Spatial Processing using Oracle Table Functions

Spatial joins and spatial index creation are two of the most expensive operations in Oracle Spatial. Since spatial indexing is implemented in extensible indexing framework where queries only return rows from a single table, spatial joins could not be effectively and efficiently implemented in Oracle8i and prior releases. On the other hand, spatial index creation involves much computation or I/O that could be easily parallelized. In this paper, we describe how Oracle Spatial applies parallel and pipelined table function technology to perform fast spatial joins and parallel index creation. This technology has been introduced in Oracle9i and allows users to iteratively return subsets of result rows to be used in the “from” clause of a SQL query. We present our experiences with these implementations and examine the performance on real datasets.