Modeling and optimization of complex database queries in a shared-nothing system

The author introduces queueing network models for the optimization of the concurrent evaluation of complex database queries, which occur e.g. in deductive query processing. The basic principle for the optimization is the reduction of response time by a better load distribution. If data access leads to a bottleneck on any CPU, response time may possibly be reduced by a preceding dynamic replication of one or more tables, whose accesses make up the bottleneck, to a disc managed by a lighter loaded CPU. For the comparison of alternative concurrent execution plans only queueing network models give quantitative results, which consider the contention on resources like CPU or disc.<
>