The Software Revolution Is Coming

STANFORD, Calif. -- One day, Nikhil Handigol got the idea for trying a different kind of load balancing. Normally, load balancers direct traffic to the lightest-loaded server, but they have no idea how congested the path to that server is. Handigol wondered if he could improve performance by taking the path into account.

Ideas like that can be a dime a dozen, but Handigol, a graduate student at Stanford University , got to see his come to life, first on Stanford's network, then nationwide on the GENI test network.

"The point here is: For the first time I've seen, a graduate student was able to take an idea and run it on a national network," said Nick McKeown, the Stanford professor behind the creation of the OpenFlow protocol.

To McKeown, who was speaking at the Open Networking Summit Tuesday, that's part of the value of software-defined networking and of OpenFlow in particular. They open up DIY possibilities that, in turn, could spark changes in the networking business. But like any movement that promises big change, software-defined networking first has to convince a lot of people to change the way they're thinking.

That was a major theme at the Summit, a three-day event where 400 attendees -- including about 50 from Cisco Systems Inc. (Nasdaq: CSCO), according to organizers -- packed into one of Stanford's most modern buildings to rub shoulders with OpenFlow's elite and to discuss the long-term future of networks.

OpenFlow, a protocol that lets operators reprogram a network's control plane, has been getting lots of attention. But it's just one corner of software-defined networking (SDN) that, in general terms, is about turning the network into a programmable entity.

The concept of software-defined networking has been around for a very long time, but it's suddenly become hip. That's partly because it could be an avenue to reawaken the startup-building machine in networking, continuing the pattern set by OpenFlow startups Big Switch Networks and Nicira Networks Inc. Some also see the potential for new business models in companies old and new. Consulting, for instance -- companies could use SDN expertise to execute some of the customized networking cases that operators dream up.

SDN could also lead to a network that's easier and safer to tweak, opening myriad pathways of innovation; think of Handigol's experiment as the SDN equivalent of a smartphone app. The innovative potential is already playing out with OpenFlow, which has made tremendous progress in the past two years not through standards-pushing, but in that goofy open-source way of letting anyone play around with the technology.

"It all happened through the broader community and not some standards effort," said Martin Casado, a founder of Nicira, in his Summit kickoff speech.

But beyond the business angles, software-defined networking is part of a bigger issue: that unlike computer science, networking has never become a discipline that's been boiled down to some fundamental principles.

The abstract truth
It might seem like a trivial distinction, but in a Tuesday morning talk, researcher Scott Shenker of the University of California at Berkeley made a convincing case that networking's future lies in developing a software-like attitude. And that should scare a lot of networking experts, not to mention companies.

In software, he said, layers upon layers of abstraction have been built up, so that tough problems can be defined and solved in simple terms. That's led to software being boiled down to foundational principles -- provable cases that form the basis for the field.

Networking doesn't have that. It's got abstraction of data forwarding -- that's the seven-layer OSI stack we're all familiar with. But there's no such simplification in the control plane.

So, in a sense, networking "is an utter academic failure," Shenker said. "We built an artifact. We did not build a discipline." And instead of fundamental principles to pass on, networking professors teach "a big bag of protocols."

The problem isn't only that networking is complex; it's that the people mastering the complexity are still the ones who get rewarded, Shenker said. To argue why that's bad, he used the analogy of the personal computer: The person you want to have designing the interface is the one who always hated typing DOS commands.

Networking needs to divide and conquer its functions the way software has, Shenker said. That means developing grand abstractions -- one object that simply represents the state of the network, for example, rather than thinking of different nodes having their own states. By dividing the problem, it becomes possible to tackle bigger problems.

New worlds
But these abstractions mean adding elements of centralized control to the network, and that would be a major change for every vendor in the business. "This spells the end for distributed protocols," Shenker said.

The transition could also cause trouble for the people in networking, because software has developed a different mode of thinking, where standards aren't so important and where complexity is meant not to be mastered, but to be obscured.

The process is going to take years, but the advocates of software-defined networking think it's necessary and even inevitable. "It's a software-oriented culture that's going to rule our field," Shenker said.

— Craig Matsumoto, West Coast Editor, Light Reading

Page 1 / 2   >   >>
Pete Baldwin 12/5/2012 | 4:50:54 PM
re: The Software Revolution Is Coming

So, what do we think here? Is software-defined networking the long-term future of the industry, or just an academics' dream?

Pete Baldwin 12/5/2012 | 4:50:53 PM
re: The Software Revolution Is Coming

btw -- anyone else find it interesting that Cisco sent 50 people to an OpenFlow conference?

Pete Baldwin 12/5/2012 | 4:50:53 PM
re: The Software Revolution Is Coming

You're taking the term too literally. Yeah, the protocols are in software, but the operator doesn't get to change them. There's a lot that you're not allowed to do with your network. SDN aims to free that up -- to unlock the network, in a sense.

About standards -- OpenFlow is trying hard to not be one, actually. Yes, there'll be a base set of specifications and definitions. Call that a standard if you want. But beyond that, the Open Networking Foundation wants to keep things in a more open-source mode, if I understand correctly. (Actually, maybe I should write that up as a separate story.) 

