【摘要】 为了提高分布式计算集群系统的可靠性,增强系统的容错能力,使系统在局部出错的情况下仍能稳定正常运行,建立了一个容错系统模型,该模型采用两级容错机制即节点级容错和任务级容错。此模型为分布式计算集群系统下的容错的进一步研究建立了基础。更多还原

【Abstract】 In order to improve the reliability,enhance the fault-tolerant ability of distributed computing cluster,and make the system run normally when the system has a local erro,a fault-tolerant model was built that uses a two-level fault tolerance,that is,node and task level.Based on the model,the further research of fault tolerance on distributed computing cluster system is available.更多还原