Programming and Computer Software

, Volume 27, Issue 6, pp 297–308 | Cite as

Organization of Parallel Query Processing in Multiprocessor Database Machines with Hierarchical Architecture

  • L. B. Sokolinsky


The development of database systems with hierarchical hardware architecture is currently a perspective trend in the field of parallel database machines. Hierarchical architectures have been suggested with the aim to combine advantages of shared-nothing architectures and architectures with shared memory and disks. A commonly accepted way of construction of hierarchical systems is to combine shared-memory (shared-everything) clusters in a unique system without shared resources. However, such architectures cannot ensure data accessibility under hardware failures on the processor cluster level, which limits their use in systems with high fault-tolerance requirements. In this paper, an alternative approach to construction of hierarchical systems is suggested. In accordance with this approach, the systems is constructed as an assembly of processor clusters with shared disks, with each cluster being a two-level multiprocessor structure with a standard strongly connected topology of interprocessor connections. A stream model for organization of parallel query processing in systems with the hierarchical architecture suggested is described. This model has been implemented in a prototype parallel database management system Omega designed for Russian multiprocessor computational systems MBC-100/1000. Our experiments show that the total performance of the processor clusters in the Omega system is comparable with that of the processor clusters with shared resources even in the case of great data skew. At the same time, the clusters of the Omega system are capable of ensuring a higher degree of data availability compared to the clusters with shared-memory architectures.


