Is it Just Software Defined Networks (SDN)?
This is the question I continue to ask myself as I look back at my career at various companies in multiple industries. As I look back, I remind myself of the industry changing trends that we’ve gone through in past few decades: the rise (and fall) of the mainframe, the PC, numerous different networking protocols and technologies, and various standards that come and go. On top of all this I recall, dozens of system architectures and hundreds of programming languages. And these days … Open Source Software, Si-photonics, mega/giga/tera-bit interfaces, smart phones and tablets, big data and real time analytics, cloud computing, everything fully virtualized.
Let’s pause here to think about the game changers. The architectures, processes and ideas that once pushed industries forward seemed to eventually disappear into the next big thing. Distributed Object Technology (RFC), Loosely Coupled Technology and Architectures (SOA). Agile, or is it Dev/Ops? As you can see, there are major differences here. Each technology trend brings tremendous value and is of critical importance but, like so many of these examples there is that fundamental difference, that many of these trends evolve and merge into much bigger vision. It’s also present in how we view SDN and how we are including it in what we’re building at Cisco.
Once you take that step back and can separate “game-changing” from the “industry-shifting” movements, you can fundamentally break down why we believe that SDN is a piece of a larger puzzle. Software Defined Networks are a great game-changer likely to help many companies provide new services – it is definitely something we see as beneficial and are working on. However, when I dig into what we’re truly working on and the ripples that we (and a few of our customers) think this will have, we see market evolution. Something that affects not only how people build technology or products or scale and operate them, but something that makes people look at their business differently. It allows them to re-think revenue and business models. How people collaborate. It creates new business channels and models on top of that. That’s where we are. And as we talk to more service providers; we find that they think so too.
Let me share with you my perspective…
Two Fundamental “Platforms” and Underlying Complexity
The importance of the diversity of functionality and programming interfaces necessary to make networking hardware and software platforms work better together can’t be underestimated. But to make them really work better together we must start thinking multi-dimensionally. The need for real-time, duplex communication between both hardware and software and application development platforms needs to be pushed further. It’s absolutely necessary for this to happen as the intelligence in the network is far underutilized. But that’s not enough. How do the hardware and software platforms connect? How is the value delivered in a usable way to the market segments that need it? Programmability coupled with key protocols, APIs and new technologies enable real-time, fully duplex transfer of ‘state’ between the applications and Management Service
planes of the network. This isn’t only about separating and programming two planes (which is how SDN is defined largely today); it’s about full duplex access to all of the planes of the network.
You can only get this to work if the network programming interfaces (NPIs) are dynamic and capable of extracting data out of the network as well as programming features and state. The elements across and between the layers of the network need to be able to talk to each other in ways that allow them to signal application requests faster and with location-based information enabling new functionality to developers and integrated into development platforms. Real-time, full duplex interaction is the key to how these programmable interfaces must work with the application and the network and this is where SDN needs to get to.
I see a workflow based on the concept of a real-time feedback loop that includes data mined from the network, the transformation of that data to actual and usable information via analytics engines that can be consumed at multiple levels of infrastructure communicating via orchestration mechanisms to policy servers to create a unified policy (in the generic sense) and the programming of that policy into the network using an active set of NPIs. Policy here can be config, features, VDI, hypervisor, security profiles, content access …i.e we are referring to policy in the most general sense.
Imagine an environment that is constantly managing not just the state of the network but analyzing the applications network requirements and state and calculating policies that are programmed across every network plane. This vision reflects exactly what is already attempting to be built in Provider’s networks and is only realizable when the application developer’s information and ability to program state is multi-dimensional vs. uni-dimensional.
If we introduce this continuous feedback loop coupled with the multi-dimensional benefits it becomes the key that unlocks the real value that comes from SDN. Better and more intelligent applications can be created by integrating data derived from the network. The critical understanding is that multi-dimensional environments add additional elements to SDN. Looking at what data is the right data, the transformation and packaging of that into information that can be consumed and utilized is critical. Not everyone consumes technology the same way, and it’s rapidly evolving. Much of what we’re focusing on includes this in particular.
In order to innovate and scale into the future while also providing customers with investment protection we must expanding our thinking to include the data transformation, delivery, and consumption models as well as evolving architectures of existing platforms. Harnessing this kind of power for development will foster innovation and yield new services – but at what level? And how will we drive real business benefit versus just short term improvements?
Challenging the Current Business Model
I hear a lot of talk about the business problems that SDN will help address and you can read about a variety of use cases for SDN. Many use cases concentrate on extracting data and programming data (or information, once transformed), but they’re missing the real problem. SDN is about helping customers and users find ways to efficiently use their network and operational resources and increase revenue from services to start. If we base our offerings solely on the aspect of lowering infrastructure cost and increasing a couple of points on Total Cost of Ownership. , we change small things. Pennies in a jar, so to speak. Better and more lucrative business models are needed not only for providers but for enterprises as well. At Cisco, we know that there’s something better we can do for our customers, partners, and end-users.
The problems we see customers facing and the use cases on the market today quite emphatically demonstrate that the solution that we need to provide is bigger than just separating the control and forwarding planes in the network. This is a critical first step, but there needs to be more than just layer separations and abstractions.
