Comparative evaluation of limited preemptive methods

Schedulability analysis of real-time systems requires the knowledge of the worst-case execution time (WCET) of each computational activity. A precise estimation of such a task parameter is quite difficult to achieve, because execution times depend on many factors, including the task structure, the system architecture details, operating system features and so on. While some of these features are not under our control, selecting a proper scheduling algorithm can reduce the runtime overhead and make the WCETs smaller and more predictable. In particular, since task execution times can be significantly affected by preemptions, a number of scheduling methods have been proposed in the real-time literature to limit preemption during task execution. In this paper, we provide a comprehensive overview of the possible scheduling approaches that can be used to contain preemptions and present a comparative study aimed at evaluating their impact on task execution times.