论文信息 - Availability Analysis of a Fault-Tolerant Computer System

Availability Analysis of a Fault-Tolerant Computer System

Queueing network theory is applied in order to determine the availability of a fault-tolerant multiprocessor computer system. Mean repair times and utilizations of system units are computed. Subsystem availabilities are obtained by the decomposition technique of queueing network theory.

Mario Dal Cin

[1] J. Little. A Proof for the Queuing Formula: L = λW , 1961 .

[2] Martin Reiser,et al. Interactive Modeling of Computer Systems , 1976, IBM Syst. J..

[3] Barry R. Borgerson,et al. PRIME: a modular architecture for terminal-oriented systems , 1972, AFIPS '72 (Spring).

[4] K. Mani Chandy,et al. Approximate Analysis of General Queuing Networks , 1975, IBM J. Res. Dev..

[5] Jeffrey P. Buzen,et al. Computational algorithms for closed queueing networks with exponential servers , 1973, Commun. ACM.

[6] K. Mani Chandy,et al. Parametric Analysis of Queuing Networks , 1975, IBM J. Res. Dev..

[7] Milos D. Ercegovac,et al. A study of standard building blocks for the design of fault-tolerant distributed computer systems , 1978 .

[8] K. Mani Chandy,et al. Open, Closed, and Mixed Networks of Queues with Different Classes of Customers , 1975, JACM.