Cluster-Based Repositories and Analysis

This effort focuses on building a distributed data warehouse infrastructure running on an inexpensive cluster of processors and free-to-use, open source software, using the following components: Linux (operating system), openMosix (Cluster Software), andmySQL (Database Management Software.) In order for the system to perform as a single cohesive unit, a number of custom components will also have to be developed. Many organizations collect vast amounts of data for a variety of purposes, includingresource exploration, market forecasting, intelligence analysis, or process management. In a number of industries, such as Pharmaceuticals, or disciplines such as Cancer or AIDS Research, BioInformatics, or Seismology, relatively massive primary data isroutines collected from actual events - such as patient response to drug cocktails, results of research experiments, or earthquakes. This effort creates a viable option for the analysts and researchers in government, academia, or industry to bring down thecost of implementing multi-terabyte repositories to a reasonable amount.