Exact Fault-Tolerant Feasibility Analysis of Fixed-Priority Real-Time Tasks

In this paper, a necessary and sufficient (exact) feasibility test is proposed for fixed-priority scheduling of a periodic task set to tolerate multiple faults on uniprocessor. We consider a fault model such that multiple faults can occur in any task and at any time, even during recovery operations. The proposed test considers tolerating a maximum of f faults that can occur within any time interval equal to the largest relative deadline of the task set. The feasibility of the task set is checked based on the maximum workload requested by the higher-priority jobs within the released time and deadline of the job of each task that is released at the critical instant. The maximum workload is calculated using a novel technique to compose the execution time of the higher-priority jobs. To the best of our knowledge, no other work (assuming the same fault model as ours) has derived an exact feasibility test for periodic task sets having a lower time complexity than that of the test proposed in this paper.