Database inquiry processing method facing concurrency OLAP (On Line Analytical Processing)

Abstract

The invention discloses a database inquiry processing method facing the concurrency OLAP (On Line Analytical Processing). On the basis of the predicate vector-based memory OLAP star join optimization, the concurrency OLAP inquiry processing on the basis of the bit operation of inquiring predicate vectors in batches is carried out. According to the invention, in a database management system, aiming at the I / O (Input / Output) performance and the parallel OLAP processing performance, a concurrency inquiry processing optimization technology is implemented and the optimization and setting of a concurrency OLAP processing load facing the I / O performance are supported, so that the predictable processing performance facing the diversified OLAP inquiry is improved and the concurrency inquiry star join bitmap filtering processing on the basis of an array of the predicate vectors is implemented.

Description

technical field [0001] The invention relates to a database query processing method, in particular to a method for reducing the cost of star connection in concurrent OLAP and improving the concurrent query processing capability through a predicate vector batch bit processing technology, which belongs to the technical field of database management. Background technique [0002] Today, data processing can be roughly divided into two categories: on-line transaction processing (OLTP for short) and on-line analytical processing (On-Line Analytical Processing, OLAP for short). OLTP is mainly about day-to-day transaction processing, such as bank transactions. OLAP is designed to meet specific query and reporting requirements for decision support or multidimensional environments. Many applications including OLAP drive the emergence and development of data warehouse technology; and data warehouse technology in turn promotes the development of OLAP technology. [0003] In OLAP, I / O (i...

AI Technical Summary

Problems solved by technology

The expansion of this public HASH aggregation table will lead to an increase in the cost of HASH filtering (HASH connection), the possibility that the HASH aggregation table needs disk exchange will increase, the average performance of the query will decrease, and the performance of each HASH filter is unpredictable.

When the selectivity of the query is low, the group query needs to pass a large amount of data between the HASH filters, even when the final query bit vector is all zeros, it also needs to pass data between the HASH filters, but in fact only the query bit vector The query corresponding to the non-zero position in the result needs to use all the data passed between the HASH filters, which causes a lot of waste of memory bandwidth.

Images