Time: Tuesday, May 8 (half-day, afternoon, 1:30pm to 5:00pm)
The study and design of Web applications and services require good models of the workloads to which these applications are subject. The Web is a complex system with hundreds of millions of users demanding services from thousands of applications. In order to understand the Web, one needs first to understand the workload associated with their most popular applications, such as email, peer-to-peer, e-business, search engines, streaming media, etc. This tutorial presents a comprehensive study of real Web workloads. It shows the main properties of these workloads and discusses the invariants across different types of workloads. It introduces methodologies and techniques used in workload characterization and modeling. Constructing a model involves tradeoffs between realism and complexity. The tutorial shows how characterization techniques have been used to capture the most relevant aspects of Web workloads while keeping the model as simple as possible. A major goal of this tutorial is to show how workload models can be used to design efficient Web systems and services. The attendees of the tutorial will be exposed to the most important techniques for characterizing and modeling Web workloads.
Little background in statistics, very little mathematical background, and general knowledge about the Internet and Web techniques and services.
Virgilio Almeida is a Professor of Computer Science at the Federal University of Minas Gerais, Brazil. He holds a Ph.D. in Computer Science from Vanderbilt University. Dr. Almeida held Visiting Professor positions at Boston University and Polytechnic University of Catalunya in Barcelona. He also held visiting research positions at Xerox PARC and Hewlett Packard Research Laboratory. He published over 80 technical papers and was co-author of five books. He was the recipient of various prizes, and best paper awards including the Compaq/Brazil Award for Research and Development in Computer Science. Virgilio is a recipient of a Fulbright Research Scholar Award. He has consulted extensively for government and private organizations in the area of capacity planning and performance modeling, including IBM, Travelocity, and large Brazilian banks. Dr. Almeida has 20 years of teaching experience as a faculty member. He has also taught numerous tutorials and professional development seminars.
Daniel Menasce is a Professor of Computer Science and the Associate Dean for Research and Graduate Studies at the Volgenau School of Information Technology and Engineering at George Mason University, Fairfax, Virginia, USA. He holds a Ph.D. in Computer Science from UCLA. He published over 180 technical papers and is the co-author of five books. He is a Fellow of the ACM, an elected member of IFIP's Working Group 7.3 in Modeling and Analysis, and a recipient of the 2001 A.A. Michelson Award from the Computer Measurement Group for lifetime contributions in computer metrics. Dr. Menasce has almost thirty years of teaching experience in academia and has received two outstanding teaching awards at George Mason University. He consulted for many US Government and private organizations (e.g., US Army, US Mint, IBM, Travelocity, United Online) on issues related to e-commerce, web-based systems, and performance. He taught tutorials at many conferences including ACM Sigmetrics, Usenix, Computer Measurement Group Conferences, and MASCOTS, and he was the keynote speaker at many international conferences.