Abstract—In the past few years, along with the expansion ofthe data volume and the cost of computer hardware down, thedemand of quickly handling huge amounts of data is driving therising and development of distributed computing. Database ^stembased on the column storage also gradually rise along with thevigorous development of the cloud computing technology. Manyorganizations are trying to turn the traditional row storage databasemigration to the column storage database, so as to adapt to themassive growth of data. In addition to providing a distributed file^aem and supporting the MapReduce computing framework,Hadoop also provides a scalable and structured data distributedstorage system: Hadoop Database(HBase). In currently industry.The HBase column store data is one of the moa popular opensource products. HBase as an open source implementation ofBigTable, the users pay more attention to the performance with thepopularization of its application.Even though the industry has high expectations on HBase, butit am has some disadvantages, for example: not according to thecharacteristics of the column data stored in columns for efficientdata compression, compression mode does not support directoperation data, and so on. Therefore, improving HBaseperformance has important practical significance. This paperanalyses the principle of HBase distributed storage system first, andthen studying HBase performance testing in-depth, and outlook onthe future development of distributed storage system.In general, HBase will provide satisfactory read performance aslong as the cluster memory is enough. But HBase writeperformance will be restricted by many factors. Therefore, thispaper mainly studies HBase write performance. This paperintroduces HBase environment firstly, then analysis of the principleof HBase distributed storage system, focus on HBase writingprocess analysis. This paper did the random write tea and datawrite tea, analyze the tea results to find the influence factors forHBase writing performance. By modifying the HBase ...