What they're trying to avoid is the standards-body process of honing every last detail down to a consensus. They want to be more like the mobile apps world: Here's the platform, go do whatever you want with it. You might think there are problems with that (the multiple-vendor problem that you mention, for instance) -- and that's fine. I really don't know if this approach will pay off or not.

To your final paragraph -- good points. It will be interesting to see how viable a third-party software industry would be in SDN. Separately, I think a lot of people are hoping that those hardware optimizations go away -- i.e., that something more commodity-looking starts to replace the switches and routers of today, so that your reference to the PC model would become reality. That would be a long way off, of course.

NetworkOptimizer 12/5/2012 | 4:50:53 PM
re: The Software Revolution Is Coming

To take Larry Ellison's rant on Cloud computing (Youtube it), what do you mean software defined networking: All the networking protocols run in software. Hardware is used only to optimise certain functionality (either fast data path routing, session actions, lookup, some security). Everything is written in software. Infact software is what makes the exisiting networking products useful.

Having got that out, I think moving away from standards would be good. But, it would  only work for green field, one vendor solutions. OpenFlow is still a standard with specifications. Whenever you need to deal with multiple vendors you will always need standardization (even though I am not in favor of the current standards process, which is more political rather than working towards a solution). And in networking you will always deal with multiple vendors (It's not just an app on the user's phone).

Concept of a programmable network is good. Currently that programming is static using CLI/SNMP etc. Making the system dynamically programmable will definitely improve the flexibility. Instead of vendor's software configuring all the hardware components you could have 3rd party software running on a different server/appliance manipulating the hardware components (IO/fabric/ASIC/backplane). But there is always performance hit for these solutions. Unless all the network equipments run on the off the shelf products with well-known/public internal details (like a PC), a 3rd party writing a software on a different hardware will always be inefficient. There are so many intricate details of the hardware that is used for optimizing the processing, and all of them might not be exposed using APIs.




Pete Baldwin 12/5/2012 | 4:50:52 PM
re: The Software Revolution Is Coming

Thanks, NetworkOptimizer - a story like this one cries out for a devil's advocate opinion, so I'm glad for the input.

I do like your picture of the future ecosystem. It's probably going to be a long-long-term future. But I'd bet there are people at all these companies that have been expecting this transition for a long time -- and, at least for now, everyone else has to actually listen to them!  :)

NetworkOptimizer 12/5/2012 | 4:50:52 PM
re: The Software Revolution Is Coming

I was just being a devil's advocate. I tried using the OpenvSwitch and am exploring different applications on it, but this is too early (or I don't have enough contacts in the service provider industry to know that they are already bought into it).

One more aspect of this is that it would drive the router/switches/load balancers into PC style market. What I mean by that is there will be one or two (CISCO/HP/DELL) or some chinese vendor (Huawei) who optimize the supply chain and use volume pricing to drive any other hardware networking company out of the market.

The eco-system would be built such a way that you have hardware from a few companies and OS from few (Microsoft/Linux => Linux + Open Flow) and applications from everyone else. That would definetly revolutionize the industry. It will cannibalize some companies, but provides opportunities for others.

New software applications will be provided by ALU/Ericsson/Juniper/Riverbed/F5/Brocade/Aruba/Citrix(Netscalar)/Checkpoint/fortinet/netgear/palo alto/sonicwall or their replacements.


raid 12/5/2012 | 4:50:51 PM
re: The Software Revolution Is Coming

Continuing the PC analogy, The 800lb gorilla in the merchant switching silicon is Broadcom. It has a central role to play in the transition.

PC-World                    Switch-Analogy                     Components


Intel                           Broadcom                            Chipsets

Dell/HP/IBM                 Dell/HP/IBM                         Systems

MSoft / OpenSource      Start-up/Broadcom-Partner    Platform Software

many                          many                                  App developers

The apps consume entire industries -  l2/l3 datacenter fabric, firewalls, load balancers, network security, application accelerators and wan optimization!

Dell/HP/IBM are the common links in the supply-chain for both PC and switch platforms. The assumption here is that the datacenter will converge and the server, storage and network hardware platforms will all be consolidated together as hardware commodities.

Sorry - I could'nt find a good place for cisco/juniper in the datacenter. They can play in the app space but their current business model will get battered in that scenario.






desiEngineer 12/5/2012 | 4:50:50 PM
re: The Software Revolution Is Coming

I remember the cute notion of running a JVM on your network processor so anyone could download the "appropriate" software and have a configurable network element.

OK, I'll admit that networking is moving so fast that we hardly have time to do the science that should come before the engineering.  But there's gold in them thar hills, so we (engineers) skip the abstract stuff.

I think the challenge for academia as described by Scott Shenker is the right one: they need to run slightly ahead of us, with an academic basis for networking, rather than teaching what the engineers built, which may work, but is hardly scientific discipline, and usually not even worthy of mention.

MPLS-TP is a case in point.  Please don't teach it in schools.


OldPOTS 12/5/2012 | 4:50:50 PM
re: The Software Revolution Is Coming

'This spells the end for distributed protocols'

Anyone remember PNNI?

Guaranteed delivery routing and re-route at the level path subscribed.



paolo.franzoi 12/5/2012 | 4:50:49 PM
re: The Software Revolution Is Coming


I managed my PNNI with my SS#7.







Page 1 / 2   >   >>
Sign In