Evaluation of performability measures for replicated banyan networks

Performability, a composite measure that evolved from the synergy between performance and reliability, can capture the cumulative performance of a degradable multistage interconnection network over its operational life. In this paper, we present a technique for conservative analysis of performability measures for the replicated banyan network. Assuming uniformally distributed message generation at unblocked sources, we make a reward assignment for synchronous circuit switched operation that translates the cumulative performance to total number of messages routed. The analytical results and simulated values for the average level of the cumulative performance of a replicated banyan are compared. The analysis technique is capable of handling non-Markovian model of component failure. The effect of perturbation from the Markovian model on the cumulative performance has been studied.<<ETX>>

[1]  Bruno Sericola,et al.  Performability Analysis Using Semi-Markov Reard Processes , 1990, IEEE Trans. Computers.

[2]  John F. Meyer,et al.  A Performability Solution Method for Degradable Nonrepairable Systems , 1984, IEEE Transactions on Computers.

[3]  Kishor S. Trivedi,et al.  Reliability analysis of interconnection networks using hierarchical composition , 1989 .

[4]  John F. Meyer,et al.  Closed-Form Solutions of Performability , 1982, IEEE Transactions on Computers.

[5]  Janak H. Patel.  Performance of Processor-Memory Interconnections for Multiprocessors , 1981, IEEE Transactions on Computers.

[6]  John F. Meyer,et al.  Performability: A Retrospective and Some Pointers to the Future , 1992, Perform. Evaluation.

[7]  Ted H. Szymanski,et al.  On the Permutation Capability of Multistage Interconnection Networks , 1987, IEEE Transactions on Computers.

[8]  Santosh K. Shrivastava,et al.  Reliable Computer Systems , 1985, Texts and Monographs in Computer Science.

[9]  R.R. Rao,et al.  Performability analysis of non-repairable multicomponent systems using order statistics , 1994, Proceedings of 1994 6th IEEE Symposium on Parallel and Distributed Processing.

[10]  I. Gertsbakh,et al.  Statistical Reliability Theory , 1988 .

[11]  Lorenzo Donatiello,et al.  Analysis of a composite performance reliability measure for fault-tolerant systems , 1987, JACM.

[12]  H. A. David,et al.  Order Statistics (2nd ed). , 1981 .

[13]  Manoj Kumar,et al.  Performance of Unbuffered Shuffle-Exchange Networks , 1986, IEEE Transactions on Computers.

[14]  John F. Meyer,et al.  On Evaluating the Performability of Degradable Computing Systems , 1980, IEEE Transactions on Computers.

[15]  Marc Snir,et al.  The Performance of Multistage Interconnection Networks for Multiprocessors , 1983, IEEE Transactions on Computers.

[16]  Kishor S. Trivedi,et al.  Performability Analysis: Measures, an Algorithm, and a Case Study , 1988, IEEE Trans. Computers.

[17]  Ting-Ting Y. Lin,et al.  Delay analysis in synchronous circuit-switched delta networks , 1993, [1993] Proceedings Seventh International Parallel Processing Symposium.

[18]  L. Donatiello,et al.  On Evaluating the Cumulative Performance Distribution of Fault-Tolerant Computer Systems , 1991, IEEE Trans. Computers.

[19]  Krishna R. Pattipati,et al.  On the Computational Aspects of Performability Models of Fault-Tolerant Computer Systems , 1990, IEEE Trans. Computers.