Dependable and reliable cloud-based systems using multiple software spare components

Abstract

Cloud computing relies on a set of service components running on a service provider datacenter to achieve specific tasks. A trusted cloud-based software system is a highly dependable, reliable, available and predictable advanced computing system with guaranteed Quality of Service (QoS). Due to well-established studies and practices on hardware reliability, software faults have become the major factor of system failures in cloud-based systems. In this paper, we introduce a scheme of developing dependable and reliable cloud-based systems using multiple software spare components. We address the software-aging phenomenon in cloud computing, where the reliability of a software component decreases along the time. To counteract the software aging issue, we propose a mechanism to maintain the system reliability above a predefined safety threshold using software rejuvenation schedules. The calculation of system reliability is based on an extended Dynamic Fault Tree (DFT) model of cloud-based systems with Software SPare (SSP) gates. We verify our approach using Continuous Time Markov Chain (CTMC) for the case of constant failure rates, and provide a case study of a cloud-based system to show the detailed procedure as well as the feasibility of our approach.