Shared Memory Shared Resource Hardware Architecture Database Management System Hierarchical System 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Stonebraker, M., The Case for Shared Nothing, Database Eng. Bull., 1986, vol. 9, no. 1, pp.4–9.Google Scholar
  2. 2.
    Valduriez, P., Parallel Database Systems: The Case for Shared-Something, Proc. 9th Int. Conf. on Data Eng., Vienna: IEEE Computer Society, 1993, pp. 460–465.Google Scholar
  3. 3.
    Thakkar, S.S. and Sweiger, M., Performance of an OLTP Application on Symmetry Multiprocessor System, Proc. 17th Annual Int. Symp. on Computer Architecture, Seattle: IEEE Computer Society, 1990, pp. 228–238.Google Scholar
  4. 4.
    Pfister, G., Sizing Up Parallel Architectures, Database Programming and Design OnLine (, 1998, vol. 11, no.5.Google Scholar
  5. 5.
    Golubchik, L. and Muntz, R.R., Fault Tolerance Issues in Data Declustering for Parallel Database Systems, Data Eng. Bull., 1994, vol.17, no. 3, pp. 14–28.Google Scholar
  6. 6.
    Mohan, C., Pirahesh, H., Tang, W.G., and Wang, Y., Parallelism in Relational Database Management Systems, IBM Syst. J., 1994, vol. 33, no. 2, pp. 349–371.Google Scholar
  7. 7.
    Stonebraker, M. and Hellerstein, J.M., Introduction to Chapter 5: Parallel Database Systems, in Readings in Database Systems, Morgan Kauffman, 1998, 3d Ed., pp. 399–402.Google Scholar
  8. 8.
    Lakshmi, M.S. and Yu, P.S., Effectiveness of Parallel Joins, IEEE Trans. Knowledge Data Eng., 1990, vol. 2, no. 4, pp. 410–424.Google Scholar
  9. 9.
    Bhide, A., An Analysis of Three Transaction Processing Architectures, Proc. Fourteenth Int. Conf. on Very Large Data Bases (VLDB'88), Los Angeles: Morgan Kauffman, 1988, pp. 339–350.Google Scholar
  10. 10.
    Bouganim, L., Florescu, D., and Valduriez, P., Dynamic Load Balancing in Hierarchical Parallel Database Systems, Proc. 22th Int. Conf. on Very Large Data Bases (VLDB'96), Mumbai, India, 1996, pp. 436–447.Google Scholar
  11. 11.
    Hua, K.A., Lee, C., and Peir, J.-K., Interconnecting Shared-Everything Systems for Efficient Parallel Query Processing, Proc. First Int. Conf. on Parallel and Distributed Information Systems (PDIS 1991), Miami Beach, IEEE-CS, 1991, pp. 262–270.Google Scholar
  12. 12.
    Xu, Y. and Dandamudi, S.P., Performance Evaluation of a Two-Level Hierarchical Parallel Database System, Proc. Int. Conf. Computers and Their Applications, Tempe, Arizona, 1997, pp. 242–247.Google Scholar
  13. 13.
    Bitton, D. and Gray, J., Disk Shadowing, Proc. Fourteenth Int. Conf. on Very Large Data Bases (VLDB'88), Los Angeles: Morgan Kauffman, 1988, pp. 331–338.Google Scholar
  14. 14.
    Patterson, D.A., Gibson, G.A., and Katz, R.H., A Case for Redundant Arrays of Inexpensive Disks (RAID), Proc. 1988 ACM SIGMOD Int. Conf. on Management of Data, Chicago: ACM Press, 1988, pp. 109–116.Google Scholar
  15. 15.
    Sokolinsky, L.B., Choosing Multiprocessor System Architecture for Parallel Database Systems, Proc. 2nd Int. Workshop on Comput. Sci. and Inform. Technologies (CSIT'2000), Ufa, Russia, 2000.Google Scholar
  16. 16.
    Sokolinsky, L.B., Axenov, O., and Gutova, S., Omega: The Highly Parallel Database System Project, Proc. First East-European Symp. on Advances in Database and Inform. Syst. (ADBIS'97), St. Petersburg, 1997, vol. 2, pp. 88–90.Google Scholar
  17. 17.
    Levin, V.K., Russian Supercomputers of the MBC family, Scholar
  18. 18.
    Sokolinsky, L.B., Operating System Support for a Parallel DBMS with a Hierarchical Shared-Nothing Architecture, Advances in Databases and Information Systems (Third East European Conf., ADBIS'99), Maribor, Slovenia, 1999. Proc. of Short Papers, Maribor: Institute of Informatics. 1999, pp. 38–45.Google Scholar
  19. 19.
    Stonebraker, M., Operating System Support for Database Management, Commun. ACM, 1981, vol. 24, no. 7, pp. 412–418.Google Scholar
  20. 20.
    Sokolinsky, L.B., Interprocessor Communication Support in the Omega Parallel Database System, Proc. 1st Int. Workshop on Comput. Sci. and Inform. Technologies (CSIT'99), Moscow: MEPhl Publishing, 1999, vol. 2.Google Scholar
  21. 21.
    Zymbler, M. and Sokolinsky, L.B., Implementation Principles of File Management System for Omega Parallel DBMS, Proc. 2nd Int. Workshop on Comput. Sci. and Inform. Technologies (CSIT'2000), Ufa, Russia, 2000.Google Scholar
  22. 22.
    Williams, M.H. and Zhou, S., Data Placement in Parallel Database Systems, in Parallel Database Techniques, IEEE Computer Society, 1998, pp. 203–218.Google Scholar
  23. 23.
    Graefe, G., Query Evaluation Techniques for Large Databases, ACM Computing Surveys, 1993, vol. 25, no. 2, pp. 73–169.Google Scholar
  24. 24.
    DeWitt, D.J., et al., The Gamma Database Machine Project, IEEE Trans. Knowledge Data Eng., 1990, vol. 2, no. 1, pp. 44–62.Google Scholar
  25. 25.
    Boral, H., Alexander, W., Clay, L., Copeland, G., Sanforth, S., Franklin, M., Hart, B., Smith, M., and Valduriez, P., Prototyping Bubba: A Highly Parallel Database System, IEEE Trans. Knowledge Data Eng., 1990, vol. 2, no. 1, pp. 4–24.Google Scholar
  26. 26.
    Graefe, G., Encapsulation of Parallelism in the Volcano Processing Systems, Proc. 1990 ACM SIGMOD Int. Conf. on Management of Data, Atlantic City: ACM Press, 1990, pp. 102–111.Google Scholar
  27. 27.
    Lymar, T.Y. and Sokolinsky, L.B., Data Streams Organizations in Query Executor for Parallel DBMS, Databases and Information Systems, Proc. 4th IEEE Int. Baltic Workshop, Vilnius: Technica, 2000, vol. 1, pp. 85–88.Google Scholar

Copyright information

© MAIK “Nauka/Interperiodica” 2001

Authors and Affiliations

  • L. B. Sokolinsky
    • 1
  1. 1.Chelyabinsk State UniversityChelyabinskRussia

Personalised recommendations