Hadoop延迟调度中延迟时间间隔的合理设置

被引:1
作者
柯何杨
杨群
王立松
朱快快
机构
[1] 南京航空航天大学计算机科学与技术学院
关键词
延迟调度; 延迟时间间隔; 本地化; 期望本地化概率;
D O I
暂无
中图分类号
TP311.13 [];
学科分类号
1201 ;
摘要
基于Hadoop框架的云计算中,为减少数据迁移提高程序执行效率,延迟调度算法允许作业花费一定的延迟时间间隔等待某计算资源包含该作业待处理数据,而延迟时间间隔的选择往往是一个经验值。在分析了作业待处理数据在文件系统中的分布情况如何影响作业本地化调度的基础上,引入参数用户期望本地化概率,推导出等待时间的计算公式。该公式区分不同的作业,设置不同的等待时间,并且用户可以根据期望本地化概率这一参数来调控作业预期的本地化程度。对上述方法进行实验验证,结果表明:通过公式计算出的延迟时间能够使得作业达到用户预期的本地化效果。
引用
收藏
页码:207 / 210+261 +261
页数:5
相关论文
共 15 条
[1]  
Locality-Aware Reduce Task Scheduling for MapReduce. Hammoud M,Sakr M F. Proceedings of IEEE Third International Conference on Cloud Computing Technology and Science (CloudCom) . 2011
[2]  
Research on job scheduling algorithm in Hadoop. Xia, Yang,Wang, Lei,Zhao, Qiang,Zhang, Gongxuan. Journal of Computational Information Systems . 2011
[3]  
Locality-aware dynamic VM reconfiguration on MapReduceclouds. PARK J. Proc of the 21st International Symposium on High-Per-formance Parallel and Distributed Computing . 2012
[4]  
HOD. http://hadoop.apache.org/common/docs/r0.18.3/hod.html .
[5]  
Improving Data Locality of MapReduce by Scheduling in Homogeneous Computing Environments. Zhang X,Zhong Z,Feng S. 9th IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) . 2011
[6]  
Google’s MapReduce programming model — Revisited[J] .  &nbspScience of Computer Programming . 2007 (1)
[7]  
MapReduce[J] . Jeffrey Dean,Sanjay Ghemawat. &nbspCommunications of the ACM . 2008 (1)
[8]  
MapReduce[J] . Jeffrey Dean,Sanjay Ghemawat. &nbspCommunications of the ACM . 2010 (1)
[9]  
Delay scheduling:a simple technique for achieving locality and fairness in cluster scheduling. Matel Z,Dhruba B,Joydeep S,et al. Proceedings of the 5th European conference on Computer systems . 2010
[10]  
The Hadoop Distributed File System. Konstantin S,Hairong K,Radia S,et al. Mass Storage Systems and Technologies (MSST) . 2010