|By Lori MacVittie||
|September 20, 2013 09:15 AM EDT||
One of the most commonly cited use cases for SDN (the classical, architectural definition) centers on ensuring quality of service for applications, usually by adjusting bandwidth constraints and prioritization, sometimes dynamically based on the operating conditions present on the network.
In such a scenario the application magically informs the SDN controller of its bandwidth and service-level requirements and the controller adjusts the network and distributes the appropriate flow tables to the network fabric to support the application.
This is a great vision, but it is not without challenges.
The most significant obstacle is actually not getting the application to talk to the SDN controller. Northbound APIs could be used for this purpose, or some other API-based mechanism that is used to instruct the controller on application specific requirements. Let's not rat hole on that and assume that this is easily enough accomplished.
At this point the SDN controller has some requirements dictated by an application. Given the way in which an SDN controller distributes forwarding information to the network fabric, one has to ask how the SDN controller will represent the requirements of the application and, more importantly, how it will distribute those requirements.
Assuming a classical SDN architecture and the use of OpenFlow or a protocol similar in capability, the flow table in the network fabric will only be able to distinguish packets on a per-IP / port combination. Let's assume that's an accurate representation of the overall topology; that is, every application has a distinct IP / port combination. That means the SDN controller can, in fact, push flow table rules that are able to provision the appropriate bandwidth for those application flows as well enforce prioritization (if that's needed, too).
So far so good. You're thinking I'm barking up a pedantic tree or something, aren't here? Nope, here comes a significant problem starting with the question: How does the application define its need for bandwidth?
"Applications" today are comprised of a variety of functions and capabilities ranging from the delivery of simple text to dozens of images to embedded multi-media to video (and probably a few others I'm missing). The bandwidth needs of video is different from text is different from images is different for real-time messaging applications. Sensitivity to latency, throughput, bandwidth - these characteristics are peculiar to content-types, not the application itself (capabilities of the client-side network and device not withstanding, either). Given an application will varying - sometimes wildly - content types and requirements, should it simply request from the network the highest throughput and lowest latency required of all content being delivered? That's terribly inefficient.
HTTP is the new TCP
At the root of the problem is the reality that HTTP is the new TCP, with a significant percentage (62% in our research) of applications all using HTTP. A smaller percentage of those applications use port 8080 and port 443, but are still HTTP. In an increasingly API-enabled application world, the best chance we have to profile bandwidth needs for an "application" is at the URI level.
All the interesting application-layer stuff is going on above layer 7 (HTTP) or more precisely within layer 7, in the payload (and across multiple packets and flows, but that's a different discussion). To really define the specific bandwidth needs of an application you have to look at the content being delivered. In many cases that content-type can be deduced from clues in the URI (file extensions like JPG, PNG, CSS, etc...) or extracted from the HTTP header Content-Type, which spells it out. In either case, you must be able to inspect and evaluate data in the HTTP payload, not merely IP and TCP parameters.
The biggest problem is that the current SDN architectural model, which focuses heavily on packet and flow-based processing, does not have the depth of visibility necessary to properly distinguish content type within an application and thus apply routing and forwarding policies based on each content type's unique requirements. An application delivering both video (a plurality of video is delivered via HTTP today, and it's increasing rapidly) and text will either need to be optimized for one or the other, but not both. The same is true for images, and even for different delivery models (push, pull, real-time, static) of text-based information.
To do that you need visibility into the application, down to the payload in some cases. That's just not a capability that the classical SDN architecture today is able to provide, for a variety of reasons. Current SDN architectures assume visibility and action on L2-4 only. Unfortunately the data necessary is at and above L7.
Ultimately the answer to this conundrum is to include L7 capable data path elements in the SDN architecture. The standard L2-3 SDN fabric can then optimally route packets through the network based on general, application-oriented network requirements while allowing the L7 aware data path elements the ability to do what they do best: inspect, analyze, evaluate and even modify (optimize) application messages in order to optimally deliver data to the end-user.
Application awareness, as it's often referred to, is not enough. To really ensure the network - and thus SDN - is able to offer application-specific services in the network requires application fluency. And application fluency isn't something you find by peeking at packets from layer 2-4. You've got to go deeper - to layer 7 and beyond.
In his keynote at 18th Cloud Expo, Andrew Keys, Co-Founder of ConsenSys Enterprise, provided an overview of the evolution of the Internet and the Database and the future of their combination – the Blockchain. Andrew Keys is Co-Founder of ConsenSys Enterprise. He comes to ConsenSys Enterprise with capital markets, technology and entrepreneurial experience. Previously, he worked for UBS investment bank in equities analysis. Later, he was responsible for the creation and distribution of life sett...
