Improving the schedulability and quality of service for federated scheduling of parallel mixed-criticality tasks on multiprocessors

This paper presents federated scheduling algorithm, called MCFQ, for a set of parallel mixedcriticality tasks on multiprocessors. The main feature of MCFQ algorithm is that different alternatives to assign each high-utilization, high-critical task to the processors are computed. Given the different alternatives, we carefully select one alternative for each such task so that all the other tasks can be successfully assigned on the remaining processors. Such flexibility in choosing the right alternative has two benefits. First, it has higher likelihood to satisfy the total resource requirement of all the tasks while ensuring schedulability. Second, computational slack becomes available by intelligently selecting the alternative such that the total resource requirement of all the tasks is minimized. Such slack then can be used to improve the QoS of the system (i.e., never discard some low-critical tasks). Our experimental results using randomly-generated parallel mixed-critical tasksets show that MCFQ can schedule much higher number of tasksets and can improve the QoS of the system significantly in comparison to the state of the art