Analysis of fault tolerant computer systems

In many critical applications of digital systems, fault tolerance has been an essential architectural attribute for achieving high reliability. In recent years, the concept of the performability of such systems has drawn the attention of many researchers. In this paper we develop a general Markov model for fault tolerant computer systems. Various important performance measures, including the performability measures as well as some new performance measures, are treated in a unified manner. Furthermore, general and efficient computational procedures are developed for calculating these performance measures based on the uniformization technique of Keilson. A numerical example is given to illustrate the computational procedures developed.