Bounding the Maximum Length of Non-preemptive Regions under Fixed Priority Scheduling

The question whether preemptive systems are better than non-preemptive systems has been debated for a long time, but only partial answers have been provided in the real-time literature and still some issues remain open. In fact, each approach has advantages and disadvantages, and no one dominates the other when both predictability and efficiency have to be taken into account in the system design. In particular, limiting preemptions allows increasing program locality, making timing analysis more predictable with respect to the fully preemptive case. In this paper, we integrate the features of both preemptive and non-preemptive scheduling by considering that each task can switch to non-preemptive mode, at any time, for a bounded interval. Three methods (with different complexity and performance) are presented to calculate the longest non-preemptive interval that can be executed by each task, under fixed priorities, without degrading the schedulability of the task set, with respect to the fully preemptive case. The methods are also compared by simulations to evaluate their effectiveness in reducing the number of preemptions.