Performance Analysis of Media Cloud-Based Multimedia Systems With Retrying Fault-Tolerance Technique

In this paper, the performance of a cloud-based multimedia system using retrying for fault tolerance is studied. Specifically, the response time of the cloud-based multimedia system is modeled and the probability distribution of the response time is derived considering the effect imposed by retrying tasks in case of service failures happening. As another important performance metric that can better reflect requirements of customers, the percentile of response time that characterizes a threshold response time so that a certain percentage of requests can be served in under the threshold value is also studied. Relationships among number of service resources, task arrival rate, service rate, and system performance are studied through numerical examples. In addition, the percentile of response time of cloud-based multimedia systems using the retrying technique is compared with that of systems using the check-pointing technique.