Skip to main content
SpringerLink
Log in

Randomized parallel prefetching and buffer management

  • Workshop on Randomized Parallel Computing Panos Pardalos, University of Florida, Gainesville Sanguthevar Rajasekaran, University of Florida, Gainesville
  • Conference paper
  • First Online:
Parallel and Distributed Processing (IPPS 1998)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1388))

Included in the following conference series:

Abstract

We show that deterministic algorithms using bounded lookahead cannot fully exploit the potential of a parallel I/O system. Randomization can be used to significantly improve the performance of parallel prefetching and buffer management algorithms. Using randomization in the data layout and a simple prefetching scheme, we show that a readonce reference string of length N can be serviced in θ(N/D) parallel I/Os in a D-disk system. For the case of read-many reference strings we introduce a novel algorithm using randomized write-back with a competitive ratio of θ(D). In contrast, we show that deterministic write-back results in a competitive ratio of at least (D).

Supported in part by NSF Grant CCR-9704562 and a grant from the Schlumberger Foundation.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Albers, S.: The influence of lookahead in competitive paging algorithms. Proc. 1st European Symp. on Algorithms, LNCS, Springer Verlag, (1993) 1–12

    Google Scholar 

  2. Barve, R. D., Grove, E. F., and Vitter, J. S.: Simple Randomized Mergesort on Parallel Disks. Parallel Computing, 23(4) (1997) 601–631

    Article  Google Scholar 

  3. Barve, R. D., Kallahalla, M., Varman, P. J., and Vitter, J. S.: Competitive Parallel Disk Prefetching and Buffer Management. Fifth Annual Workshop on I/O in Parallel and Distributed Systems, ACM (1997) 47–56

    Google Scholar 

  4. Belady, L. A.: A Study of Replacement Algorithms for Virtual Storage. IBM Systems Journal, 5 (1866) 78–101

    Google Scholar 

  5. Breslauer, D.: On Competitive On-Line Paging With Lookahead. Proc. Symp. Theoretical Aspects of Computer Science (1996) 593–603

    Google Scholar 

  6. Cao, P., Felten, E., Karlin, A., and Li, K.: A Study of Integrated Prefetching and Caching Strategies. Proc. ACM SIGMETRICS Conf. on Measurement and Modeling of Computer Systems (1995) 188–197

    Google Scholar 

  7. Chen, P. M., Lee, E. K., Gibson, G. A., Katz, R. H., and Patterson. D. A.: RAID: High-Performance Reliable Secondary Storage. ACM Computing Surveys 26(2) (1994) 145–185

    Article  Google Scholar 

  8. Fiat, A., Karp, R., Luby, M., McGeoch, L., Sleator, D. D., and Young, N. E: Competitive Paging Algorithms. J. Algorithms 12 (1991) 685–699

    Article  Google Scholar 

  9. Kallahalla, M.: Competitive Prefetching and Buffer Management for Parallel I/O Systems Masters Thesis, Rice University (1997)

    Google Scholar 

  10. Kallahalla, M., and Varman, P. J.: Improving Competitiveness of Parallel-Disk Buffer Management Using Randomized Write-back. Tech. report, Dept. of Electrical and Computer Engineering, Rice University (1997)

    Google Scholar 

  11. Kimbrel, T., and Karlin, A.: Near Optimal Parallel Prefetching and Caching. 37th Ann. Symp. on Foundations of Computer Science (1996)

    Google Scholar 

  12. McGeoch, L. A., and Sleator, D. D.: A Strongly Competitive Randomized Paging Algorithm Algorithmica 6 (1991) 816–825

    Article  Google Scholar 

  13. Pai, V. S., Schäffer, A. A, and Varman, P. J.: Markov Analysis of Multiple-Disk Prefetching Strategies for External Merging. Theoretical Computer Science 128(1-2) (1994) 211–239

    Article  Google Scholar 

  14. Sleator, D. D., and Tarjan, R. E.: Amortized Efficiency of List Update and Paging Rules. Comm. ACM 28(2) (1985) 202–208

    Article  Google Scholar 

  15. Varman, P. J., and Verma, R. M.: Tight Bounds for Prefetching and Buffer Management Algorithms for Parallel I/O Systems. Proc. of the 1996 Symp. on Foundations of Software Tech. and Theoretical Computer Science, LNCS 1180 (1996)

    Google Scholar 

  16. Vitter, J. S., and Shriver, E. A. M.: Optimal Algorithms For Parallel Memory 1: Two-Level Memories. Algorithmica 12(2-3) (1994) 110–147 *** DIRECT SUPPORT *** A0008D07 00013

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Rice University, 77005, Houston, TX, USA

    Peter J. Varman

Authors
  1. Peter J. Varman
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

José Rolim

Rights and permissions

Reprints and permissions

Copyright information

© 1998 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Varman, P.J. (1998). Randomized parallel prefetching and buffer management. In: Rolim, J. (eds) Parallel and Distributed Processing. IPPS 1998. Lecture Notes in Computer Science, vol 1388. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64359-1_708

Download citation

  • DOI: https://doi.org/10.1007/3-540-64359-1_708

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-64359-3

  • Online ISBN: 978-3-540-69756-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation