Title :
Rainbow Net analysis of VAXcluster system availability
Author :
Johnson, Allen M., Jr. ; Schoenfelder, Michael A.
Author_Institution :
Rainbow Anal. Syst. Group, Austin, TX, USA
fDate :
6/1/1991 12:00:00 AM
Abstract :
A system modeling technique, Rainbow Nets, is used to evaluate the availability and mean-time-to-interrupt of the VAXcluster. These results are compared to the exact analytic results showing that reasonable accuracy is achieved through simulation. The complexity of the Rainbow Net implemented for the VAXcluster does not increase as the number of processors increases, but remains constant. This is unlike a Markov model which increases in size exponentially. The constancy is achieved by using tokens with identity attributes (items) that can have additional attributes associated with them (features) which can exist in multiple states. The time to perform the simulation increases, but this is a polynomial increase rather than exponential. With Rainbow Nets, there is no restriction on distributions used for transition firing times. This freedom allows real situations to be modeled more accurately by choosing the distribution which best fits the system performance. This eliminates the need to make the many simplifying assumptions that are typically required to keep analytic calculations from becoming intractable
Keywords :
DEC computers; Petri nets; fault tolerant computing; multiprocessing systems; Rainbow Net analysis; VAXcluster system availability; identity attributes; mean-time-to-interrupt; multiprocessor; simulation; system modeling; tokens; Analytical models; Availability; Computational modeling; Logic functions; Petri nets; Power system modeling; Power system reliability; Probability; Statistics; Stochastic processes;
Journal_Title :
Reliability, IEEE Transactions on