分布式任务调度与副本复制集成策略研究

Decentralized integration of task scheduling with replica placement strategy

研究了分布式任务调度和副本复制集成体系结构,并提出了基于博弈理论的分布式副本复制模型及相应算法——Best-Reply算法,最后通过仿真实验与其他4种算法进行比较。结果表明,尽管分布式的在线任务调度算法与Best-Reply算法集成策略与集中式的集成策略相比其任务平均完成时间稍高,但是它对存储空间的敏感度较低,网络负载更稳定,因此完全可以替代现有集中式的任务调度和副本复制集成策略。

A decentralized architecture of integration of task scheduling with replication placement was put forward in advance.Based on this architecture,a game theory based decentralized replication placement model and related algorithm,Best-Reply algorithm,were proposed.At last,four compositions of task scheduling and replica placement algorithms were compared by simulations in terms of average job completion time and average network load.The result shows that though the integration of decentralized online task scheduling algorithm with best-reply algorithm,against centralized in-tegration algorithms,is a little worse in average job completion time,its average network load changes a little and it can be substituted for the centralized integration algorithms whatever the size of disk space of storage resources is.