Comparative Study of Apache Hadoop vs Spark
Keywords:
Hadoop, Spark, Map-Reduce, HDFSAbstract
The paper focuses on analyzing the differences and comparative study of two most talked about frameworks – Hadoop and Spark - both of which have increasing potential for the big data management. The analysis is carried out regarding components, design, data storage, recovery from failure among other features. Comparative analysis is made by executing certain algorithms on two platforms and comparing the execution time. Similarly, suitability of frameworks for different scenarios is discussed.
References
- Verma Ankush, Mansuri Ashik Hussain, Jain Neelesh, "Big Data Management Processing with Hadoop MapReduce and Spark Technology: A Comparison", 2016 Symposium on Colossal Data Analysis and Networking (CDAN).
- S Humbetov, "Data-intensive computing with map-reduce and hadoop", International Conference on Applcation of Information and Communication Technologies, pp. 1-5, 17-190ct. 2012.
- Polato Ivanilton, R Reginaldo, Goldman Alfredo, Kon Fabio, "A comprehensive view of Hadoop research-A systematic literature review", Journal of Network and Computer Applications, vol. 46, pp. 1-25, November 2014.
- online] Available: http://spark.apache.hadoop.org/.
- online] Available: http://spark.apache.org/docs/latest/mllib-Iinear-methods.html.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT

This work is licensed under a Creative Commons Attribution 4.0 International License.