HBASE Performance Analysis in Big Datasets Processing

Abstract

The term Big Data has gained popularity in recent years due to technological developments and the accumulation of data from various sources, mobile devices and sensors. Hbase is a distributed open source environment that uses available disk space optimally and efficiently based on data. It organizes data in a very different way from standard relational databases and works with both structured and unstructured data. This article describes our experience and research on how the execution time for inserting datasets and selecting data depends on the size of the data volumes, the locations (nodes of the same or different networks) from which they send or retrieve and what is the effect of the selected data organization (especially RowKey design) on the execution time.