Characteristics of Scalability and Their Impact on Performance

André B. Bondi
Hudson Williams, Inc.

Scalability is a desirable attribute of a network, system, or process. Poor scalability can result in poor system performance, necessitating the reengineering or duplication of systems. While scalability is valued, its characteristics and the characteristics that undermine it are usually only apparent from the context. Here, we attempt to define different aspects of scalability, such as structural scalability and load scalability. Structural scalability is the ability of a system to expand in a chosen dimension without major modifications to its architecture. Load scalability is the ability of a system to perform gracefully as the offered traffic increases. It is argued that systems with poor load scalability may exhibit it because they repeatedly engage in wasteful activity, because they are encumbered with poor scheduling algorithms, because they cannot fully take advantage of parallelism, or because they are algorithmically inefficient. We qualitatively illustrate these concepts with classical examples from the literature of operating systems and local area networks, as well as an example of our own. Some of these are accompanied by rudimentary delay analysis.

This work was performed at AT&T Labs, Network Design and Performance Analysis Department, Middletown, New Jersey. It was first presented at the Workshop on Software Performance (WOSP2000) in Ottawa during September 2000.

André Bondi joined Hudson Williams Inc., a web performance consulting company, in January 2001. Prior to that, he was a Principal Technical Staff Member in the Network Design and Performance Analysis Department at AT&T Labs, Middletown, NJ. Dr. Bondi holds a Ph.D. in computer science from Purdue University and an M.Sc. in statistics from University College London. Before joining AT&T (Bell) Labs in 1987, he was an assistant professor of computer science at the University of California, Santa Barbara.

Date: Thursday, April 19, 2001, 8:00 PM
Location: Auditorium, Sarnoff Corporation, 201 Washington Road (Rt 571 1/4 mile south of US 1), Princeton, NJ

Additional Information: recorded info (609) 924-8704, Dennis Mancl (908) 582-7086, or David Soll (215) 854-3461
A pre-meeting dinner with the speaker is held at 6 p.m. at the Rusty Scupper on Alexander Road in Princeton. If you would like to attend, please RSVP with an e-mail to or call the information number to record your reservation on the answering machine.

Princeton ACM / IEEE Computer Society meeting are open to the public. Students and their parents are welcome. There is no admission charge, and refreshments are served.