In a recent post on Miles Davis’ blog he reports the latest statistics of the wireless network of the Stanford Computer Science Department. The numbers are interesting to say the least. The Laptop market is split equally between Mac OS X and Windows. Both however are crushed by the iPhone which is also the fastest growing segment. Android which had not yet made a dent on last month’s statistics is slowly creeping up.
Mac OS X
For complete statistics visit his blog post here. Stanford is far from typical network. However it sometimes is a good leading indicator of things to come. That phones are becoming a major category on wireless networks (and eventually the majority) seems like a safe bet. How quickly it happened is amazing though. It has been 2.5 years since the iPhone was introduced).
We just finished the OpenFlow Demo at the GENI Engineering Conference, and it was amazing. We showed our new OpenFlow protocol running on switches from Cisco, Juniper, HP and NEC. Our experimental network stretched half way around the globe from Stanford to Tokyo via New York. It used fibers from Internet2, CalRen and JGN2plus.
Over this network we showed how we can move around a running game server from one physical host to another without the game even getting interrupted. We demonstrated how you can route a network connection with a simple drag and drop interface (e.g. a TCP flow inside Stanford going via Tokyo and Houston). We even sent a running game server to Tokyo from Stanford, without losing the connection.
Press coverage of the demo included articles English, Japanese, Swedish and Spanish. The OpenFlow web site recieved a few thousand hits, with visitors from every major company in the networking space. All this was made possible by about 40 people from Stanford, Internet2, Cisco, Juniper, HP and NEC had been working on this for months.
As a result of this, OpenFlow is building momentum. NEC announced during the conference support for OpenFlow in their product, and more announcements will follow. By mid next year we are hoping to have pilot deployments at 6-10 universities, and I would hope we will see commercial deployments in that time frame as well. All in all a huge step forward for OpenFlow.
Congratulations to Neda, Yashar, Monia, Nick and Geoff for their best paper award at the Internet Measurement Conference. Their paper Experimental Study of Router Buffer Sizing tests out recent results on buffer requirements of high-speed routers that serve highly aggregated traffic. Amongst other things it verifies the C/sqrt(n) result from my thesis as well as my former office mate Yashar Ganjali’s work on very small buffers and find that they hold well.
It is great to see this work getting recognized, but what is even more encouraging is that two router vendors privately confirmed to me that the next generation of some of their products will have substantially smaller buffers. This not only reduces power consumption, but also means that we are less likely to see latency spike whenever peering points or core links are congested.
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 OpenF
low 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:
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.
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.
Currently the main thing I am working on at Stanford is the OpenFlow Standard. OpenFlow basically allows a software that is running on a commodity PC, to remotely control the flow table and thus the entire routing functionality of a switch (see the excellent white paper). This is a very interesting application for networking, as it allows researchers or start-ups to build new technologies in this space. Think of it as the Facebook API for the networking world. If it takes off, it will lead to a lot of innovation in this space.
Last week we presented a demo of using OpenFlow to migrate game servers in real time (and while people play games on them) across different IP subnets at SIGCOMM 2008. The demo received rave reviews and won the Best Demo Award by a wide margin. I will post more about the Demo and other OpenFlow news on the OpenFlow Blog soon. This week we also held the first OpenFlow tutorial at HOT Interconnects at Stanford (organized by our own John Lockwood this year – great work John!). It was well received and we learned some good lessons how we can improve it in the future.
The 2008 MIT Technology Review list of top innovators under 35 came out today, Sundar Iyer and Seth Hallem, both fellow Stanford Ph.D. students, made the list this year, and I am very happy for both of them. Sundar has had a profound impact on how buffers for high-speed routers work, and Seth has changed what is considered best practice for code checking. Both have also founded great start-up companies in the process.
Congratulations Sundar and Seth!
Update: As Sundar points out, Stanford CS faculty Andrew Ng and former Ph.D. student Meridith Ringel Morris also made the list. Congratulations here as well!
I am happy to announce that this week I have joined Stanford University as a Consulting Assistant Professor. This may come as a suprise to some people, as I am not exactly your typical academic. Those people would be correct, my job here is not primarily about teaching. The main reason I am joining Stanford is OpenFlow, and it is one of the most exciting technologies I have seen in networking for a long time.
OpenFlow is exciting in two ways. First, it allows you to run new protocols and algorithms on production networks. Before OpenFlow this was very hard, as modern routers have no API that gives access to this low level functionality. Second, it allows you to make centralized yet fine grain routing decisions. This has huge advantages in some areas such as security, data centers or mobility.