计算机与数字工程2017，Vol.45Issue(1)：83-87,5.DOI:10.3969/j.issn.1672-9722.2017.01.018
Hadoop MapReduce新旧架构的对比研究综述
Comparative Study of Old and New Architecture of Hadoop MapReduce
摘要
Abstract
After a reconstruction of Hadoop MapReduce framework,it changes a lot.This paper firstly describes the architecture of the old version of MapReduce,processes in which the job execution scheduling,resource allocation and other tasks,it points the limitations of the framework.And then it introduces the new architecture,task scheduling and resource allocation.Compared both new and old architecture,it points the advantages of the new framework.With the new generation MapReduce framework YARN,it applications using different computational framework on it,and reduce the difficulty of operation and maintenance,improve the utilization of cluster resources.关键词
MapReduce/YARN/任务调度/资源分配Key words
MapReduce/YARN/task schedule/resource allocation分类
信息技术与安全科学引用本文复制引用
于金良,朱志祥,李聪颖..Hadoop MapReduce新旧架构的对比研究综述[J].计算机与数字工程,2017,45(1):83-87,5.基金项目
2015年工信部通信软科学研究项目(编号:2015-R-19) （编号:2015-R-19）
2015陕西省信息化技术研究项目课题(编号:2015-002)资助. （编号:2015-002）
