Graduate Project
 

Collaborative Online Learning For Join Processing

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_projects/1831cs57t

Descriptions

Attribute NameValues
Creator
Abstract
  • Relational binary operators, such as join, are arguably the most costly and frequently used operations in relational data systems. In many join algorithms, the majority of the process time is spent on scanning and attempting to join the parts of the relations that do not satisfy the join condition and do not generate any join results. It causes slow response time, particularly, in interactive and exploratory environment where users would like real-time performance. Current solutions to this problem usually require lengthy and repeating preprocessings, which are costly in general settings and may not be possible to do in some, such as interactive and exploratory workloads. They may support only for a restricted types of joins. In this report, we outline a novel approach for achieving efficient join processing in which a scan operator learns online and during query execution the portions of its underlying relation that may satisfy the join condition and use them for join sooner. We further improve this method by an algorithm in which both scan operators collaboratively learn an efficient join execution strategy. We also show that this approach generalizes traditional and non-learning methods of join. Our empirical studies using standard benchmarks indicate that this approach outperforms similar methods considerably.
Contributor
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

Items

Thumbnail Title Date Uploaded Visibility Actions
file details XieMian2021.pdf 2022-01-04 Public Download