Experimental Analysis of WebHDFS API Throughput

Data analysis is very important for the success of any business today. It helps to optimize processes, analyze users’ behavior, demands etc. There are powerful data analytics tools, such as ones Hadoop ecosystem, but they require multiple high-performance servers run and high-qualified experts install, configure support them. In most cases, small companies start-ups could not afford expenses. However, can use them web services, on demand, pay much lower fees per request. To do that, should somehow share their with an existing, already deployed, cluster. The common way uploading files Hadoop’s Distributed File System (HDFS) through WebHDFS API (Application Programming Interface) that allows remote access HDFS. For reason, API’s throughput efficient integration a company’s This paper performs series experimental analyses aiming determine throughput, if it bottleneck in existing infrastructure detect all possible factors influence speed transmission between clients’ software Hadoop’ file system.