A Recommendation Based Comparative Information of Tuning Mechanisms for Performance Management in Hadoop
Anusha R J1, L.RamaParvathy2
1Anusha R J, Research Scholar, Department of Computer Science and Engineering, Saveetha Institute of Technical and Medical Sciences Engineering, Chennai (Tamil Nadu), India.
2Dr. L. Rama Parvathy, Professor SSE, Department of Computer Science and Engineering, Saveetha Institute of Technical and Medical Sciences Engineering, Chennai (Tamil Nadu), India.
Manuscript received on 29 May 2019 | Revised Manuscript received on 11 June 2019 | Manuscript Published on 22 June 2019 | PP: 663-672 | Volume-8 Issue-3S, February 2019 | Retrieval Number: C11420283S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Organizations around the world nowadays collect and handle large datasets which demand parallel and distributed processing. To enable parallel processing, several parallel and distributed frameworks, such as Apache Hadoop and Spark exists.Hadoop configuration parameters are closely related to the utilization of resources such as CPU, memory and network. Tuning these parameters thus becomes one of the important approaches to improve the resource utilization of Hadoop.For automatic tuning of configuration parameters for the new job, various tuning and recommendation methods have been proposed. This paper provides comparative analysis which deals with the parameter tuning and hence performance tuning for Hadoop.In this paper, benefits and limitations of the various tuning methods and a complete study of the conducted research are examined. Also, this paper provides details of some existing open issues and also future research recommendations.
Keywords: Hadoop, Configuration Parameters, Performance Tuning, Online Configuration Recommendation, Resource Utilization Optimization.
Scope of the Article: Measurement & Performance Analysis