed extentions without abandoning FC, such as FCIP.

    FCP will remain the high end SAN solution for years to come, and FCoE will probably fill in the gaps between low end customers who run iSCSI, and those who want to tie into existing FCP SAN’s without going full blown FC.