Answering Join Queries Instantly

Author

Mohammed Hamdi, Southern Illinois University CarbondaleFollow

Date of Award

5-1-2018

Degree Name

Doctor of Philosophy

Department

Computer Science

First Advisor

Hou, Wen-Chi

Abstract

This research presents an innovative way to process queries without having to perform expensive join and set operations. We propose to store the equi-join relationships of tuples on mass storage devices, such as disks, to facilitate query processing. The equi-join relationships are captured, grouped, and stored as various tables on disks, which are collectively called the Join Core. Queries involving arbitrary legitimate sequences of equi-joins, semi-joins, outer-joins, anti-joins, unions, differences, and intersections can all be answered quickly by merely merging these tables. Without having to performing joins, memory consumptions are dramatically reduced. The Join Core can also be updated dynamically. Preliminary experimental results showed that all test queries began to generate results instantly, and many completed instantly too. The proposed methodology can be very useful for queries with complex joins of large relations, and can be even more advantageous to distributed query processing, as there are fewer or even no relations or intermediate results needed to be retrieved, generated or transferred over the networks.