一种集群计算并行I/O中启发式文件分类分配策略研究

提出了一种新的应用于集群计算环境的文件分配算法,即启发式文件分类分配算法(Heuristic FileSorted Assignment algorithm,HFSA),它在保证系统负载基本均衡的前提下,按相似的访问服务时间对每个待分配的数据文件进行磁盘分配.具体实现时,首先对待分配文件按它们的服务时间大小进行排序,然后从集群中选择一个结点的磁盘,将有序的若干文件连续地分配到该磁盘上,直接该磁盘达到最大负载时为止.通过对新策略与已有的贪婪文件分配法进行实验比较,结果表明:在访问响应时间方面,系统轻负载时,缩短了20.2%,系统重负载时,缩短了31.6%,并且数据访问的速率越高,由启发式文件分类分配策略所改善的性能就越明显.

Heuristic File Sorted Assignment Algorithm of Parallel I/O on Cluster Computing

A new file assignment strategy of parallel I/O is proposed on cluster computing system. It is named Heuristic File Sorted Assignment algorithm(HFSA). Based on the load balancing, it assigns the files to the same disk according to the similar service time. Firstly, the files are sorted and stored at the set I in descending order in terms of their service time, then one disk of cluster node is selected randomly when the files are to be assigned, at last the contiguous files are taken orderly from the set I to the disk until the disk reaches its load maximum. The experimental result shows that the new strategy improves the performance by 20.2% when the load of system is light and 31.6% when the load is heavy. Meanwhile, the result shows that the much higher data access rate, the more evident improvement of the performance obtained by the HFSA.