The U.S. Census Bureau, one of the largest number-crunching operations in the universe, has adopted Egenera’s BladeFrame system as its shifts to a utility computing infrastructure. The Census Bureau Utility Computing Environment (CBUCE) project aims to reduce the cost and complexity of datacenter infrastructure by centralizing the bureau’s systems and replacing proprietary RISC/UNIX servers with open platforms running Red Hat Linux and Microsoft Windows. The commitment to Eegenera blades is expected to further accelerate the census its adoption of utility computing.
“Utility computing is the future of datacenter infrastructure at the Census,” said the bureau’s Thomas J. Berti. “Capitalizing on this vision means eliminating dedicated servers in favor of flexible resources that can be allocated to any application at any time. It means delivering processing capacity to our clients in minutes or hours instead of weeks or months. And it means sharing systems across departments for high availability and continuity of operations, improving utilization, consolidating servers and reducing both capital and operational costs.”
“The utility computing environment being deployed by the Bureau is one of the most visionary we’ve seen,” said Bob Dutkowsky, chairman, president and CEO, Egenera. “Clearly, IT infrastructure is critical to achieving this objective. Egenera is proud to be part of this groundbreaking initiative with one of our federal government’s key civilian agencies.”
The computing-intensive, mission-critical applications being handled by the Census Bureau’s utility environment include the Master Address File/Topologically Integrated Geographic Encoding and Referencing Accuracy Improvement Project (MAF/TIGER). The MAF, or Master Address File, is designed to be a complete and current list of all addresses and locations where people live or work, covering an estimated 115 million residences as well as 60 million businesses and other structures in the U.S. The TIGER portion of the project is a digital database that identifies the type, location and name of streets, rivers, railroads and other geographic features, and geospatially defines their relationships to each other, to the MAF addresses, and to numerous other entities.
With four CPUs and 32 GB of memory on each Egenera blade module, MAF/TIGER can be supported by the equivalent of 24 very powerful eight-way servers in a single chassis. The exceptional performance of the AMD-based blades should also contribute to unprecedented server consolidation. The Census Bureau is also migrating both the MAF and TIGER databases to Oracle Database 10g with Real Application Clusters (RAC), the first relational database designed for utility computing.