SAN JOSE, Calif. – The OpenFlow movement has been casting a shadow in Silicon Valley where it was born. But the reality is that the move to software-defined networking (SDN) remains in its infancy and relatively immature for use in grown up markets.
OpenFlow got its start at Stanford University in a research program geared to radically simplify the process of configuring and managing today’s complex multi-vendor, multi-protocol networks. Its aim was to let any programmer issue commands in high-level languages to servers that would control networks.
[Get a 10% discount on ARM TechCon 2012 conference passes by using promo code EDIT. Click here to learn about the show and register.]
This vision generated a tsunami of interest particularly from Google, one of OpenFlow’s biggest proponents. Simplification is a top priority for the Internet giant as it wrestles with some of the world’s largest and most secretive global nets.
OpenFlow also has its skeptics, especially among the world’s biggest communications vendors. If the OpenFlow vision is realized, tomorrow’s servers could handle many of the jobs run today on their big routers and switches.
In an OpenFlow world, complex ASICs used by comms gear makers like Alcatel-Lucent, Ericsson, Cisco, Huawei, Juniper and others could shrink to simpler merchant chips. Their resulting routers and switches could collapse to commodity status like the servers that would control them.
But a closer look at OpenFlow shows it is little more than a skeleton that cannot yet handle the wealth of functions running on today’s networks. What’s more, even proponents say some of the early implementations of OpenFlow aren’t fully compatible given the spec’s immaturity.
But like everything else in Silicon Valley, OpenFlow is changing rapidly. The Open Networking Foundation (ONF) that manages OpenFlow announced plans this summer for four new working groups that aim to help flesh out the technology.
In a short term there will be thousands of people that will argue that there are thousands of reasons why OpenFlow can't happen...some be real, some will be invented to protect their businesses...but in a long term simplicity in hardware and protocols might prevail...we have seen this movie played out historically several times in various industries...Kris
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.