分布式计算系统回卷恢复容错的仿真设计

摘要

In order to solve the evaluation problem of the rollback recovery fault tolerance in the distributed computing system, a rollback recovery fault tolerance simulation was designed.According to the structure of the rollback recovery fault tolerance scheme, the node`s task process of the distributed computing system was simulated by the discrete events.The simulation function of the rollback recovery fault tolerance was added in the application layer based on the network simulation software.The related structure, function modules and system parameters were introduced in the proposed simulation.Finally, the proposal was evaluated that the proposed simulation method is capable of the evaluation of the different rollback recovery fault tolerance scheme, and can be utilized to compare, improve and optimize the related fault tolerant algorithms.%为了解决分布式计算系统回卷恢复容错的验证评估问题,设计一种分布式计算系统的回卷恢复容错算法的仿真机制,依据分布式计算系统回卷恢复容错的总体架构,将分布式计算系统中的节点任务过程使用离散事件模拟,在网络系统仿真工具的应用层增加支持多任务回卷恢复容错仿真的模块,并设计用于回卷恢复容错仿真的结构、功能模块和系统参数设定.结果表明本文提出的仿真机制能够实现分布式计算系统的回卷恢复容错算法的模拟验证,为不同容错算法间对比、改进与优化提供参照.