Explicit Preemption Placement for Real-Time Conditional Code

In the limited-preemption scheduling model, tasks cooperate to offer suitable preemption points for reducing the overall preemption overhead. In the fixed preemption-point model, tasks are allowed to preempt only at statically defined preemption points, reducing the variability of the preemption delay and making the system more predictable. Different works have been proposed to determine the optimal selection of preemption points for minimizing the preemption overhead without affecting the system schedulability due to increased non-preemptivity. However, all works are based on very restrictive task models, without being able to deal with common coding structures like branches, conditional statements and loops. In this work, we overcome this limitation, by proposing a pseudo-polynomial-time algorithm that is capable of determining the optimal set of preemption points to minimize the worst-case execution time of jobs represented by control flow graphs with arbitrarily-nested conditional structures, while preserving system schedulability. Exhaustive experiments are included to show that the proposed approach is able to significantly improve the bounds on the worst-case execution times of limited preemptive tasks.