Computational performance and scalability of large distributed enterprise-wide systems supporting engineering, manufacturing and business applications

摘要

The Boeing Company has been implementing large client/server systems that support all major engineering, manufacturing and business functions. One of the challenges has been computational performance and scalability to a very large number of users and data sets. Modeling and simulation combined with analytical approximations have been used to predict performance, identify bottlenecks and to establish the required system capacity. This approach is highly dependent on the accurate workload predictions which usually are uncertain and changing. To get around this difficulty the system models have been used in conjunction with parametric studies that explore ranges of system performance behavior. Good performance and scalability are important system quality indicators but there are other issues that have to be taken into account such as system's cost and availability. One of our recent research projects aims at designing a method for defining an initial system topology and capacity. This definition is not unique and can be further refined by considering system's costs. The three models: workload model, performance model and cost model together allow trade-off studies and making rational decisions about the final system selection in view of the present and the future technological and business uncertainties.