NEC has delivered a new type of experimental switch to European research institutions based on the OpenFlow packet routing system. The idea behind the OpenFlow effort is that today’s network needs to be smarter and more flexible in order to handle and efficiently deliver more information. To do that, the fundamental idea is to separate the packet switching mechanisms and control functions. Users can freely develop and operate control middleware independently of the switching mechanism.
For example, in a conventional router, a piece of silicon tracks when a packet arrives and then consults a routing table to send it on its way in the most efficient manner. In an OpenFlow switch, the acts of receiving and determining where to send the packet are no longer performed inside the same box. As the Internet gets more end points and more traffic, the routing tables get longer, and it becomes more time-consuming to send on packets, creating bottlenecks. The goal of the OpenFlow initiative is to create an overlay mechanism that directs where the packets go. This sits on top of the network of routers and switches that are used to actually move the packets. For more on this, check out our video of Nick McKeown, professor of Electrical Engineering and Computer Science at Stanford University speaking on OpenFlow at our Structure 2010 conference last June.
NEC has provided several Programmable Flow Switches to entities in Europe that will be used to build the European OpenFlow infrastructure to aid network experiments and application development among the European R&D community. NEC is providing switches to two projects. The first, the OpenFlow in Europe: Linking Infrastructure and Applications (OFELIA) project, will set up a test bed facility based on OpenFlow Technology for experiments. The second, the Change Project, aims to build flow-processing network platforms. As OpenFlow experimentation progresses, it will change the fundamental architecture of the Internet. It’s only a question of how long that will take.
Related GigaOM Pro research (sub req’d):
- For Open Cloud Computing Look Inside Your Data Center
- Defining Internal Cloud Options: From Appistry to VMware
- If We Compute in the Cloud, We Need a Network Fabric