Automatically classifying database workloads
Proceedings of the eleventh international conference on Information and knowledge management
Towards Automated Performance Tuning for Complex Workloads
VLDB '94 Proceedings of the 20th International Conference on Very Large Data Bases
Analysis of locking behavior in three real database systems
The VLDB Journal — The International Journal on Very Large Data Bases
| Hi-index | 0.00 |
The DBMS performance might change by allocating resources and by performing a specific kind of workload. Database administrators should be able to identify relative resources that can change DBMS performance in order to effectively manage database systems. This paper aims to identify the relative resources that can affect the DBMS performance depending on the different kinds of workload. The relative resource is identified by the incremental or the decremental relationship between the performance indicator and the resource. The relationship is determined by the Pearson's correlation coefficient with the t-test. We identify the relative resources that have an impact on the DBMS performance under TPC-C and TPC-W benchmarks using our proposed method. As a result, the data buffer and the shared memory could affect the DBMS performance in TPC-C, and only the data buffer in TPC-W. In order to verify our works, we measure the maximum load that can be executed in the individual system for TPC-C and TPC-W.