Strategic Study of CAE >> 2007, Volume 9, Issue 10
Modeling and Analysis of Fault-tolerant System With Rejuvenation
Department of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China
Next Previous
Abstract
A fault-tolerant system experiences a crash due to hardware components' faults or progressive performance degradation as an "aging" phenomenon, because of running continuously for very long periods. This paper considers both hardware components' faults and "aging" phenomenon, proposes composing redundant structure and rejuvenation schedule in the fault-tolerant system, formalizes the system with Non-Markovian stochastic Petri nets, and evaluates quantitatively the performance of a system based on this model.
Keywords
fault-tolerant system ; software rejuvenation ; software aging ; redundant strategy ; Non-Markovian stochastic Petri nets
References
[ 1 ] Castelli V, Harper R E, Heidelberger P, et al.Proactive manage-ment of software aging [ J ] .IBM J Research & Development, 2001 , 45 : 311 ~332 link1
[ 2 ] Marshall E.Fatal error: how Patriot overlooked a scud [ J ] . Science, 1992 , 255 : 1347 link1
[ 3 ] Huang Y, Kintala C, Kolettin N, et al.Software rejuvenation: analysis, module and applications [ A] .Proc 25th Int’ l Symp on Fault Tolerant Computing [ C] .IEEE CS Press, 1995.381 ~390 link1
[ 4 ] Shereshevsky M, Cukic B, Crowel J, et al.Software aging and multifractality of memory resources [ A ] . Proc Int ’ l Conf on Dependable Systems and Networks [ C] .IEEE CS Press, 2003. 721 ~730 link1
[ 5 ] Garg S, Telek M, Puliafito A, et al.Analysis of software rejuve-nation using Markov regenerative stochastic Petri net [ A] .Proc 6th Int’ l Symp on Software Reliab Eng [ C] .IEEE CS Press, 1995.24 ~27 link1
[ 6 ] Balbo G.Introduction to stochastic Petri nets [ A] .Brinksms E, Hermanns H, Katoen J-P ( Eds) .FMPA 2000 , LNCS 2000 [ C] . ©Springer-Verlag Berlin Heldelberg, 2001.183 ~231
[ 7 ] German R.Iterative analysis of Markov regenerative models [ J] . Journal of Performance Evaluation, 2001 , 44 : 51 ~72 link1
[ 8 ] Choi H, Kulkarni V G, Trivedi K.Markov regenerative stochastic Petri nets [ A] , Iazeolla G, Lavenberg S S eds.Performance-93 [ C] .1993.339 ~356 link1