Performance analysis of a relational data base management system

ABSTRACT

The effect on the performance of data management systems of the use of extended storage devices, multiple processors and prefetching data blocks is analyzed with respect to one system, INGRES. Benchmark query streams, derived from user queries, were run on the INGRES system and their CPU usage and data reference patterns traced. The results show that the performance characteristics of two query types: data-intensive queries and overhead-intensive queries, are so different that it may be difficult to design a single architecture to optimize the performance of both types. It is shown that the random access model of data references holds only for overhead-intensive queries, and then only if references to system catalogs are not considered data references. Significant sequentiality of reference was found in the data-intensive queries. It is shown that back-end data management machines that distribute processing toward the data may be cost effective only for data-intensive queries. It is proposed that the best method of distributing the processing of the overhead-intensive query is through the use of intelligent terminals. A third benchmark set, multi-relation queries, was devised, and proposals are made for taking advantage of the locality of reference which was found.

REFERENCES

• 1: Eric Allman , Michael Stonebraker , Gerald Held, Embedding a relational data sublanguage in a general purpose programming language, Proceedings of the 1976 conference on Data : Abstraction, definition and structure, p.25-35, March 22-24, 1976, Salt Lake City, Utah, United States
• 2: {BLAS76} Blasgen, M.W. and Eswaren, K.P., "On the Evaluation of Queries in a Relational Data Base System," IBM Research Report RJ-1745, April, 1976.
• 3: Peter J. Denning, The working set model for program behavior, Communications of the ACM, v.11 n.5, p.323-333, May 1968 [doi>10.1145/363095.363141]
• 4: David J. DeWitt, DIRECT - a multiprocessor organization for supporting relational data base management systems, Proceedings of the 5th annual symposium on Computer architecture, p.182-189, April 03-05, 1978 [doi>10.1145/800094.803046]
• 5: {EPST77} Epstein, R., "Creating and Maintaining a Database Using INGRES," Electronics Research Laboratory, University of California, Berkeley, Ca., Memo #M77-71, Dec. 1977.
• 6: {GRAY78} Gray, James, "Notes on Data Base Operating Systems," IBM Research Report RJ2188 (30001) 2/23/78.
• 7: Tomás Lang , Christopher Wood , Eduardo B. Fernández, Database buffer paging in virtual storage systems, ACM Transactions on Database Systems (TODS), v.2 n.4, p.339-351, Dec. 1977 [doi>10.1145/320576.320585]
• 8: E. A. Ozkarahan , S. A. Schuster , K. C. Sevcik, Performance evaluation of a relational associative processor, ACM Transactions on Database Systems (TODS), v.2 n.2, p.175-195, June 1977 [doi>10.1145/320544.320553]
• 9: {RODR76} Rodriguez-Rosell, Juan, "Empirical Data Reference Behavior in Data Base Systems," Computer, Nov., 1976, Pages 9--13.
• 10: {REIT76} Reiter, Allen, "A Study of Buffer Management Policies for Data Management Systems," Mathematics Research Center, University of Wisconsin-Madison, Technical Summary Report # 1619, March 1976.
• 11: Dennis M. Ritchie , Ken Thompson, The UNIX time-sharing system, Communications of the ACM, v.17 n.7, p.365-375, July 1974 [doi>10.1145/361011.361061]
• 12: Stephen W. Sherman , Richard S. Brice, Performance of a database manager in a virtual memory system, ACM Transactions on Database Systems (TODS), v.1 n.4, p.317-343, Dec. 1976 [doi>10.1145/320493.320494]
• 13: {SMIT76} Smith, Alan Jay, "Sequentiality and Prefetching in Data Base Systems," IBM Research Report RJ 1743, March 19, 1976.
• 14: Michael Stonebraker , Gerald Held , Eugene Wong , Peter Kreps, The design and implementation of INGRES, ACM Transactions on Database Systems (TODS), v.1 n.3, p.189-222, Sept. 1976 [doi>10.1145/320473.320476]
• 15: {TUEL76} Tuel, W. G. Jr., "An analysis of Buffer Paging in Virtual Storage Systems," IBM Journal of Research and Development, Vol. 20, No.5, September 1976.
• 16: Eugene Wong , Karel Youssefi, Decomposition—a strategy for query processing, ACM Transactions on Database Systems (TODS), v.1 n.3, p.223-241, Sept. 1976 [doi>10.1145/320473.320479]
• 17: S. Bing Yao , David DeJong, Evaluation of database access paths, Proceedings of the 1978 ACM SIGMOD international conference on management of data, May 31-June 02, 1978, Austin, Texas [doi>10.1145/509252.509273]
• 18: {YOUS78} Youssefi, Karel A., "Query Processing for a Relational Database System," Electronics Research Laboratory, University of California, Berkeley, Ca., Memo #M78-3.