On Creating Efficient Object-relational Views of Scientific Datasets

Scientific datasets are often large and distributed in flat files across several storage nodes. Scientists frequently want to analyze subsets of these datasets. A data source abstraction that provides an object-relational view of data while hiding the details of storage and transport mechanisms and dataset layouts is useful in this regard. In this abstraction, basic data sources (BDS) interpret flat files as a set of records and are the building blocks of the view mechanism. Derived data sources (DDS) may be built on top of BDSs and provide more complex objects that serve the scientists' needs. The simplest DDS is one that supports a join based view over BDSs. We investigate issues involving building such DDSs for scientific applications and consider distributed versions of the indexed join and the grace hash join algorithms. We construct cost models that capture their performance in a restricted space of dataset and system parameters and compare them analytically and experimentally