Design and implementation of a cache-conscious index manager for the Tachyon, a main memory DBMS

The main memory DBMS (MMDBMS) efficiently supports various database applications that require high performance since it employs main memory rather than disk as a primary storage. In this paper, we discuss the cache-conscious index manager of the Tachyon, a next generation MMDBMS. The index manager is an essential sub-component of a DBMS used to speed up the retrieval of objects from a large volume of a database in response to a certain search condition. Recently, the gap between the CPU processing and main memory access times is becoming much wider due to rapid advance of CPU technology. By devising data structures and algorithms that utilize the behavior of the cache in CPU, we are able to enhance the overall performance of MMDBMSs considerably. In this paper, we address the practical implementation issues and our solutions for them obtained in developing the cache-conscious index manager of the Tachyon. The main issues touched are (1) consideration of the cache behavior, (2) compact representation of an index entry, (3) support of variable-length keys, (4) support of multiple-attribute keys, (5) support of duplicated keys, and (6) definition of the system catalog for indexes. We also show the effectiveness of our approach through extensive experiments.