Reliability enhancement of real-time multiprocessor systems through dynamic reconfiguration
Kai Yu, Israel Koren · 2002
Enhancing the reliability of a system executing real-time jobs is, in many cases, one of the most important design goals. A dynamically reconfigurable system offers an approach for improvement of reliability. To achieve high reliability the most suitable recovery action must be used when a fault occurs, which means that some kind of optimal recovery strategy should be followed. This is called a dynamic recovery strategy. To satisfy the service requirements of real-time jobs with hard deadlines, a more powerful system, intuitively, should always be preferred. On the other hand, higher processing capacity means more processing modules and electronics parts, which may result in more frequent faults and a higher risk that the system will fail to complete the real-time jobs prior to their deadline. In this paper, we investigate the reliability enhancement of a real-time distributed computing system with hard deadlines through the employment of dynamic recovery strategies. Since the classical reliability evaluation technique is not applicable to a dynamically reconfigurable system, we present a new approach to reliability evaluation. The results show that the optimal recovery policy can significantly improve the system's reliability, that both the job arrival rate and the job's deadline have significant effect on the optimal reliability and optimal policy and that for a given workload and deadline, the maximum of the system reliability can be achieved at a certain (optimal) configuration.