Earlier today, Nicira publicly emerged as a company from stealth mode with more than just an idea, but with a product and several customers actually using it. While many find that approach old school, I like the fact that they are more than just PowerPoint slides and buzzword bingo press releases. I like that they waited to publicly announce the company until they had built a working product and actually sold it to some customers. I wish more companies would do that.
Granted, information about the company has been around for a while, including an article in the New York Times last fall describing how NTT, in the wake of the Tsunami disaster, has been able to effectively leverage Nicira to maintain availability in the midst of rolling data center blackouts. According to Nicira, other large service providers are also enamored with this technology, citing AT&T, eBay and Rackspace as customers as well. Nicira also cites a large enterprise customer, Fidelity, among those that have adopted its technology.
Why have these very large and well known service providers selected to work with Nicira? Simply put, because Nicira is helping them solve a very large, and fairly well known problem - network complexity in rapidly scaling, highly dynamic virtual environments. My colleague Jon Oltsik has defined this as Data Center Network Discontinuity. As organizations continue to consolidate data centers, drive increased use of server virtualization technology, and increase their ability to react more quickly to business needs, legacy network solutions will reach a breaking point. Something needs to change in order to drive new and sustainable growth. Organizations will need to create a virtual network platform to fully abstract the physical layer from the logical one, instead of an even bigger maze of individual boxes.
OpenFlow and Software Defined Networking hold a lot of promise in this regard. Many companies, including HP and IBM/NEC, are leveraging this technology and have recently made some big announcements, while other companies like Arista, BigSwitch, and Juniper have been pursuing their own implementations. Nicira hopes its model will take network virtualization to a whole new level. By placing the intelligence in the virtual switch and leveraging an external controller, Nicira hopes to virtualize (and commoditize) the underlying physical network.
By taking this approach, Nicira proves that it has no hardware agenda and therefore organizations do not have to rip and replace any equipment. It can be deployed in conjunction with existing technology from any vendor. As the customer list suggests, large service providers with cloud environments will receive the most benefit, but those enterprises that have committed to and deployed their own private clouds could take advantage of this technology as well, like Fidelity has done. As more enterprises consolidate data centers and mature their server virtualization environments, I would expect to see more enterprise logos pop up on its website, if the technology works as advertised with its initial customers.
You can read Bob's other blog entries at Data Center Continuum.