Improved handling of soft aperiodic tasks in offline scheduled real-time systems using total bandwidth server

Abstract

Real-world industrial applications impose complex constraints, such as distribution, end-to-end deadlines, and jitter control on real-time systems. Most scheduling algorithms concentrate on single or limited combinations of constraints and requirements only. Offline scheduling resolves complex constraints, but provides only very limited flexibility. Online scheduling on the other hand, supports flexibility, resource reclaiming, and overload handling, but handling constraints such as distribution or end-to-end deadline can be costly, if not intractable. In the paper, we propose a method to efficiently handle soft real-time tasks in offline scheduled real-time systems using a total bandwidth server. In a first step, the offline scheduler resolves complex constraints, reduces their complexity, and provides for guaranteed available bandwidth. The constructed schedule is translated into independent tasks on single nodes with start-times and dead-line constraints only. These are then executed using earliest deadline first, total bandwidth server scheduling at runtime.