Performance Analysis of a Distributed Software Development Environment

This paper studies the performance of a distributed computing system under a software development application workload. To quantify the load generated by typical software developers a series of controlled experiments with application benchmarks were performed. The measurements obtained from the experiments were used to parameterize a quequeing network model of the system, which was then used to project the performance of the system under various loading conditions, to identify system bottlenecks, and to compare design alternatives. The results obtained from the quequeing network analysis were used to determine the maximum number of clients that can be supported by the system without violating system performance requirements.