Title :
Informix parallel data query (PDQ)
Author_Institution :
Sequent Comput. Syst., Beaverton, OR, USA
Abstract :
The PDQ project, which enables the Informix relational DBMS to perform parallel query evaluation on shared memory multiprocessors, is discussed. It is built on the Informix multithreaded server, which provides efficient creation and synchronization of parallel threads. The operators that are parallelized include scan, sort, join, and aggregate. Parallelization is achieved through the use of horizontal table partitioning and the exchange operator, which was developed as part of the Volcano research DBMS. The exchange operator initiates parallel threads, manages data flow between threads, and provides for partitioning of data among threads
Keywords :
distributed databases; parallel programming; query processing; relational databases; shared memory systems; Informix multithreaded server; Informix relational DBMS; PDQ project; Volcano research DBMS; aggregate; data flow; exchange operator; horizontal table partitioning; join; parallel query evaluation; parallel threads; scan; shared memory multiprocessors; sort; synchronization; Concurrent computing; Network servers; Operating systems; Performance evaluation; Prototypes; Query processing; Runtime; Switches; Volcanoes; Yarn;
Conference_Titel :
Parallel and Distributed Information Systems, 1993., Proceedings of the Second International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-8186-3330-1
DOI :
10.1109/PDIS.1993.253069
