Cache management method of distributed internal memory column database

Abstract

The invention discloses a cache management method of a distributed internal memory column database. The cache management method comprises the steps that cache queues are established on cache master control nodes; each physical task is used as a root node to cut the physical execution plan the node is located so as to obtain the cache calculation track corresponding to each physical task; cache feature trees are established on the cache master control nodes according to the cache calculation track corresponding to each physical task; when query requests arrive, an execution engine is queries to parse SOL statements into the physical execution plans; layer-level transversal is conducted on each node in the physical execution plans starting from the root nodes of the physical execution plan to execute, and whether the cache calculation track corresponding to each physical task is matched with the corresponding cache feature tree or not is judged; if yes, actual cache data of the physical tasks is directly read from the cache nodes, if not, the physical tasks are calculated. According to the cache management method of a distributed internal memory column database, weather a cache hits the target or not is rapidly detected through an efficient cache matching algorithm, and the query efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of computer software, in particular to a cache management method of a distributed memory column database. Background technique [0002] With the development of the information age, the scale of data has shown explosive growth. How to extract valuable information from these massive data is a huge challenge facing the current society. The On-Line Analytical Processing (OLAP, On-Line Analytical Processing) system has demonstrated its powerful data analysis capabilities, and it has been widely used in commercial fields such as banking, telecommunications, and stock exchanges. [0003] The distributed in-memory columnar database that supports OLAP systems allows users to extract and analyze valuable information from massive data in multiple dimensions. This information may be a simple report or a complex analysis result. As the complexity of query statements increases, the time required for query operations will...

AI Technical Summary

Problems solved by technology

[0004] The query requests in the database are highly semantically related, so some query results are likely to have appeared in historical queries

Images