论文部分内容阅读
检查点技术,也称为“回溯恢复”,是软件容错的重要手段,它主要用于保存和恢复程序的运行状态。在分布式计算和并行计算系统中有十分重要的作用。该文从减少检查点的开销角度,对分布式系统检查点算法中关于程序卷回时文件系统状态的恢复问题进行了分析讨论和进一步的研究。
Checkpoint technology, also known as “backtrace recovery,” is an important means of software fault tolerance and is used primarily to save and restore program health. In distributed computing and parallel computing systems have a very important role. In this paper, from the point of view of reducing the cost of checkpoint, this paper analyzes and discusses the restoration of file system state during the program rewind in distributed system checkpoint algorithm.