Better Capacity Planning with Queueing Network Models

Abstract

Capacity planning is the key to orderly growth, and performance modeling is the key to orderly capacity planning. Queueing network models have emerged as the preferred performance modeling technology for many capacity planning applications. This article familiarizes data center operations managers with the capabilities of queueing network models and assists performance analysts in using this planning tool by developing and modifying a hypothetical system model using a typical software package for queueing network modeling.

Additional information

Notes on contributors

Edward D. Lazowska

Dr. Edward D. Lazowska is an associate professor of computer science at the University of Washington, Seattle and a principal of Quantitative System Performance, a consulting firm in Seattle and Toronto specializing in computer system analysis. Much of the material in this article has been adapted, with permission, from Quantitative System Performance: Computer System Analysis Using Queueing Network Models by Edward D. Lazowska, John Zahorjan, G. Scott Graham, and Kenneth C. Sevcik, Prentice-Hall, Englewood Cliffs NJ, 1984