Skip Links

Network World

  • Social Web 
  • Email 
  • Close

Application benchmarking helps you to determine how apps will perform

The value of benchmarking your applications
Wide Area Networking Alert By Steve Taylor and Jim Metzler , Network World , 04/06/2006
Steve Taylor
Sign up for this newsletter now!

WAN experts Steve Taylor and Jim Metzler analyze and share best practices on WAN issues from optimization to management.

  • Share/Email
  • Comment
  • Print

Last time, we pointed out that since a company's CIO as well the company's business and functional managers care more about applications than they do about the WAN, WAN managers need to be able to demonstrate how the WAN enables appropriate application performance. The recommendation that we made was that WAN managers should benchmark any major new application that the company is in the process of deploying.

An IT organization can do the benchmarking themselves or use an outside vendor. The primary purpose of the benchmarking is to determine in advance how the application will perform when run over a production WAN and it endures varying amounts of latency, jitter and packet loss.

For example, before the typical interactive application gets deployed, there is a target for how long a transaction should take. For the sake of example, assume that the target is five seconds and further assume that if there is no WAN latency that the transaction completes in two seconds.

As part of the benchmark exercise, artificial amounts of WAN latency are introduced and the response time of the application is recorded. Typically, as the WAN latency is increased, the application response time also increases. Ideally, the response time increases gradually as WAN latency is increased. However, in some instances application response time can increases dramatically in response to only minor increases in WAN latency.

Staying with our example, assume that when faced with 300 milliseconds of WAN latency the application has a response time of 4 seconds, but if there is a WAN latency of 400 milliseconds, the response time jumps up to 6 seconds.

Armed with this information, the WAN organization can set thresholds throughout the WAN so that the appropriate people are notified when the WAN latency approaches 300 milliseconds. The reason for doing this is so that the WAN organization can know that one of the company's key applications is about to start performing badly and can take steps proactively to ensure that this does not happen.

Future newsletters will come back to the general topic of how WAN managers can better relate the WAN to the company's senior managers.

Steve Taylor is president of Distributed Networking Associates and publisher/editor-in-chief of Webtorials. Jim Metzler is vice president of Ashton, Metzler & Associates.

  • Share/Email
  • Comment
  • Print
Partner Content

Simplify Your Branch Infrastructure

Learn how to simplify your branch infrastructure while dramatically increasing app performance with Citrix Branch Repeater.

Download the Free Info Kit

Next-Gen Load Balancing

Free Guide: "Next Gen Load Balancing: 8 Things You Need to Handle Today's Network Traffic" shows you the functionality needed in your next load balancer.

Download the Free Guide

Accelerate Your Web Apps by up to 5x

Free Guide: "The Secret to Getting Maximum Speed from your Web Applications." Learn how you can deliver Web apps up to 5x faster.

Download the Free Guide

Comment
Login
Forgot your account info?
Add comment
Anonymous comments subject to approval. Register here for member benefits.
Have a NetworkWorld account? Log in here. Register now for a free account.

Videos

rssRss Feed
Get instant email notification when white papers, webcasts, executive guides are added to our library. Stay informed and up-to-date with the latest on IT Technologies with Network World's Resource Alerts.
Network World,to go. Wherever you are. Breaking news delivered to your mobile device. Select the hottest topics in networking and start receiving Network World on your mobile device today.