Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Throughput-Optimized, Global-Scale Join Processing in Scientific Federations Xiaodan Wang, Randal Burns, Andreas Terzis
 

Summary: Throughput-Optimized, Global-Scale Join Processing in Scientific Federations
Xiaodan Wang, Randal Burns, Andreas Terzis
Computer Science Department
The Johns Hopkins University
{xwang, randal, terzis}@cs.jhu.edu
Abstract
We present distributed query scheduling algorithms that
minimize network utilization for spatial joins in the Sky-
Query federation of Astronomy databases. Unlike existing
works that measure the quality of join schedules based on
query response time, our metric both minimizes network
utilization and balances the utilization of heterogeneous
network paths. Preliminary experiments show that our
algorithms reduce network utilization dramatically when
compared with SkyQuery's existing scheduling algorithm.
1 Introduction
Making observational data available for analysis over the
Internet is increasingly important in the disciplines such as
Astronomy and Biology. The SkyQuery federation of As-
tronomy databases [13] provides one such service. Sky-

  

Source: Amir, Yair - Department of Computer Science, Johns Hopkins University
Burns, Randal - Department of Computer Science, Johns Hopkins University

 

Collections: Computer Technologies and Information Sciences