期刊名称：International Journal of Engineering and Computer Science
印刷版ISSN：2319-7242
出版年度：2014
卷号：3
期号：8
页码：7938-7942
出版社：IJECS
摘要：The increasing popularity of Cloud computing as an attractive alternative to classic information processing systems has increased theimportance of its correct and continuous operation even in the presence of faulty components. Fault tolerance is a major concern to guaranteeavailability and reliability of critical services as well as application execution. In order to minimize failure impact on the system and applicationexecution, failures should be anticipated and proactively handled. Fault tolerance techniques are used to predict these failure and take anappropriate action before failure actually occur. In this paper, we introduce an innovative, system-level, modular perspective on creating andmanaging fault tolerance in Clouds. We propose a high-level approach at SaaS layer for hiding the implementation details of the fault tolerancetechniques to application developers and users. In particular, the service layer hides the user from fault tolerance mechanism, and does notrequire knowledge about the fault tolerance technique applied and that are available in the Cloud and their implementations.The fault tolerant technique applied shall use the heartbeat algorithm(s) and gossip algorithm to detect whether the application is workingsmoothly or not. In case the application is detected to be down then the proposed work deploys an application recovery mechanism applied at theSaaS layer, which will try to start, recover from failure or will reinstall the application so that users can use the same smoothly with minimumdowntime.
关键词：heartbeat algorithm; gossip algorithm; time synchronization; fault tolerance; SaaS Layer development
