Primary-Backup Based Fault-tolerant Dynamic Scheduling of Tasks in Multiprocessor Real-time Systems

Multiprocessor systems are fast emerging as a powerful computing tool for real-time applications. The reliability required of real-time systems leads to the need for faulttolerance in such systems. One way of achieving faulttolerance is by Primary-Backup (PB) approach in which two versions of a task are run on two di erent processors. In this paper, we compare and contrast three basic PB approaches (i) primary-backup exclusive, (ii) primarybackup concurrent, and (iii) primary-backup overlapping in the context of dynamic scheduling of real-time tasks. Our simulation studies reveal some interesting results about the relative performance of these approaches.