The continuing evolution of Nicira Networks has been intriguing to watch. At one point, not so long ago, many speculated on what Nicira, then still in a teasing stealth mode, might be developing behind the scenes. We now know that it was building its Network Virtualization Platform (NVP), and we’re beginning to learn about how the company’s early customers are deploying it.
Back in Nicira’s pre-launch days, the line between OpenFlow and software defined networking (SDN) was blurrier than it is today. From the outset, though, Nicira was among the vendors that sought to provide clarity on OpenFlow’s role in the SDN hierarchy. At the time — partly because the company was communicating in stealthy coyness — it didn’t always feel like clarity, but the message was there, nonetheless.
Not the Real Story
Virtualization and the cloud is the most profound change in information technology since client-server and the web overtook mainframes and mini computers. We believe the full promise of virtualization and the cloud can only be fully realized when the network enables rather than hinders this movement. That is why it needs to be virtualized.
Oh, by the way, OpenFlow is a really small part of the story. If people think the big shift in networking is simply about OpenFlow, well, they don’t get it.
A few months before Cohen joined the company, Nicira’s CTO Martin Casado had played down OpenFlow’s role in the company’s conception of SDN. We understand now where Nicira was going, but at the time, when OpenFlow and SDN were invariably conjoined and seemingly inseparable in industry discourse, it might not have seemed as obvious.
Don’t Get Hung Up
That said, a compelling early statement on OpenFlow’s relatively modest role in SDN was delivered in a presentation by Scott Shenker, Nicira’s co-founder and chief scientist (as well as a professor of electrical engineering in the University of California at Berkeley’s Computer Science Department). I’ve written previously about Shenker’s presentation, “The Future of Networking, and the Past of Protocols,” but here I would just like to quote his comments on OpenFlow:
“OpenFlow is one possible solution (as a configuration mechanism); it’s clearly not the right solution. I mean, it’s a very good solution for now, but there’s nothing that says this is fundamentally the right answer. Think of OpenFlow as x86 instruction set. Is the x86 instruction set correct? Is it the right answer? No, It’s good enough for what we use it for. So why bother changing it? That’s what OpenFlow is. It’s the instruction set we happen to use, but let’s not get hung up on it.”
I still think too many industry types are “hung up” on OpenFlow, and perhaps not focused enough on the controller and above, where the applications will overwhelmingly define the value that SDN delivers.
As an open protocol that facilitates physical separation of the control and data-forwarding planes, OpenFlow has a role to play in SDN. Nonetheless, other mechanisms and protocols can play that role, too, and what really counts can be found at higher altitudes of the SDN value chain.
In Nicira’s recently announced customer deployments, OpenFlow has played relatively minor supporting roles. Last week, for instance, Nicira announced at the OpenStack Design Summit & Conference that its Network Virtualization Platform (NVP) has been deployed at Rackspace in conjunction with OpenStack’s Quantum networking project. The goal at Rackspace was to automate network services independent of data-center network hardware in a bid to improve operational simplicity and to reduce the cost of managing large, multi-tenant clouds.
According to Brad McConnell, principal architect at Rackpspace, Quantum, Open vSwitch, and OpenFlow all were ingredients in the deployment. Quantum was used as the standardized API to describe network connectivity, and OpenFlow served as the underlying protocol that configured and managed Open vSwitch within hypervisors.
A week earlier, Nicira announced that cloud-service provider DreamHost would deploy its NVP to reduce costs and accelerate service delivery in its OpenStack datacenter. In the press release, the following quote is attributed to Carl Perry, DreamHost’s cloud architect:
“Nicira’s NVP software enables truly massive leaps in automation and efficiency. NVP decouples network services from hardware, providing unique flexibility for both DreamHost and our customers. By sidestepping the old network paradigm, DreamHost can rapidly build powerful features for our cloud. Network virtualization is a critical component necessary for architecting the next-generation public cloud services. Nicira’s plug-in technology, coupled with the open source Ceph and OpenStack software, is a technically sound recipe for offering our customers real infrastructure-as-a-service.”
You will notice that OpenFlow is not mentioned by Nicira in the press releases detailing NVP deployments at DreamHost and Rackspace. While OpenFlow is present at both deployments, Nicira correctly describes its role as a lesser detail on a bigger canvas.
At DreamHost, for example, NVP uses OpenFlow for communication between the controller and Open vSwitch, but Nicira has acknowledged that other protocols, including SNMP, could have performed a similar function.
Reflecting on these deployments, I am reminded of Casado’s earlier statement: “Open Flow is about as exciting as USB.”
For a long time now, Nicira has eschewed the fetishization of OpenFlow. Instead, it has focused on the bigger-picture value propositions associated with network virtualization and programmable networks. If it continues to do so, it likely will draw more customers to NVP.