A. Bogárdi-Mészöly, T. Levendovszky, and H. Charaf (Hungary)
Software performance engineering, queueing models,performance prediction, and measurements
Distributed systems and web applications play an important role in computer science nowadays. The most common consideration is performance, because these systems must provide cost-effective and high-availability services in the long term, thus they have to be scaled to meet the expected load. Performance measurements can be the base for performance modeling and prediction. With the help of performance models, the performance metrics (like response time, throughput and utilization) can be determined at the early stages of the development process. The goal of our work is to predict the response time, the throughput and the utilization of the tiers of ASP.NET web applications based on a queueing model with MVA evaluation algorithm. We estimated the model parameters (number of customers, number of tiers, user think time, visit numbers, and service times) based on a measurement. We implemented the evaluation algorithm with the help of MATLAB. We tested a web application with concurrent user sessions to validate the model in ASP.NET environment.
Important Links:
Go Back
