The San Diego Supercomputer Center (SDSC) just upgraded their tape-based storage capacity to 36 petabytes, maintaining their status as the largest archival storage site of any education facility in the world. That’s 36 thousand trillion bytes of information, approximately 1,400 times the text equivalent of the print collection of the Library of Congress.
SDSC is the repository for a wealth of data, including digital visualizations of earthquake and tsunami data. The center is partnering with UCSD Libraries, the National Center for Atmospheric Research, and the University of Maryland in a data preservation project called Chronopolis. This effort is a geographically distributed data grid that incorporates “trust” and reliability through replication, service level agreements, monitoring, and rule-based systems.
