A new scheduling algorithm for non-preemptive independent tasks on a multi-processor platform

Abstract

The abort-and-restart scheme from the Priority-based Functional Reactive Programming (PFRP) paradigm eliminates the priority inversion problem. This paper is similar by solving the priority inversion problem using the task order restrictions sets of relations. One of the core problems in real-time systems is finding a feasible schedule for a task set on a multiprocessor platform. While preemptive scheduling has benefited from a large number of significant results, the non-preemptive case has still room for improvement. Despite the fact that the well-known EDF and LLF scheduling techniques are optimal for preemptive uniprocessor platform there is no known optimal scheduling algorithm for non-preemptive task sets on a multi-processor platform. Our paper continues our previous works [1] and [2] by describing the experimental results together with their findings about our alternate scheduling method to the EDF and LLF techniques. Our algorithm, called A, is able to schedule all considered non-preemptive independent tasks on a multi-processor platform, while EDF and LLF fail to sometimes provide a feasible schedule. The experiments indicate no execution time overhead for the cases where all the scheduling algorithms were able to provide the schedule. However, when EDF and LLF fail to provide a schedule, A gives the schedule with a 60% execution time overhead.