Comparative Study of Old and New Architecture of Hadoop MapReduce
YU Jinliang
ZHU Zhixiang
LI Congying
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.
Keywords:MapReduceYARNtask scheduleresource allocation
Publication Date:2017-01-01
Online Publishing Date:2025-08-15(First online date of this platform, not the publication date of the document)
Pages:5( 83-87 )
Computer and Digital Engineering

Computer and Digital Engineering

ISTIC
ISSN:1672-9722
Year, Vol.(Issue):2017,45(1)