采用多叉树模型数据迁移算法的设计与实现  

Design and Implementation of Data Migration Algorithm Using Multi Fork Tree

作　　者：宋春红 王佳斌 郑力新[2] SONG Chunhong;WANG Jiabin;ZHENG Lixin(College of Engineering,Huaqiao University,Quanzhou 362021,China;Industrial Intelligent Technology and System Engineering Research Center of Fujian Province Colleges and Universities,Huaqiao University,Quanzhou 362021,China)

机构地区：[1]华侨大学工学院,福建泉州362021 [2]华侨大学工业智能化技术与系统福建省高校工程研究中心,福建泉州362021

出　　处：《华侨大学学报（自然科学版）》2018年第6期932-936,共5页Journal of Huaqiao University(Natural Science)

基　　金：国家自然科学基金青年科学基金资助项目(61505059);福建省泉州市科技计划项目(2013Z12)

摘　　要：针对目前传统关系型数据库中的历史数据向非关系型数据库迁移的低效率问题,提出利用多叉树模型对历史数据存储模式进行重构.基于4种模式迁移规则对各表节点之间的关联关系进行分析,推导算法完成传统关系型数据库中存储模式和历史数据的自动化迁移.该算法不受源数据库存储模式的限制,具有一定的通用性.数据迁移实验表明:在查询性能上,基于多叉树的迁移算法比官方迁移工具Sqoop有较大的提高.In order to solve the issues on of low migration efficiency about the historical data from traditional relation database to nosql database,the multi fork tree model is proposed to reconstruct the historical data storage model.Then analyzed the relationship between each table node based on four migration rules.Finally the migration algorithm is derived to complete the automatic migration of the storage model and historical data in the relational database.The algorithm has a certain versatility that is not restricted by the storage mode of source database.Data migration experiments verify that the migration algorithm based on the multi fork tree has greatly improved the query performance compared with the apache official tool Sqoop.

关 键 词：关系型数据库 非关系型数据库 数据迁移 多叉树模型 Sqoop 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]