Small Sized File Storage Problems in Hadoop Distributed File System
Neeta Alange, Anjali Mathur · 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT) · 2019
Hadoop Distributed File System (HDFS) is widely used to store the files, which are having heavy size. HDFS is so-called as distributed file system, which intends to store and access the huge volume of data. It is highly fault tolerant system. HDFS opts for the characteristic of cloud repository base, which is having capacity of ready-to-scale, good in performance efficiency and low-cost storing ability. It offers parallel processing therefore, it has high throughput. HDFS is more appropriate for applications, which are having massive datasets. However, it is inefficient for accumulation of multiple small sized files and faces many problems while processing. In this paper, the number of existing techniques have compared in terms of their performance throughput and a comparative chart has been prepared to compare the solutions in a better way for small file problem in Hadoop. By analyzing the chart, a better and efficient solution will able, to propose to store the small sized files in faster way.