Welcome!

@CloudExpo Authors: Carmen Gonzalez, Scott Millis, Kalyan Ramanathan, Pat Romanski, Liz McMillan

Related Topics: SDN Journal, Microservices Expo, Containers Expo Blog, Agile Computing, @CloudExpo, @BigDataExpo

SDN Journal: Blog Feed Post

Bandwidth, Bandwidth, Bandwidth!

To really provision bandwidth efficiently you have to get inside the application

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.

http-the-new-tcp-f5All 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.

Read the original blog entry...

More Stories By Lori MacVittie

Lori MacVittie is responsible for education and evangelism of application services available across F5’s entire product suite. Her role includes authorship of technical materials and participation in a number of community-based forums and industry standards organizations, among other efforts. MacVittie has extensive programming experience as an application architect, as well as network and systems development and administration expertise. Prior to joining F5, MacVittie was an award-winning Senior Technology Editor at Network Computing Magazine, where she conducted product research and evaluation focused on integration with application and network architectures, and authored articles on a variety of topics aimed at IT professionals. Her most recent area of focus included SOA-related products and architectures. She holds a B.S. in Information and Computing Science from the University of Wisconsin at Green Bay, and an M.S. in Computer Science from Nova Southeastern University.

@CloudExpo Stories
@DevOpsSummit taking place June 6-8, 2017 at Javits Center, New York City, is co-located with the 20th International Cloud Expo and will feature technical sessions from a rock star conference faculty and the leading industry players in the world. @DevOpsSummit at Cloud Expo New York Call for Papers is now open.
Predictive analytics tools monitor, report, and troubleshoot in order to make proactive decisions about the health, performance, and utilization of storage. Most enterprises combine cloud and on-premise storage, resulting in blended environments of physical, virtual, cloud, and other platforms, which justifies more sophisticated storage analytics. In his session at 18th Cloud Expo, Peter McCallum, Vice President of Datacenter Solutions at FalconStor, discussed using predictive analytics to mon...
"We are an all-flash array storage provider but our focus has been on VM-aware storage specifically for virtualized applications," stated Dhiraj Sehgal of Tintri in this SYS-CON.tv interview at 19th Cloud Expo, held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA.
Today we can collect lots and lots of performance data. We build beautiful dashboards and even have fancy query languages to access and transform the data. Still performance data is a secret language only a couple of people understand. The more business becomes digital the more stakeholders are interested in this data including how it relates to business. Some of these people have never used a monitoring tool before. They have a question on their mind like “How is my application doing” but no id...
@GonzalezCarmen has been ranked the Number One Influencer and @ThingsExpo has been named the Number One Brand in the “M2M 2016: Top 100 Influencers and Brands” by Onalytica. Onalytica analyzed tweets over the last 6 months mentioning the keywords M2M OR “Machine to Machine.” They then identified the top 100 most influential brands and individuals leading the discussion on Twitter.
As data explodes in quantity, importance and from new sources, the need for managing and protecting data residing across physical, virtual, and cloud environments grow with it. Managing data includes protecting it, indexing and classifying it for true, long-term management, compliance and E-Discovery. Commvault can ensure this with a single pane of glass solution – whether in a private cloud, a Service Provider delivered public cloud or a hybrid cloud environment – across the heterogeneous enter...
In IT, we sometimes coin terms for things before we know exactly what they are and how they’ll be used. The resulting terms may capture a common set of aspirations and goals – as “cloud” did broadly for on-demand, self-service, and flexible computing. But such a term can also lump together diverse and even competing practices, technologies, and priorities to the point where important distinctions are glossed over and lost.
All clouds are not equal. To succeed in a DevOps context, organizations should plan to develop/deploy apps across a choice of on-premise and public clouds simultaneously depending on the business needs. This is where the concept of the Lean Cloud comes in - resting on the idea that you often need to relocate your app modules over their life cycles for both innovation and operational efficiency in the cloud. In his session at @DevOpsSummit at19th Cloud Expo, Valentin (Val) Bercovici, CTO of Soli...
