The analysis of a system from the pure performance viewpoint tends to be optimistic since it ignores the failure/repair behavior in the system. On the other hand, pure availability analysis tends to be too conservative since performance considerations are not taken into account. Also, in a well-designed system, the failure of a component node will cause partial outage of the system, specifically, the decrease of system capacity available to the users, which further affects the performance and quality of service (QoS) to the users. Therefore, in real systems, availability, and performance are important QoS indices which should be studied in a composite manner. The combined evaluation of the indices described above is useful when the system under study can operate in a gracefully degradable manner in the presence of component failures. SHARPE and SPNP software packages that we have developed allow such combined performance/availability analysis.
Computation of the distribution of the completion time when the work requirement is a ph random variableThis work was supported in part by the US Office of Naval Research under Contract no. N3014-88-K-0623, by NASA under Grant NAG-1-70, and by the Italian (1990)