Scheduling in Hadoop Cluster: A Review

Abstract

Abstract

Data generated by almost everything is electronically stored in the units of exabyte or zetabyte known as big data. For big data processing, Hadoop is considered as best choice. There are lots of challenges like storage, processing and resource allocation on the basis of job deadlines, QoS, budget, network bandwidth and data transmission. In order to solve these problems, various scheduling algorithms have been developed. These scheduling algorithms are classified according to job and data scheduling. Oozie tool in Hadoop is used to combine multiple jobs into a single job and assign some schedule to execute them in either sequential or parallel manner.

Keywords: Big data, scheduling, Hadoop, HDFS, Map Reduce, Oozie

Cite this Article

Nagina, Sunita Dhingra. Scheduling in Hadoop Cluster: A Review. Journal of Advanced Database Management & Systems. 2017; 4(3): 26–31p.