Improving Feasibility of Fixed Priority Tasks Using Non-Preemptive Regions

Abstract

Preemptive schedulers have been widely adopted in single processor real-time systems to avoid the blocking associated with the non-preemptive execution of lower priority tasks and achieve a high processor utilization. However, under fixed priority assignments, there are cases in which limiting preemptions can improve schedulability with respect to a fully preemptive solution. This is true even neglecting preemption overhead, as it will be shown in the paper. In previous works, limited-preemption schedulers have been mainly considered to reduce the preemption overhead, and make the estimation of worst-case execution times more predictable. In this work, we instead show how to improve the feasibility of fixed-priority task systems by executing the last portion of each task in a non-preemptive fashion. A proper dimensioning of such a region of code allows increasing the number of task sets that are schedulable with a fixed priority algorithm. Simulation experiments are also presented to validate the effectiveness of the proposed approach.