期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2014
卷号：8
期号：3
页码：115-119
DOI：10.14445/22312803/IJCTT-V8P121
出版社：Seventh Sense Research Group
摘要：As Hadoop is a Substantial scale, open source programming system committed to adaptable, disseminated, information concentrated processing. Hadoop [1] Mapreduce is a programming structure for effectively composing requisitions which prepare boundless measures of information (multiterabyte information sets) inparallel on extensive bunches (many hubs) of merchandise fittings in a dependable, shortcoming tolerant way. A Mapreduce [6] skeleton comprises of two parts. They are "mapper" and "reducer" which have been examined in this paper. Fundamentally this paper keeps tabs on Mapreduce modifying model, planning undertakings, overseeing and reexecution of the fizzled assignments. Workflow of Mapreduce is indicated in this exchange.
