Advertisement

Least Likely to Use: A New Page Replacement Strategy for Improving Database Management System Response Time

  • Rodolfo A. Pazos R.
  • Joaquín Pérez O.
  • José A. Martínez F.
  • Juan J. González B.
  • Mirna P. Ponce F.
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3967)

Abstract

Since operating systems (OSs) file systems are designed for a wide variety of applications, their performance may become suboptimal when the workload has a large proportion of certain atypical applications, such as a database management system (DBMS). Consequently most DBMS manufacturers have implemented their own file manager relegating the OS file system. This paper describes a novel page replacement strategy (Least Likely to Use) for buffer management in DBMSs, which takes advantage of very valuable information from the DBMS query planner. This strategy was implemented on an experimental DBMS and compared with other replacement strategies (LRU, Q2 and LIRS) which are used in OSs and DBMSs. The experimental results show that the proposed strategy yields an improvement in response time for most types of queries and attains a maximum of 97-284% improvement for some cases.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Andy Riebs and Compaq Computer Corporation. The Open Source Database Benchmark (2005), http://osdb.sourceforge.net/
  2. 2.
    Bressan, S., Goh, C.L., Ooi, B.C., Tan, K.: A Framework for Modeling Buffer Replacement Strategies. In: Proc. Ninth International Conference on Information and Knowledge Management, McLean, Virginia, USA, pp. 62–69 (2000)Google Scholar
  3. 3.
    Butt, A.R., Gniady, C., Hu, Y.C.: The Performance Impact of Kernel Prefetching on Buffer Cache Replacement Algorithms. In: Proc. ACM SIGMETRICS, Banff, Canada, pp. 157–168 (2005)Google Scholar
  4. 4.
    Cooksey, R.: Content-Sensitive Data Prefetching. PhD dissertation, University of Colorado, Colorado, USA (2002)Google Scholar
  5. 5.
    Dan, A., Yu, P.S., Chung, J.: Characterization of Database Access Pattern for Analytic Prediction of Buffer Hit Probability. VLDB Journal 4(1), 127–154 (1995)CrossRefGoogle Scholar
  6. 6.
    Effelsberg, W.: Principles of Database Buffer Management. ACM Transactions on Database Systems 9(4), 560–595 (1984)CrossRefGoogle Scholar
  7. 7.
    Jeon, S.H., Noh, S.H.: A Database Disk Buffer Management Algorithm Based on Prefetching. In: Proc. ACM CIKM, Bethesda, USA, pp. 167–174 (1998)Google Scholar
  8. 8.
    Jiang, S., Zhang, X.: LIRS: An Efficient Low Inter-Reference Recency Set Replacement Policy to Improve Buffer Cache Performance. In: Proc. ACM SIGMETRICS, Marina del Rey, USA, pp. 31–42 (2002)Google Scholar
  9. 9.
    Johnson, T., Shasha, D.: 2Q: A Low Overhead High Performance Buffer Management Replacement Algorithm. In: Proc. VLDB, Santiago de Chile, Chile, pp. 439–450 (1994)Google Scholar
  10. 10.
    Juurlink, B.: Approximating the Optimal Replacement Algorithm. In: Proc. Conf. Computing Frontiers, Ischia, Italy, pp. 313–319 (2004)Google Scholar
  11. 11.
    Smaragdakis, Y.: General Adaptive Replacement Policies. In: Proc. Fourth International Symposium on Memory Management ISMM, Vancouver, Canada, pp. 108–119 (2004)Google Scholar
  12. 12.
    Traub, O., Lloyd, A., Ledlie, J.: Application-Specific File Caching for Unmodified Applications and Kernels. Technical Report, MIT, Massachusetts, USA (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Rodolfo A. Pazos R.
    • 1
  • Joaquín Pérez O.
    • 1
  • José A. Martínez F.
    • 1
    • 2
  • Juan J. González B.
    • 2
  • Mirna P. Ponce F.
    • 2
  1. 1.Centro Nacional de Investigación y Desarrollo TecnológicoCuernavaca, MorelosMexico
  2. 2.Instituto Tecnológico de Cd.Madero, Cd. Madero, Tamps.Mexico

Personalised recommendations