Performance based multiple server support for distributed real time applications

Abstract

In real time systems, tasks must be performed correctly within time constraints. The system throughput is also a key performance measure. One of the difficulties, which the system designer faces, is to control these performance factors. A heavily requested computation, or a subtask that requires long service time, may reduce the system performance. This paper presents two different solutions for the above problem using multiple servers to support the execution of such a subtask. The first approach uses a pipeline subtask decomposition while the second approach uses a set of parallel servers. A queuing model, that takes into consideration the communication delay, is used for the analysis. In addition, the proposed approaches consider the operating environment, both system and user constraints, and the required resource cost.