The Workload Adaptation in Autonomic DBMSs Based on Layered Queuing Network Model

Modern network computing is in the process of changing from manual management to autonomic computing. As the core of network computing, database management system with autonomic computing must be able to participate in the process to meet the performance requirements of the network applications. This paper studies on workload adaptation technology. In the workload adaptation framework, the performance forecasting component is the base of developing workload control scheme. Layered queuing network modeling techniques was used to establish the performance model of DBMS. A test platform based on this architecture has been built and been tested. Test result shows that this framework has played an effective role in workload control, and improved client satisfaction rate and the application performance of the network.