| 本文已被：浏览 5958次 下载 8557次 |
码上扫一扫！ |
|
|
| 基于Hadoop 的高效连接查询处理算法CHMJ |
|
赵彦荣1,2,3, 王伟平1,2, 孟丹1,2, 张书彬4, 李均4
|
|
1.中国科学院 计算技术研究所,北京 100190;2.中国科学院 国家智能计算机研究开发中心,北京 100190;3.中国科学院 研究生院,北京 100049;4.腾讯公司 数据平台部,广东 深圳 518057
|
|
| 摘要: |
| 提出了一种并行连接查询处理算法CoLocationHashMapJoin(CHMJ).首先,设计了多副本一致性哈希算法,将具有连接关系的表根据其连接属性的哈希值在机群中进行分布,在提升了连接查询处理中数据本地性的同时,保证了数据的可用性;其次,基于多副本一致性哈希数据分布,提出了HashMapJoin 并行连接查询处理算法,有效地提高了连接查询的处理效率.CHMJ 算法在腾讯公司的数据仓库系统中进行了应用,结果表明,CHMJ 连接查询的处理效率比Hive 系统提高了近5 倍. |
| 关键词: 大数据 Hadoop 连接查询处理 HashMapJoin |
| DOI：10.3724/SP.J.1001.2012.04124 |
| 分类号: |
| 基金项目:国家自然科学基金(60903047) |
|
| Efficient Join Query Processing Algorithm CHMJ Based on Hadoop |
|
ZHAO Yan-Rong1,2,3, WANG Wei-Ping1,2, MENG Dan1,2, ZHANG Shu-Bin4, LI Jun4
|
|
1.Institute of Computing Technology, The Chinese Academy of Sciences, Beijing 100190, China;2.National Research Center for Intelligent Computing Systems, The Chinese Academy of Sciences, Beijing 100190, China;3.Graduate University, The Chinese Academy of Scienc;4.Data Platform Department, Tencent, Inc., Shenzhen 518057, China
|
| Abstract: |
| This paper proposes a join query processing algorithm CoLocationHashMapJoin (CHMJ). First the study designs a multi-copy consistency hash algorithm. The algorithm distributes the data of tables over the cluster according to the hash values of the join property, which improves the data locality while ensure data availability. Second, based on the multi-copy consistency hash algorithm, the study proposes a parallel join query processing algorithm called HashMapJoin. HashMapJoin improves the efficiency of join query significantly. CHMJ has been used in Tencent’s data warehouse system, and plays an important role in Tencent’s daily analysis tasks. The results show that CHMJ improves the efficiency of join query processing by five times comparing to Hive. |
| Key words: big data Hadoop join query processing HashMapJoin |
