|Nguyen, Andre B.: Optimized Scheduling of Load Processes in IBM DB2 Analytics Accelerator. |
Universität Stuttgart, Fakultät Informatik, Elektrotechnik und Informationstechnik, Bachelorarbeit Nr. 1 (2014).
104 Seiten, englisch.
|CR-Klassif.||I.7.2 (Document Preparation)|
The DB2 Analytics Accelerator for z/OS is a high-performance appliance to accelerate the processing of analytical queries of enormous data volumes by combining IBMs DB2 database with Netezzas Data Warehouse appliance. Netezza specializes in efficient computations of complex queries. Prior to the query processing on the Netezza system, tables on DB2 need to be loaded to Netezza and kept in sync periodically. As of now, the table load algorithm indicates few weaknesses that stall the query processing. An advanced scheduler for table loading would help improve data throughput, optimally limiting resource usage in the process. The thesis discusses concepts that accelerate table loading in IDAA by introducing improvements to the prevalent algorithm. The original scheduling of IDAA is enhanced in assistance of a prototype that relies on a performance analysis and simulation techniques. The current algorithm is integrated in the simulator and will be replaced by a more advanced algorithm. Consequently, different algorithms can be easily integrated, tested and evaluated.
|Abteilung(en)||Universität Stuttgart, Institut für Parallele und Verteilte Systeme, Anwendersoftware|
|Betreuer||Schwarz, PD Dr. Holger; Kern, Johannes|
|Eingabedatum||16. November 2018|