Monday, October 15, 2007

FCoE in high gear

The drive to craft Fibre Channel over Ethernet products is in high gear. Witness today's news that longtime card maker Emulex is teaming up with Cisco spin-out Nuova Systems to co-develop silicon.

The interesting bit here is that the pair already has working hardware under development testing in the lab (probably just an FPGA), expects to have qualification chips early next year and actually to be shipping products before the end of 2008. That's pretty darned fast given the T11 spec is not expected to be in draft form until April at the earliest, and the related IEEE 802.1au work may take even longer.

My take away is that everybody sees a real need here and the data center sector is in rare form putting aside competitive issues to make something happen. So who else out there wants to talk silicon for FCoE?

1 comment:

Anonymous said...

Who is "everybody" in "everybody sees a real need"? Does everybody include customers who likely haven't even heard about FCoE? Is everybody mean Cisco and Brocade who want to sell yet another gateway product to unify the data center? Does everybody include the InfiniBand camp who are trying to sell the InfinBand unified data center vision?

Emulex, Qlogic, and all of the other FC IHV have been diversifying their product suites for the past couple of years but still make most of their money off of Fibre Channel. FCIA continues to tout Fibre Channel has the stalwart of the storage fabric technologies and is out beating the drumbs for the imminent 8G transition and how FC will continue to evolve to even higher speeds.

Emulex and Qlogic jumping into the FCoE arena sounds more like an attempt to insure they are not locked out of any aspect of the FC market while reacting on bended knee to the big switch vendors who demand they produce products if they want to stay relevant.

FCoE has some benefits but the notion that it is time critical to the data center or to customers is absurd. Where is the customer demand for this technology? Where are the testimonials that customer data centers are just falling apart and only FCoE can save them? The industry is a long way aways from solving the unified fabric problem. Will it be Ethernet? Most likely. Will it require FCoE? Unclear. There are many storage paradigms in the market and while a gateway to FC storage is required for some amount of time, the long-term prognosis for FCoE is very unclear.