A Survey of Fault Tolerant Computer Architecture and its Evaluation

Abstract

In striving to design highly reliable, highly available computers, two basic strategies have been employed: increasing the reliability throug-h advances in component technology; and designing self-repairing computers which use functional redundancy to permit correct performance (perhaps in a degraded manner) in the presence of component failures. Time has shown a fluctuation in the popularity of each strategy, based primarily on changes in technologies, applications and costs.