Availability Improvement in Virtualized Multiple Servers with Software Rejuvenation and Virtualization

Software aging often affects the performance of a software system and eventually causes it to fail. To highlight the aging problems in long running applications, we have conducted the study of software rejuvenation approach and virtualization technology in this paper. In order to reduce the downtime during rejuvenation interval, software rejuvenation and virtualization technology are combined in this paper. Virtualization allows multiple operating system instances to run concurrently on a single physical machine. In this paper, we map virtualization based software rejuvenation approach with Markov Chain process and get mathematical steady-state solutions of the chain. We model multiple physical servers which are used to host multiple virtual machines (VMs) using stochastic modeling and evaluate it through both numerical analysis and SHARPE (Symbolic Hierarchical Automated Reliability and Performance Evaluator) tool simulation. The numerical results show that software rejuvenation and virtualization can be used to prolong the availability of the services and reduce the downtime of the systems.