Availability improvement of active/standby cluster systems

Software rejuvenation method for highly available clustering systems is a proactive fault-tolerant approach to handle system failures. The method prevents failures from occurring, while previous methods recover from failures after happening. In this paper, we calculate steady-state probability, availability, downtime, and downtime cost of clustering systems applying the software rejuvenation method. validate the closed-form solutions of the proposed analytic model by. experiments using various operating parameters. The experimental results suggest that the software rejuvenation can be chosen as a preventive fault-tolerant technique. The failure rate and the unstable rate of clustering systems are essential factors in deciding rejuvenation policies.