A scheduling algorithm for replicated real-time tasks

An algorithm for scheduling real-time periodic tasks on a multiprocessor system under a fault-tolerant requirement is presented. The approach incorporates both the redundancy and masking technique, and the imprecise computation model. Since the tasks in hard real-time systems have stringent timing constraints, the redundancy and masking technique is more appropriate than the rollback techniques, which usually require extra time for error recovery. The imprecise computation model provides flexible functionality by trading off the quality of the result produced by a task with the amount of processing time required to produce it. It therefore permits the performance of a real-time system to degrade gracefully. The algorithm was evaluated by stochastic analysis and Monte Carlo simulations. The results showed that the algorithm was resilient under hardware failure.<>