TechOpsGuys.com Diggin' technology every day

14Feb/11Off

Lackluster FCoE adoption

I wrote back in 2009, wow was it really that long ago, one of my first posts, about how I wasn't buying into the FCoE movement, at first glance it sounded really nice until you got into the details and then that's when it fell apart. Well it seems that I'm not alone, not long ago in an earnings announcement Brocade said they were seeing lackluster FCoE adoption, lower than they expected.

He discussed what Stifel's report calls "continued lacklustre FCoE adoption." FCoE is the running of Fibre Channel storage networking block-access protocol over Ethernet instead of using physical Fibre Channel cabling and switchgear. It has been, is being, assumed that this transition to Ethernet would happen, admittedly taking several years, because Ethernet is cheap, steamrolls all networking opposition, and is being upgraded to provide the reliable speed and lossless transmission required by Fibre Channel-using devices.

Maybe it's just something specific to investors, I was at a conference for Brocade products I think it was in 2009 even, where they talked about FCoE among many other things and if memory serves they didn't expect much out of FCoE for several years so maybe it was management higher up that was setting the wrong expectations or something I don't know.

Then more recently I saw this article posted from slashdot which basically talks about the same thing.

Even today I am not sold of FCoE, I do like Fibre Channel as a protocol but don't see a big advantage at this point to running it over native Ethernet. These days people seem to be consolidating on fewer, larger systems, I would expect the people more serious about consolidation are using quad socket systems, and much much larger memory configurations (hundreds of gigs). You can power that quad socket system with hundreds of gigs of memory with a single dual port 8Gbps fibre channel HBA.Those that know about storage and random I/O understand more than anyone how much I/O it would really take to max out an 8Gbps Fibre channel card, your not likely to ever really manage to do it with a virtualization workload, even with most database workloads. And if you do you're probably running at a 1:1 ratio of storage arrays to servers.

The cost of the Fibre network is trivial at that point (assuming you have more than one server). I really like the latest HP blades because well you just get a ton of bandwidth options with them right out of the box, why stop with running everything over a measly single dual port 10Gbe NIC when you can have double the NICs, AND throw in a dual port Fibre adapter for not much more cash. Not only does this give more bandwidth, but more flexibility and traffic isolation as well(storage/network etc). On the blades at least it seems you can go even beyond that(more 10gig ports), I was reading in one of the spec sheets for the PCIe 10GbE cards that on the Proliant servers no more than two adapters are supported

NOTE: No more than two 10GbE I/O devices are supported in a single ProLiant server.

I suspect that NOTE may be out of date with the more recent Proliant systems that have been introduced, after all they are shipping a quad socket Intel Proliant blade with three dual port 10GbE devices on it from the get go. And I can't help but think the beast DL980 has enough PCI busses to handle a handful of 10GbE ports. The 10GbE flexfabric cards list the BL685c G7 as supported as well, meaning you can get at least six ports on that blade as well. So who knows.....

Do the math, the added cost of a dedicated fibre channel network really is nothing. Now if you happen to go out and chose the most complicated to manage fibre channel infrastructure along with the most complicated fibre channel storage array(s) then all bets are off. But just because there are really complicated things out there doesn't mean your forced to use them of course.

Another factor is staff I guess, if you have monkeys running your IT department maybe Fibre channel is not a good thing and you should stick to something like NFS, and you can secure your network by routing all of your VLANs through your firewall while your at it, because you know your firewall can keep up with your line rate gigabit switches right? riiight.

I'm not saying FCoE is dead, I think it'll get here eventually, I'm not holding my breath for it though, it's really more of a step back than a step forwards with present technology.

TechOps Guy: Nate

Tagged as: Comments Off
Comments (2) Trackbacks (1)
  1. Hey there Nate, I generally agree with all your points though I’m not too up on traditional FC since my company uses iSCSI… I’ve been waiting for several years to find out that I bought the wrong flavor of storage and wish I had FCOE but that hasn’t happened.

    I did recently read about this Intel release that made me think FCOE might finally start catching on:

    http://www.eweek.com/c/a/Enterprise-Networking/Intel-Eases-Data-Center-Complexity-with-Free-FCoE-Stack-366063/

  2. DCIG’s Interactive Buyer’s Guide (ibg.dcig.com) system shows that FCOE is only 18% adopted by midrange array storage vendors – indicating we have a long way to go (scroll to the bottom of this article) – http://www.dcig.com/2012/04/final-and-somewhat-random-thoughts-from-snw.html