Performance of load balancing techniques for join operations in shared-nothing database management systems

被引:5
作者
Hua, KA [1 ]
Tavanapong, W
Lo, YL
机构
[1] Univ Cent Florida, Sch Comp Sci, Orlando, FL 32816 USA
[2] Chao Yang Univ Technol, Dept Informat Management, Taichung, Taiwan
基金
美国国家科学基金会;
关键词
parallel database system; join operation; performance evaluation; load balancing; sampling;
D O I
10.1006/jpdc.1998.1507
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
We investigate various load balancing approaches for hash-based join techniques popular in multicomputer-based shared-nothing database systems. When the tuples are not uniformly distributed among the hash buckets, redistribution of these buckets among the processors is necessary to maintain good system performance. Two recent load balancing techniques which rely on sampling and incremental balancing, respectively, have been shown to be more robust than conventional methods. The comparison of these two approaches, however, has not been investigated. In this study, we improve these two schemes and implement them along with a conventional method and a standard join technique which does not do load balancing on an nCUBE/2 parallel computer to compare their performance. Our experimental results indicate that the sampling technique is the better approach. To further evaluate the performance of these techniques under diverse hardware conditions, we also develop a cost model and implement a simulator to perform sensitivity analyses with respect to various hardware parameters. The simulation results show that both sampling and incremental techniques provide noticeable savings over conventional methods, with the sampling approach being more scalable in supporting very large database systems. (C) 1999 Academic Press.
引用
收藏
页码:17 / 46
页数:30
相关论文
共 26 条
[11]  
HUA KA, 1990, P INT COMP S HSINCH, P47
[12]  
HUA KA, 1990, P 16 VER LARG DAT BA, P493
[13]  
KITSUREGAWA M, 1990, P 16 INT C VER LARG, P210
[14]  
KITSUREGAWA M, 1983, NEW GENERAT COMPUT, V1, P66
[15]  
LAKSHMI S, 1988, P INT S DAT PAR DIST, P107
[16]  
Lee C., 1993, Proceedings. Ninth International Conference on Data Engineering (Cat. No.92CH3258-1), P411, DOI 10.1109/ICDE.1993.344040
[17]   EXPLOITING DATABASE PARALLELISM IN A MESSAGE-PASSING MULTIPROCESSOR [J].
LORIE, RA ;
DAUDENARDE, JJ ;
STAMOS, JW ;
YOUNG, HC .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 1991, 35 (5-6) :681-695
[18]   JOIN PROCESSING IN RELATIONAL DATABASES [J].
MISHRA, P ;
EICH, MH .
COMPUTING SURVEYS, 1992, 24 (01) :63-113
[19]  
*NCUBE, 1990, NCUBE 2 SUP TECHN OV
[20]  
REE DA, 1987, MULTICOMPUTER NETWOR