Abstract
In this paper, we describe our approach to optimization of query execution plans in XPRS, a multiuser parallel database system based on a shared memory multiprocessor and a disk array. The main difficulties in this optimization problem are the compile-time unknown parameters such as available buffer size and number of free processors, and the enormous search space of possible parallel plans. We deal with these problems with a novel two phase optimization strategy which dramatically reduces the search space and allows run time parameters without significantly compromising plan optimality. In this paper we present our two phase optimization strategy and give experimental evidence from XPRS benchmarks that indicate that it almost always produces optimal or close to optimal plans.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
A. Bhide and M. Stonebraker, “A performance comparision of two architectures for fast transaction processing,” inProc. 1988 IEEE Data Engineering Conf.
D. Bitton, et al., “Benchmarking database systems: A systematic approach,” inProc. 1983 VLDB Conf.
M. Blasgen, et al., “The convoy phenomenon,”Oper. Syst. Rev. vol. 13, no. 2, 1979.
G. Bultzingsloewen, “Optimizing SQL queries for parallel execution,”SIGMOD Rec. vol. 18, no. 4, 1989.
G. Copeland, et al., “Data placement in Bubba,” inProc. 1988 ACM-SIGMOD conf.
D. Cornell and P. Yu, “Integration of buffer manegement and query optimization in relation database environment,” inProc. 1989 VLDB Conf.
D. DeWitt, et al., “GAMMA: A high performance dataflow database machine,” inProc. 1986 VLDB Conf.
G. Graefe and K. Ward, “Dynamic query evaluation plans,” inProc. 1989 ACM-SIGMOD Conf.
W. Hong, “Exploiting inter-operation parellelism in XPRS,” inProc. 1992 ACM-SIGMOD Conf.
R. Katz, and W. Hong, “Performance implications of disk arrays to shared memory database machines,” to appear inDistributed Parallel Databases, 1992.
L. Mackert, et al., “Index scans using a finite LRU buffer: A validated I/O model,”ACM-TODS, Sept. 1989.
M. Murphy and D. Rotem, “Processor scheduling for multiprocessor joins,” inProc. 1989 IEEE Data Engineering Conf.
M. Murphy and M. Shan, “Execution plan balancing,” inProc. 1991 IEEE Data Engineering Conf.
D. Patterson, et al., “RAID: Reduntant arrays of inexpensive disks,” inProc. 1988 ACM-SIGMOD Conf.
J. Richardson, et al., “Design and evaluation of parallel pipelined join algorithms,” inProc. 1987 ACM-SIGMOD Conf.
D. Schneider and D. DeWitt, “A performance evaluation of four parellel join algorithms in a shared nothing environment,” inProc. 1989 ACM-SIGMOD Conf.
D. Schneider and D. DeWitt, “Tradeoffs in processing complex join queries via hashing in multiprocessor database machines,” inProc. 1990 VLDB Conf.
P. Selinger, et al., “Access path selection in a relational data base system,” inProc. 1979 ACM-SIGMOD Conf.
L. Shapiro, “Join processing in database systems with large main memories,”ACM-TODS, Sept. 1986.
M. Stonebraker, “The case for shared nothing,” inProc. 1986 IEEE Data Engineering Conf.
M. Stonebraker, et al., “The design of XPRS,” inProc. 1988 VLDB Conf.
H. Zeller and J. Gray, “An adaptive hash join algorithm for multiuser environments,” inProc. 1990 VLDB Conf.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Hong, W., Stonebraker, M. Optimization of parallel query execution plans in XPRS. Distrib Parallel Databases 1, 9–32 (1993). https://doi.org/10.1007/BF01277518
Issue Date:
DOI: https://doi.org/10.1007/BF01277518