A Reliability Model for Gracefully Degrading and Standby-Sparing Systems

A model for analyzing the reliability of gracefully degrading and standby-sparing computer systems is developed. The basis of the model is the identification of four distinct causes of crashes: time-domain multiple faults, resource exhaustion, space-domain multiple faults, and solitary faults. Expressions are developed for each of these crash-causing mechanisms and for their interrelationship. The model is then demonstrated by using it to analyze the reliability of a gracefully degrading computer system called PRIME.