Quarterly Technical Report. Massive Data Analysis Systems.

Abstract : The creation of a Massive Data Analysis System (MDAS) will enable new modes of science through improved data management of scientific data sets. This requires a scalable software infrastructure that can manage petabytes of data, support rapid access of selected data sets, and provide support for subsequent computationally intensive analyses. To accomplish this, object-relational database technology is being integrated with archival storage systems. By supporting transportable methods for manipulating the data, it then becomes possible to analyze selected data sets on remote systems. The MDAS becomes a scheduling system, managing the flow of data and computation across distributed resources. Usage models are needed that simplify the identification, transport and analysis of large collections of data. The system must automate the collection of metadata describing the data set attributes, and handle interactive WEB access, distributed database access, and discipline specific application interfaces. A software infrastructure has been designed which manages user access restrictions, matches application requirements with resource availability, and schedules the data movement and application execution. Development of this software system is proceeding on schedule, with selected applications testing the initial prototypes.