Workload Characterization of Autonomic DBMSs Using Statistical and Data Mining Techniques

Abstract

In this paper a model where an autonomic DBMS can identify and characterize the type of workload acting upon it is developed and the most important database status variables which are highly affected by changing workloads are identified. Two algorithms are selected for database workload classification: hierarchical clustering and classification & regression tree for classifying database workloads after running database workloads from TPC (Transaction Processing Performance Council) benchmark queries and transactions. The costs of these workloads are measured in terms of status variables of MySQL. A set of extensive experiments and analyses have been conducted and the results are presented in this paper.