关键业务中内存数据库的T树索引优化

Optimization of T-tree Index of Main Memory Database in Critical Application

在关键业务中,提高DBMS性能的一个途径是把数据库放在主存中而不是硬盘中,这样便可以设计新的数据结构和算法,来提高内存数据库(MMDB)的效率。该文列举了当前MMDB研究中关于索引结构的一些成果, 并设计了一个新的索引结构——T-tail 树, 最后给出了T-tail 树的主要算法和这些算法的性能分析。结果表明在内存数据库中, T-tail 树具备非常好的性能。

One approach to achieve high performance in the DBMS in the critical application is to store the database in main memory rather than on disk. Then one can design new data structures and algorithms oriented towards increasing the efficiency of the main memory database (MMDB). This paper presents some results on index structures from an ongoing study of MMDB, and proposes a new index structure, the T-tail tree. At last it gives the main algorithm of the T-tail Tree and the performance of these algorithms. These results indicate that T-tail tree provides good overall performance in main memory.