Utilitiy Accrual Scheduling With Real-Time Java

Graceful performance degradation during overload conditions is the primary objective of soft real-time systems. Utility accrual soft real-time scheduling algorithms allow specification of highly customized temporal system behavior during overload. Such algorithms are typically found in real-time supervisory systems where significant run-time uncertainty exists. This paper outlines an investigation of several utility accrual scheduling algorithms implemented in a Real-Time Java (RTJ) environment. These alternate schedulers are constructed, tested, and evaluated under the MIT FLEX/RTJ Compiler Infrastructure. The scheduling framework for this environment and its associated scheduling primitives are described and the corresponding performance characteristics are profiled. Furthermore, we outline the architecture of an experimental distributed Real-time Java scheduler.