DMCA
XJoin: A Reactively-Scheduled Pipelined Join Operator (2000)
| Venue: | IEEE DATA ENGINEERING BULLETIN |
| Citations: | 138 - 8 self |
BibTeX
@ARTICLE{Urhan00xjoin:a,
author = {Tolga Urhan and Michael J. Franklin},
title = {XJoin: A Reactively-Scheduled Pipelined Join Operator},
journal = {IEEE DATA ENGINEERING BULLETIN},
year = {2000},
volume = {23},
pages = {2000}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Wide-area distribution raises significant performance problems for traditional query processing techniques as data access becomes less predictable due to link congestion, load imbalances, and temporary outages. Pipelined query execution is a promising approach to coping with unpredictability in such environments as it allows scheduling to adjust to the arrival properties of the data. We have developed a non-blocking join operator, called XJoin, which has a small memory footprint, allowing many such operators to be active in parallel. XJoin is optimized to produce initial results quickly and can hide intermittent delays in data arrival by reactively scheduling background processing. We show that XJoin is an effective solution for providing fast query responses to users even in the presence of slow and bursty remote sources.
Keyphrases
reactively-scheduled pipelined join operator query execution many operator wide-area distribution promising approach small memory footprint bursty remote source fast query response effective solution background processing load imbalance temporary outage data arrival intermittent delay data access non-blocking join operator initial result traditional query processing technique arrival property significant performance problem
