Reliability modeling and analysis of application servers using stochastic Petri Net Model

摘要

As modern society relies on the fault-free operation of complex computing systems, system fault-tolerance has become a matter of course. So, requests on software reliability and availability have progressed greatly due to the current applications. Software applications executing continuously for a long period of time show a degraded performance and/or an increased occurrence rate of hang/crash failure. In this paper, we present and analyze a proactive fault-tolerance using virtualization technology and rejuvenation (preventive maintenance) technique based on stochastic Petri Net Model. This proposed system presents a new model using the virtualized reliability recovery plan to offer high reliability for application servers. Moreover, our results show that the comparison of numerical calculation and SHARPE (Symbolic Hierarchical Automated Reliability and Performance Evaluator) tool simulation.