"We're a cybersecurity firm that specializes in engineering security solutions both at the software and hardware level. Security cannot be an after-the-fact afterthought, which is what it's become," stated Richard Blech, Chief Executive Officer at Secure Channels, in this SYS-CON.tv interview at @ThingsExpo, held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA.
"IoT is going to be a huge industry with a lot of value for end users, for industries, for consumers, for manufacturers. How can we use cloud to effectively manage IoT applications," stated Ian Khan, Innovation & Marketing Manager at Solgeniakhela, in this SYS-CON.tv interview at @ThingsExpo, held November 3-5, 2015, at the Santa Clara Convention Center in Santa Clara, CA.
Information technology is an industry that has always experienced change, and the dramatic change sweeping across the industry today could not be truthfully described as the first time we've seen such widespread change impacting customer investments. However, the rate of the change, and the potential outcomes from today's digital transformation has the distinct potential to separate the industry into two camps: Organizations that see the change coming, embrace it, and successful leverage it; and...
Join Impiger for their featured webinar: ‘Cloud Computing: A Roadmap to Modern Software Delivery’ on November 10, 2016, at 12:00 pm CST. Very few companies have not experienced some impact to their IT delivery due to the evolution of cloud computing. This webinar is not about deciding whether you should entertain moving some or all of your IT to the cloud, but rather, a detailed look under the hood to help IT professionals understand how cloud adoption has evolved and what trends will impact th...
Data is the fuel that drives the machine learning algorithmic engines and ultimately provides the business value. In his session at Cloud Expo, Ed Featherston, a director and senior enterprise architect at Collaborative Consulting, discussed the key considerations around quality, volume, timeliness, and pedigree that must be dealt with in order to properly fuel that engine.
We are always online. We access our data, our finances, work, and various services on the Internet. But we live in a congested world of information in which the roads were built two decades ago. The quest for better, faster Internet routing has been around for a decade, but nobody solved this problem. We’ve seen band-aid approaches like CDNs that attack a niche's slice of static content part of the Internet, but that’s it. It does not address the dynamic services-based Internet of today. It does...
Internet of @ThingsExpo, taking place June 6-8, 2017 at the Javits Center in New York City, New York, is co-located with the 20th International Cloud Expo and will feature technical sessions from a rock star conference faculty and the leading industry players in the world. @ThingsExpo New York Call for Papers is now open.
What happens when the different parts of a vehicle become smarter than the vehicle itself? As we move toward the era of smart everything, hundreds of entities in a vehicle that communicate with each other, the vehicle and external systems create a need for identity orchestration so that all entities work as a conglomerate. Much like an orchestra without a conductor, without the ability to secure, control, and connect the link between a vehicle’s head unit, devices, and systems and to manage the ...
20th Cloud Expo, taking place June 6-8, 2017, at the Javits Center in New York City, NY, 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.
Everyone knows that truly innovative companies learn as they go along, pushing boundaries in response to market changes and demands. What's more of a mystery is how to balance innovation on a fresh platform built from scratch with the legacy tech stack, product suite and customers that continue to serve as the business' foundation. In his General Session at 19th Cloud Expo, Michael Chambliss, Head of Engineering at ReadyTalk, discussed why and how ReadyTalk diverted from healthy revenue and mor...
"Qosmos has launched L7Viewer, a network traffic analysis tool, so it analyzes all the traffic between the virtual machine and the data center and the virtual machine and the external world," stated Sebastien Synold, Product Line Manager at Qosmos, in this SYS-CON.tv interview at 19th Cloud Expo, held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA.
"We are a modern development application platform and we have a suite of products that allow you to application release automation, we do version control, and we do application life cycle management," explained Flint Brenton, CEO of CollabNet, in this SYS-CON.tv interview at DevOps at 19th Cloud Expo, held November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA.