Use of inherent parallelism in database operations

  • T. Härder
  • Ch. Hübel
  • B. Mitschang
Nonnumerical Algorithms (Session 5.2)
Part of the Lecture Notes in Computer Science book series (LNCS, volume 237)

Abstract

Non-standard applications of database systems (e.g. CAD) are characterized by complex objects and powerful user operations. Units of work decomposed from a single user operation are said to allow for inherent semantic parallelism when they do not conflict with each other at the level of decomposition. Hence, they can be scheduled concurrently. In order to support this processing scheme it is necessary to organize parallel execution by adequate control units. Therefore, client-server processes and nested transactions are applied to hierarchically structure the DBS-operations. On the other hand, the DBS-code itself has to be mapped onto a multiprocessor system to take advantage of multiple processing units.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. AS83.
    Andrews, G.R., Schneider, F.B.: Concepts and Notations for Concurrent Programming, in: ACM Computer Surveys, Vol. 15, No. 1, March 1983, S. 3–43.Google Scholar
  2. DW79.
    DeWitt, D.J.: DIRECT — A Multiprocessor Organization for Supporting Relational Database Management Systems, in: IEEE Trans. on Computers, Vol. 28, No. 6, 1979, pp. 395–405.Google Scholar
  3. Hä86.
    Härder, T.: DB-Sharing vs. DB-Distribution — die Frage nach dem Systemkonzept zukünftiger DB/DC-Systeme, in: Proc. 9. NTG/GI-Fachtagung "Architektur und Betrieb von Rechensystemen", Stuttgart, März 1986.Google Scholar
  4. HR83.
    Härder, T., Reuter, A.: Principles of Transaction-Oriented Database Recovery, in: ACM Computing Surveys, Vol. 15, No. 4, Dec. 1983, pp. 287–317.Google Scholar
  5. HR85.
    Härder, T., Reuter, A.: Architektur von Datenbanksystemen für Non-Standard-Anwendungen, in: Proc. GI-Fachtagung "Datenbanksysteme in Büro, Technik und Wissenschaft", März 1985, Karlsruhe (eingeladener Vortrag), IFB 94, S. 253–286.Google Scholar
  6. Re86.
    Reuter, A.: Load Control and Load Balancing in a Shared Database Management System, in: Proc. Int. Conf. on Data Engineering, Los Angeles, Feb. 1986.Google Scholar
  7. Wa84.
    Walter, B.: Nested Transactions with Multiple Commit Points: An Approach to the Structure of Advanced Database Applications, in: Proc. 10th Int. Conf. on VLDB, Singapore, 1984,, pp. 161–171.Google Scholar
  8. WS84.
    Weikum, G., Schek, H.-J.: Architectural Issues of Transaction Management in Layered Systems, in: Proc. 10th Int. Conf. on VLDB, Singapore, 1984, pp. 454–465.Google Scholar

Copyright information

© Springer-Verlag 1986

Authors and Affiliations

  • T. Härder
    • 1
  • Ch. Hübel
    • 1
  • B. Mitschang
    • 1
  1. 1.University KaiserslauternGermany

Personalised recommendations