Additionally, SDN is not solely about a single feature or a single network “function.” Most often “virtualization” is the capability that SDN is promised to bring. And is primarily applicable only in the Data Center. In my view its much more than that. The programmability that we have at our fingertips can be used in a multi-tenant data center BUT it isn’t limited to just that function. We can have full duplex programming of ephemeral state at all sorts of network perimeter points: hypervisor, DC security domains, Layer 3 VPN edge points, mobile and wireline subscriber termination points, secure VPN gateways, WLAN access points, CDN head-ends, provider peering points. Anywhere you can derive state – you’ll want to program a policy or feature or be able to modify the customer experience and that’s also where you’ll get the best data to analyze.
The Gold Mine
The data held in the network is the current untapped gold mine that has the ability to improve many things from real-time information, location based offerings to new service insertion points, intelligent applications that can re-route themselves based on network data and more. All of this leads to better user experiences and the potential monetization of these services. Data mining subscriber, session and application state only helps if we have this feedback loop between a policy engine and the network work together to mutual advantage.
Optimizing the network not only reduces cost by using available capacity, enabling new protection/restoration strategies and agile/flexible OSS performance service enablement capabilities but also opens up innovation in areas that have needed a lot of attention for a long time. These are primarily centered on breaking the shackles of current provisioning protocols like RADIUS, COPS, PCMM, GDOI, CAPWAP and mining protocols like NETFLOW, IPDR, as well as gateways.
My current mission working with our Cisco technical talent is about enabling both network optimization and service monetization to help customers bend back the cost curve and find value by increasing agility of service offering and improving experience. That’s today. For tomorrow, it needs to be around actual consumability, usability and smart, intuitive and usable data that delivers new business models based on abstracting network intelligence and presenting it to various existing application development environments.
Imagine having embedded in HTML5 the ability to optimize networks easier, faster, more effectively, and at much greater scale. Better usability and real-time visibility so that the focus becomes not on tasks that should be automated or deployments and scalability issues. This leaves more time to focus on strategy, planning, creating new business and monetization opportunities and actually delivering them to generate new revenue channels and real money versus just “value.” Value today is about TCO, optimization and bottom lines. But what about enablement and strategies for better business? What about revenue? Well THIS is the real challenge and the industry needs more time to work on all this. In the end, that’s how I define success for myself, our team, our business, and our industry at large. What should be clear is that in no way do I see SDN or programmable interfaces as a technology that commoditizes networking equipment. Instead, I see it unleashing all the potential we’ve built into these systems and augmenting the current internet.
Network information is power — power generated by data transformation done well — such as: on-demand and “flip-the-switch” or self-service experience levers, applications that “know” where you are and the re-routing of your application to the closest point of contact to get the information to you (and your friends) faster than before. This is a small subset of problems we’re solving today.
The multi-layered approach that I’m advocating is a bit like viewing a forest as an ecosystem. Walking into the woods and looking at only the bark of a single tree; only gives you a limited view of the health of the forest. One has to look at all elements that contribute to creating the forest. A forester must look at all these elements simultaneously, assess changes and inputs, history and emerging growth to understand and evaluate the overall health of the forest. This requiresanalysis that looks at not only a single aspect of the system but also how all the elements interact with each other.
Our view at Cisco; uses the ecosystem analogy of how we view the interaction of all the elements and variables on the Internet. The system allows the network to provide information/state to applications, enhance sessions or enable restoration scenarios in ways that were previously unachievable. The network view must be both centralized and distributed at the same time. A centralized view of the topology with real-time updates of the multi-layered network coupled with the existing distributed control plane gives the ability to “find” and “use” otherwise trapped capacity. Therefore, the foundation of the Internet built upon distributed algorithms doesn’t get reinvented instead it is augmented.
We can now discover and view the end-to-end performance, delay, jitter, etc. of the network and place bandwidth and services on optimal paths. Without distributed routing we lose the highest performance resiliency and protection/restoration; without the centralized view we lose the ability for an application developer to “write to the network” vs. control one node. The key is just this: SDN must work with the entire network, as a system and not be limited to a pairwise architecture.
By giving developers the ability to “see” and in real-time “get the weather report” of the network; they can enable service agility that allows them to build better and more intelligent applications. Session-aware applications work with every network layer and integrate with policy engines and a fluid network infrastructure that is in constant touch with those applications. This approach can drive operational costs down while laying the foundation for monetization and new business models when delivered in usable ways that are actually consumable by people building for the network layers.
A Development Community Working Together
Going back to the beginning of my post, I hope you now see the opportunity and value of both game-changers and industry shifts. When you allow yourself to take that step back you can see that what we’re thinking about is more than just SDN.
We want your businesses to be always-on and using network intelligence in ways we know are possible. We want proactive versus reactive. We want real time. We want it now and we want to change it all tomorrow. Programmable networking and enabling application development platforms with network intelligence runs strong within me. On a personal note; I’ve been working in the industry and inside Cisco to build the foundations and technologies that enables hardware and software platforms to work together. To be clear, this is not a product. It’s a solution. And you don’t have to rip out your existing network to enjoy the benefits, we will make it evolutionary. And Cisco wants to give you a solution that solves multiple real problems in new ways and allows for our customers, our partners, our users and developers to do things better, faster and more effectively as well as the way you want to do them. I’d love to hear your thoughts as well. Where do you see the future of networking?
I have much to discuss and I’ll be presenting Cisco’s viewpoint at the Open Networking Summit in Santa Clara this week. Join us in shaping this next shift – hear the presentation, meet my colleagues, and let’s continue to push our thinking further to enable what an intelligent network can deliver.