A fault-tolerance model for multiprocessor real-time systems

System reliability is an important aspect of real-time systems, because the result of a real-time application may be valid only if the application functions correctly and its timing constraints are satisfied. There are two kinds of faults, hardware and software faults, and the paper considers hardware transient faults. Full replication or full hardware redundancy can achieve a high degree of reliability; however, it wastes lots of resources. For most real-time systems, such schemes might not be available and hence reliability estimation becomes essential. We propose an analytic model for system reliability estimation based on the Markov chain and investigate the accuracy of the estimated reliability. The results show that the proposed model obtains good estimation in various simulated real-time systems. (C) 2000 Academic Press.