OpenFlow

The project that currently takes up the majority of my time at Stanford is OpenFlow. OpenFlow is a new protocol that we specified and that vendors are now adding to their routers and switches. What OpenFlow allows you to do is remotely control the behavior of a switch from an controller software that runs on a standard server. This has two major advantages:

  1. You can now write your own control software and try out new switch functionality at full line rates. In the past this has been difficult as all major router and switch vendors lack APIs and are typically closed platforms.
  2. If you use a centralized controller now has a unified view of the network. For some applications such as mobility management, virtualized data canters or security this allows you to do things that previously would have been very difficult or impossible.

OpenFlow originally came out of Martin Casado‘s work on Ethane and SANE, and was developed into a full specification by Nick McKeown‘s group with the participation of other researchers. Today we have implementations of OpenFlow in software as well as on the NetFPGA hardware.

However what really excites me is that we are starting to see commercial switches implementing OpenFlow. At SIGCOMM 2008 we demonstrated it running on HP ProCurve 5400 switches and a Cisco Catalyst 6k. For an upcoming demo we will add NEC and Juniper hardware. All of these are prototypes and not yet commercially available. But at this point it looks increasingly likely that next year we will have OpenFlow enabled switches available from major hardware vendors.

On the other side, there is a growing demand for OpenFlow hardware. A quick analysis of recent SIGCOMM papers suggests that in the order of 30% of them could implement the novel techniques described in the paper with OpenFlow. While this is a single data point, it is safe to say that a fairly substantial fraction of networkign innovation that today never moves beyond the simulation or proof of concept stage, could be implemented as production neworks using OpenFlow.

Together all of this creates momentum. Just over the last few weeks we found interest in potential OpenFlow projects from a mobile carrier, a major data center operator and a consortium of universities. Combining this demand with available products has the potential to suddenly create a burst of innovation at the network layer.

If you are interested in following what is happening with OpenFlow, please have a look at the OpenFlow Blog. The OpenFlow Team at Stanford and myself are posting updates there regularily.

Leave a Comment

Your email address will not be published. Required fields are marked *