Real-Time rejuvenation scheduling for cloud systems with virtualized software spares

With the increasing popularity of cloud services, there is a growing demand for high reliability and availability of cloud computing. As viable solutions, virtualized software spares and rejuvenation scheduling have been used to maintain highly reliable software platforms and combat Mandelbugs in cloud systems. However, developing real-time rejuvenation schedules for software components with dynamic reliability models has been a challenging task. In this paper, we propose a hybrid approach that integrates preventive and automatic failover strategies to mitigate the harmful effects of Mandelbugs. The approach allows selecting reliability models based on the state of virtualized software components, performing reliability calculations for Software SPare (SSP) gates with up to two virtual hot spares, and scheduling software rejuvenation in real time for cloud systems. Furthermore, the use of Dynamic Fault Tree (DFT) analysis supports the compositional modeling of complex and interconnected systems, alleviating the problem of state-space explosion. Finally, we present a case study of a cloud system with virtualized software spares to demonstrate how rejuvenation schedules can be generated and updated in real time.