Towards Adaptive Costing of Database Access Methods

Most database query optimizers use cost models to identify good query execution plans. Inaccuracies in the cost models can cause query optimizers to select poor plans. In this paper, we consider the problem of accurately estimating the I/O costs of database access methods, such as index scans. We present some experimental results which show that existing analytical I/O cost models can be very inaccurate. We also present a simple analysis which shows that larger cost estimation errors can cause the query optimizer to make larger mistakes in plan selection. We propose the use of an adaptive black-box statistical cost estimation methodology to achieve better estimates.