Distributed HBase Cluster Storage Engine and Database Performance Optimization

Distributed HBase Cluster Storage Engine and Database Performance Optimization

연구 분야: Databases

학회: 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys)

With the development of network society, individuals and enterprises generate massive data every day. However, the traditional relational MySQL database has poor performance in storing and processing massive data. In the case of huge amount of data, MySQL may even crash, which obviously cannot meet the needs of massive data storage. Obviously, with more and more emphasis on user-friendliness, the storage and processing application of massive data determine the future development of enterprises. This paper discusses the storage engine, high concurrency, architecture and distributed cluster of HBase, and then compares the performance differences between MySQL and HBase optimized with Bloom filter(Bloom HBase) on Linux platform.