Scheduling Algorithms for Real-Time Systems

The problem of real-time scheduling spans a broad spectrum of algorithms from simple uniprocessor to highly sophisticated multiprocessor scheduling algorithms. In this paper, we study the characteristics and constraints of real-time tasks which should be scheduled to be executed. Analysis methods and the concept of optimality criteria, which leads to design appropriate scheduling algorithms, will also be addressed. Then, we study real-time scheduling algorithms for uniprocessor systems, which can be divided into two major classes: off-line and on-line. On-line algorithms are partitioned into either static or dynamic-priority based algorithms. We discuss both preemptive and non-preemptive static-priority based algorithms. For dynamic-priority based algorithms, we study the two subsets; namely, planning based and best effort scheduling algorithms. Some of the uniprocessor scheduling algorithms are illustrated by examples in the Appendix. Multiprocessor scheduling algorithms is another class of real-time scheduling algorithms which is discussed in the paper as well. We also describe techniques to deal with aperiodic and sporadic tasks, precedence constraints, and priority inversion. This work was supported by the Natural Sciences and Engineering Research Council of Canada.