In September 2011, the San Diego Supercomputer Center (SDSC) at the University of California, San Diego, launched what is believed to be the largest academic-based cloud storage system in the U.S. based on OpenStack Object Storage (Swift). SDSC’s Web-based system is 100% disk-based and interconnected by high-speed 10 gigabit Ethernet switching technology, with an initial raw capacity of 5.5 petabytes. The goal was to develop a centralized, scalable data storage system designed to meet performance, functionality, and capacity needs of researchers and partners across the country. Developing it in-house one OpenStack platform allowed for highly-capable and flexible, yet extremely cost-effective solutions for researchers.
Having API access to storage has created new possibilities for data mining and portals to showcase data. It's been completely disruptive for users who were perviously challenged with data sharing and accessibility. It's faster to sign up and get started, and there's much better performance with data coming off a disk versus tape.
In this session, Steve Meier of SDSC will explain the impetus and requirements for the project, why the team chose OpenStack among the solutions they evaluated, lesssons learned from their deployment and results to date.