• United States

What makes for a next-generation application performance product?

Feb 21, 20063 mins

* The characteristics of next-generation

Last week, we discussed some of the factors that impact application performance and looked at the characteristics of the current generation of application acceleration products. Today, we will discuss the next-generation of application acceleration gear.

In our industry, the term “next-generation” is terribly overused. In particular, introducing some new feature into a product or service does not constitute a next-generation product or service. To be truly next-generation the change has to be more fundamental.

The way that many of the current application acceleration products work is that they require IT organizations to implement specialized appliances in each branch office. Since so many products are narrowly focused, this tends to result in vendor marketing campaigns that focus on showing that one specialized device is superior to another.

Not only is there confusion from a marketing perspective, having specialized appliances also presents some operational concerns. For example, in many cases these highly specialized appliances sit in branch offices next to numerous other appliances, each of which is performing some other highly specialized task in order to make individual applications run better over the WAN. Few companies want a deployment strategy that results in having their branch offices littered with appliances.

The current focus on specialized appliances reminds us of some of the discussions that occurred in the mid 1990s over LAN switching. At that time, a heated debate raged over the benefits of cut through switching vs. store and forward. The primary reason for the intensity of this debate was that initially some vendors only had cut through switching and some other vendors only had store and forward. The debate over which technology was superior quickly went away once next-generation products that incorporated both techniques began to hit the market.

We believe that next-generation application acceleration products are beginning to hit the market. The reason that we refer to them as being next-generation is that they are not just another appliance performing a highly specialized task. Rather, these products integrate a number of existing application optimization techniques while also typically include some powerful new technology.

Given the emergence of integrated application acceleration products, it is time to begin to shift the discussion. Whereas it used to be appropriate to focus on which vendors had the hottest box for performing one or two functions, it is now important to begin to discuss which vendors have both best architectural approach as well as blazingly fast performance.

IT organizations are going to be challenged to evaluate all of the application acceleration products that will claim to be next generation. Jim recently published a document that describes a set of criteria that IT organizations can use to make this evaluation. These criteria include performance, QoS, data reduction, scalability, transparency, and security.

This concludes this series on application acceleration. We will undoubtedly come back to this complex, important topic in the future. In the meantime, on March 20, Jim will be in Boston moderating two tracks at the Network World IT Roadmap conference. One track is on Network Management and the other is on Network and Application Acceleration. If you are in the area, kindly plan to attend. You can register at the above link.

Jim has a broad background in the IT industry. This includes serving as a software engineer, an engineering manager for high-speed data services for a major network service provider, a product manager for network hardware, a network manager at two Fortune 500 companies, and the principal of a consulting organization. In addition, Jim has created software tools for designing customer networks for a major network service provider and directed and performed market research at a major industry analyst firm. Jim’s current interests include both cloud networking and application and service delivery. Jim has a Ph.D. in Mathematics from Boston University.

More from this author