A fault-tolerant scheduling problem

Abstract

A real-time system must be reliable if a failure to meet its timing specifications might endanger human life, damage equipment, or waste expensive resources. A deadline mechanism has been previously proposed to provide fault tolerance in real-time software systems. The mechanism trades the accuracy of the results of a service for timing precision. Two independent algorithms are provided for each service subject to a deadline. The primary algorithm produces a good quality service, although its real-time reliability may not be assured. The alternate algorithm is reliable and produces an acceptable response. An algorithm to generate an optimal schedule for the deadline mechanism is introduced, and a simple and efficient implementation is discussed. The schedule ensures the timely completion of the alternate algorithm despite a failure to complete the primary algorithm within real time.