The example of speculative execution for multiple query execution systems

• Autorzy: Sasak-Okoń A. , Brzuszek M.
• Języki publikacji: EN

Abstrakty

EN

There are different levels at which parallelism can be introduced to the database system but in general there are two types of parallel optimization tasks for databases. First, that is a speedup in query execution time. The second task is such a scaleup of the system that it was able to execute more tasks in the time unit. This situation is the subject of interest of the following paper. Authors introduce the parallelization method based on the speculative execution for the database systems which are expected to give answers to complex queries coming from different sources as soon as possible. Assume that W queries wait for execution and that the best execution plan developed by the DBMS for the first query does not use full available computing power. Thus, in parallel to the first query, some excessive computations can be executed, which in further steps would reduce the execution time of the consecutive queries increasing throughput of the system. The paper introduces the idea of speculative computations, presents possible risks and benefits of using this method and also an analyses of possible execution time reduction for different models of speculative parallelization .

Słowa kluczowe

EN

database; parallel query; speculative computations

PL

baza danych; zapytanie równoległe; obliczenia spekulacyjne

• Wydawca: Komisja Informatyki Polskiej Akademii Nauk, Oddział w Gdańsku
• Czasopismo: Metody Informatyki Stosowanej
• Rocznik: 2011
• Tom: nr 3
• Strony: 157--166
• Opis fizyczny: Bibliogr. 18 poz., rys.

Twórcy

autor

Sasak-Okoń A.

autor

Brzuszek M.

• Maria Curie Sklodowska University, Institute of Computer Science

Bibliografia

• [1] Pushpa R. Suri, S. R. Mechanisms for parallel query execution. Journal of Theoretical and Applied Information Technology 4, 547-553 (2006).
• [2] Mahdi Abdelguerfi, K.-F. W. Parallel database techniques. (Wiley – IEEE Computer Society, 1998).
• [3] David Kaeli, P.-C. Y. Speculative execution in high performance computer architectures. Chapman and Hall/CRC, 2005.
• [4] Philips S. Yu, M.-S. C., Joel L. Wolf, John Turek. in Advanced Database Systems. 229-258
• [5] Sunita Mahajan, V. P. J. A Survey of Issues of Query Optimization in Parallel Databases. International Journal of Computer Applications 11, 32-37 (2010).
• [6] Bhaskar Himatsingka, J. S., Thomas M. Niccum. Tradeoffs in Parallel Query Processing and its Implications for Query Optimization. University of Minnesota, 1994.
• [7] David Taniar, C. H. L., Wenny Rahayu, Sushant Goel. High-Performance Parallel Database Processing and Grid databases. John Wiley & Sons, 2008.
• [8] Hector Garcia-Molina, J. D. U., Jennifer Widom. Database Systems. The Complete Book., Pearson Education International, 2009.
• [9] Hector Garcia-Molina, J. D. U., Jennifer Widom Database System Implementation. WNT Warszawa, 2003.
• [10] Georgia Koutrika, A. S., Yannis E. Ioannidis. Explaining Structured Queries in Natural Language. ICDE, 333-344 (2010).
• [11] Antonio Badia, Springer. Quantifiers inAction. Generalized Quantification in Query, Logical and Natural Languages. (Springer, 2009).
• [12] Grama A., G., Karypis G. Kumar V. Introduction to Parallel Computing (Second Edition). (Addison-Wesley, 2003).
• [13] Neoklis Polyzotis, Y. I. in Online Proc. of the CIDR Conference (2003).
• [14] Greg Barish, C. A. K. in Artificial Intelligence (ed G. Barish, C.A. Knoblock, presented at Artif. Intell., 2008, pp.413-453. ) 413-453 (2008).
• [15] Vagelis Hristidis, Y. P. Algorithms and Applications for answering Ranked Queries using Ranked Views. The VLDB Journal 13 (2004).
• [16] Kostas Papadopoulos, K. S., Pedro Trancoso. in IEEE International Parallel Distributed Processing Symposium 1-11 (2008).
• [17] Anna Sasak-Okoń, M. B. Speculative parallelization for multiple query execution systems. Polish J. of Environ. Stud. 18, 321–326 (2009).
• [18] Galindo-Legaria C. A., R. A. in ACM SIGMOD International Conference on Management of Data. 291–299.