Abstract

We present GridDB, a data-centric overlay for scientific grid data analysis. In contrast to currently deployed process-centric middleware, GridDB manages data entities rather than processes. GridDB provides a suite of services important to data analysis: a declarative interface, type-checking, interactive query processing, and memoization. We discuss several elements of GridDB: workflow/data model, query language, software architecture and query processing; and a prototype implementation. We validate GridDB by showing its modeling of real-world physics and astronomy analyses, and measurements on our prototype.

Citations