Jun. 25, 2016 06:15 PM EDT Reads: 964
There are several IoTs: the Industrial Internet, Consumer Wearables, Wearables and Healthcare, Supply Chains, and the movement toward Smart Grids, Cities, Regions, and Nations. There are competing communications standards every step of the way, a bewildering array of sensors and devices, and an entire world of competing data analytics platforms. To some this appears to be chaos. In this power panel at @ThingsExpo, moderated by Conference Chair Roger Strukhoff, Bradley Holt, Developer Advocate a...
Jun. 25, 2016 05:00 PM EDT Reads: 644
The pace of innovation, vendor lock-in, production sustainability, cost-effectiveness, and managing risk… In his session at 18th Cloud Expo, Dan Choquette, Founder of RackN, discussed how CIOs are challenged finding the balance of finding the right tools, technology and operational model that serves the business the best. He also discussed how clouds, open source software and infrastructure solutions have benefits but also drawbacks and how workload and operational portability between vendors ...
Jun. 25, 2016 04:30 PM EDT Reads: 716
Digital Initiatives create new ways of conducting business, which drive the need for increasingly advanced security and regulatory compliance challenges with exponentially more damaging consequences. In the BMC and Forbes Insights Survey in 2016, 97% of executives said they expect a rise in data breach attempts in the next 12 months. Sixty percent said operations and security teams have only a general understanding of each other’s requirements, resulting in a “SecOps gap” leaving organizations u...
Jun. 25, 2016 03:00 PM EDT Reads: 953
Cognitive Computing is becoming the foundation for a new generation of solutions that have the potential to transform business. Unlike traditional approaches to building solutions, a cognitive computing approach allows the data to help determine the way applications are designed. This contrasts with conventional software development that begins with defining logic based on the current way a business operates. In her session at 18th Cloud Expo, Judith S. Hurwitz, President and CEO of Hurwitz & ...
Jun. 25, 2016 03:00 PM EDT Reads: 1,503
In his general session at 18th Cloud Expo, Lee Atchison, Principal Cloud Architect and Advocate at New Relic, discussed cloud as a ‘better data center’ and how it adds new capacity (faster) and improves application availability (redundancy). The cloud is a ‘Dynamic Tool for Dynamic Apps’ and resource allocation is an integral part of your application architecture, so use only the resources you need and allocate /de-allocate resources on the fly.
Jun. 25, 2016 02:15 PM EDT Reads: 997
"A lot of times people will come to us and have a very diverse set of requirements or very customized need and we'll help them to implement it in a fashion that you can't just buy off of the shelf," explained Nick Rose, CTO of Enzu, in this SYS-CON.tv interview at 18th Cloud Expo, held June 7-9, 2016, at the Javits Center in New York City, NY.
Jun. 25, 2016 02:00 PM EDT Reads: 959
A strange thing is happening along the way to the Internet of Things, namely far too many devices to work with and manage. It has become clear that we'll need much higher efficiency user experiences that can allow us to more easily and scalably work with the thousands of devices that will soon be in each of our lives. Enter the conversational interface revolution, combining bots we can literally talk with, gesture to, and even direct with our thoughts, with embedded artificial intelligence, wh...
Jun. 25, 2016 01:45 PM EDT Reads: 857
It's easy to assume that your app will run on a fast and reliable network. The reality for your app's users, though, is often a slow, unreliable network with spotty coverage. What happens when the network doesn't work, or when the device is in airplane mode? You get unhappy, frustrated users. An offline-first app is an app that works, without error, when there is no network connection. In his session at 18th Cloud Expo, Bradley Holt, a Developer Advocate with IBM Cloud Data Services, discussed...
Jun. 25, 2016 01:30 PM EDT Reads: 718
19th Cloud Expo, taking place November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA, will feature technical sessions from a rock star conference faculty and the leading industry players in the world. Cloud computing is now being embraced by a majority of enterprises of all sizes. Yesterday's debate about public vs. private has transformed into the reality of hybrid cloud: a recent survey shows that 74% of enterprises have a hybrid cloud strategy. Meanwhile, 94% of enterpri...
