System Resource Management to Control the Risk of Data-Loss in a Cloud-Based Disaster Recovery
Yuichi Taguchi, Tsutomu Yoshinaga · 2018
A method for system resource management of a cloud-based disaster recovery is proposed. This method can determine whether system performance achieves the "recovery point objective" (RPO) or not. It is also necessary to resize resources for satisfying required performance at lower cost. Therefore, a formula for simulating system performance is established. The results of the simulation show it is possible to determine an appropriate system size that achieves RPO as well as minimizes amount of system resources. It is demonstrated that no error between the experimentally measured and simulated recovery points exists at peak workload. It is thus concluded that the proposed simulation is accurate enough. Also, it is estimated that 89% of system resource cost could be reduced in comparison to the case that the disaster recovery system is designed to fit a peak workload.