Using fixed-priority scheduling with deferred preemption to exploit fluctuating network bandwidth

Fixed Priority Scheduling with Deferred Preemption (FPDS) offers a balance between Fixed Priority Non-preemptive Scheduling (FPNS) and Fixed Priority Preemptive Scheduling (FPPS), by allowing preemptions only at specified preemption points. It provides finer grained preemptions than FPNS, improving the schedulability of higher priority tasks, and a coarser grain preemptions than FPPS, reducing switching overhead incurred during arbitrary preemptions. In this paper we investigate the extent of improvement of FPDS with respect to FPPS and qualify the costs of switching multiple resources under FPPS and FPDS, and the cost of a preemption point. It forms a starting point for our research into employing FPDS in an industrial case study, to improve an existing multimedia processing system from the surveillance domain. We focus on extending FPDS with optional preemption points, to guarantee resource provisions to tasks in spite of fluctuating resource availability, in the context of reservation-based multi-resource sharing.