On harmonic fixed-priority scheduling of periodic real-time tasks with constrained deadlines

Abstract

It is well known that a task set, i.e., task periods are integer multiples of each other, can better utilize a processor to achieve high system utilization. However, the current definition of task is limited only to tasks with deadlines equal to their periods. In this paper, we extend the concept of harmonic task set to tasks with constrained deadlines, i.e., deadlines less than or equal to their periods. We show that a task with constrained deadlines has a better schedulability than the non-harmonic one with the same task utilization. We employ this characteristic for task partitioning on multi-core platform, and our extensive experimental results show that, by taking the task relationship into consideration, our partitioning approach can greatly improve the schedulability of real-time tasks on multi-core platforms.