Jun. 25, 2016 01:15 PM EDT Reads: 1,190
What does it look like when you have access to cloud infrastructure and platform under the same roof? Let’s talk about the different layers of Technology as a Service: who cares, what runs where, and how does it all fit together. In his session at 18th Cloud Expo, Phil Jackson, Lead Technology Evangelist at SoftLayer, an IBM company, spoke about the picture being painted by IBM Cloud and how the tools being crafted can help fill the gaps in your IT infrastructure.
Jun. 25, 2016 12:00 PM EDT Reads: 551
SYS-CON Events announced today that Bsquare has been named “Silver Sponsor” of SYS-CON's @ThingsExpo, which will take place on November 1–3, 2016, at the Santa Clara Convention Center in Santa Clara, CA. For more than two decades, Bsquare has helped its customers extract business value from a broad array of physical assets by making them intelligent, connecting them, and using the data they generate to optimize business processes.
Jun. 25, 2016 11:45 AM EDT Reads: 1,150
"SpeedyCloud's specialty lies in providing cloud services - we provide IaaS for Internet and enterprises companies," explained Hao Yu, CEO and co-founder of SpeedyCloud, in this SYS-CON.tv interview at 18th Cloud Expo, held June 7-9, 2016, at the Javits Center in New York City, NY.
Jun. 25, 2016 11:15 AM EDT Reads: 714
Internet of @ThingsExpo, taking place November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA, is co-located with 19th Cloud Expo and will feature technical sessions from a rock star conference faculty and the leading industry players in the world. The Internet of Things (IoT) is the most profound change in personal and enterprise IT since the creation of the Worldwide Web more than 20 years ago. All major researchers estimate there will be tens of billions devices - comp...
Jun. 25, 2016 11:15 AM EDT Reads: 1,152
Machine Learning helps make complex systems more efficient. By applying advanced Machine Learning techniques such as Cognitive Fingerprinting, wind project operators can utilize these tools to learn from collected data, detect regular patterns, and optimize their own operations. In his session at 18th Cloud Expo, Stuart Gillen, Director of Business Development at SparkCognition, discussed how research has demonstrated the value of Machine Learning in delivering next generation analytics to imp...
Jun. 25, 2016 11:00 AM EDT Reads: 466
There is little doubt that Big Data solutions will have an increasing role in the Enterprise IT mainstream over time. Big Data at Cloud Expo - to be held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA - has announced its Call for Papers is open. Cloud computing is being adopted in one form or another by 94% of enterprises today. Tens of billions of new devices are being connected to The Internet of Things. And Big Data is driving this bus. An exponential increase is...
Jun. 25, 2016 11:00 AM EDT Reads: 1,274
The 19th International Cloud Expo has announced that its Call for Papers is open. Cloud Expo, to be held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA, brings together Cloud Computing, Big Data, Internet of Things, DevOps, Digital Transformation, Microservices and WebRTC to one location. With cloud computing driving a higher percentage of enterprise IT budgets every year, it becomes increasingly important to plant your flag in this fast-expanding business opportuni...
Jun. 25, 2016 10:30 AM EDT Reads: 1,217
Creating replica copies to tolerate a certain number of failures is easy, but very expensive at cloud-scale. Conventional RAID has lower overhead, but it is limited in the number of failures it can tolerate. And the management is like herding cats (overseeing capacity, rebuilds, migrations, and degraded performance). Download Slide Deck: ▸ Here In his general session at 18th Cloud Expo, Scott Cleland, Senior Director of Product Marketing for the HGST Cloud Infrastructure Business Unit, discusse...
Jun. 25, 2016 10:30 AM EDT Reads: 810
Cloud computing is being adopted in one form or another by 94% of enterprises today. Tens of billions of new devices are being connected to The Internet of Things. And Big Data is driving this bus. An exponential increase is expected in the amount of information being processed, managed, analyzed, and acted upon by enterprise IT. This amazing is not part of some distant future - it is happening today. One report shows a 650% increase in enterprise data by 2020. Other estimates are even higher....
Jun. 25, 2016 10:15 AM EDT Reads: 1,211
The cloud market growth today is largely in public clouds. While there is a lot of spend in IT departments in virtualization, these aren’t yet translating into a true “cloud” experience within the enterprise. What is stopping the growth of the “private cloud” market? In his general session at 18th Cloud Expo, Nara Rajagopalan, CEO of Accelerite, explored the challenges in deploying, managing, and getting adoption for a private cloud within an enterprise. What are the key differences between wh...
Jun. 25, 2016 10:00 AM EDT Reads: 653