Advertisement

Validated Cost Models for Parallel OQL Query Processing

  • Sandra F. Mendes de Sampaio
  • Norman W. Paton
  • Jim Smith
  • Paul Watson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2425)

Abstract

Query cost models are widely used, both for performance analysis and for comparing execution plans during query optimisation. In essence, a cost modelp redicts where time is being spent during query evaluation. Although many cost models have been proposed, for serial, parallel and distributed database systems, surprisingly few of these have been validated against real systems. This paper presents cost models for the parallel evaluation of ODMG OQL queries, which have been compared with experimental results obtained using the Polar object database system. The paper describes the validation of the cost model for a collection of queries, using three join algorithms over the OO7 benchmark database. The results show that the cost model generally both ranks alternative plans appropriately, and gives a useful indication of the response times that can be expected from a plan. The paper also illustrates the application of the cost model by highlighting the contributions of different features and operations to query response times.

Keywords

Cost Model Hash Table Query Response Time Distribute Database System Bucket Size 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    R. Braumandl, J. Claussen, A. Kemper, and D. Kossmann. Functional-join processing. VLDB Journal, 8(3–4):156–177, 2000. 61CrossRefGoogle Scholar
  2. 2.
    P. A. Buhr, A. K. Goel, N. Nishimura, and P. Ragde. Parallel pointer-based join algorithms in memory-mapped environments. In Proceedings of ICDE, pages 266–275, 1996. 60Google Scholar
  3. 3.
    M. Carey, D. J. DeWitt, and J. F. Naughton. The OO7 benchmark. In ACM SIGMOD, pages 12–21, 1993. 70Google Scholar
  4. 4.
    S. Cluet and C. Delobel. A general framework for the optimization of objectoriented queries. In Proceedings of the ACM SIGMOD Conference, page 383, San Diego, CA, June 1992. 61Google Scholar
  5. 5.
    D. J. DeWitt, D. F. Lieuwen, and M. Mehta. Pointer-based join techniques for object-oriented databases. In Proc. of the 2nd Int. Conference on Parallel and Distributed Information Systems (PDIS), pages 172–181. IEEE-CS, 1993. 60, 61, 67Google Scholar
  6. 6.
    G. Graefe. Encapsulation of parallelism in the Volcano query processing system. In ACM SIGMOD, pages 102–111, 1990. 61Google Scholar
  7. 7.
    M. Metha and D. J. DeWitt. Data placement in shared-nothing parallel database systems. VLDB Journal, 6(1):53–72, 1997. 60CrossRefGoogle Scholar
  8. 8.
    S. F. M. Sampaio, N. W. Paton, P. Watson, and J. Smith. A parallel algebra for object databases. In Proc. 10th DEXA Workshop, pages 56–60. IEEE Press, 1999. 61, 62Google Scholar
  9. 9.
    E. Shekita and M. J. Carey. A performance evaluation of pointer-based joins. In Proc. ACM SIGMOD, pages 300–311, 1990. 61Google Scholar
  10. 10.
    J. Smith, S. F. M. Sampaio, P. Watson, and N. W. Paton. Polar: An architecture for a parallel ODMG compliant object database. In Proc. ACM CIKM, pages 352–359. ACM press, 2000. 61Google Scholar
  11. 11.
    A. N. Wilschut, J. Flokstra, and P. M. G. Apers. Parallel evaluation of multi-join queries. In Proc. ACM SIGMOD, pages 115–126. ACM Press, 1995. 60Google Scholar
  12. 12.
    S. Bing Yao. Approximating block accesses in database organizations. Communications of the ACM, 20(4):260–261, 1977. 67zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Sandra F. Mendes de Sampaio
    • 1
  • Norman W. Paton
    • 1
  • Jim Smith
    • 2
  • Paul Watson
    • 2
  1. 1.Department of Computer ScienceUniversity of ManchesterManchesterUK
  2. 2.Department of Computing ScienceUniversity of Newcastle upon TyneNewcastleUK

Personalised recommendations