CC*DNI DIBBs: Data Analysis and Management Building Blocks for Multi-Campus Cyberinfrastructure through Cloud Federation

The ability to aggregate, share, and analyze important large data sets while reducing time to science has become essential to support multi-disciplinary and multi-institutional data-driven discovery. Cornell University, the University at Buffalo, and the University of California, Santa Barbara, have created a federated cloud system called the Aristotle Cloud Federation (federatedcloud.org). Each site operates standard OpenStack cloud infrastructure components augmented with DIBBs storage assets including data analysis servers, scalable storage, and a Globus file transfer and sharing endpoint. This project serves as an important model for campus cyberinfrastructure that other institutions can follow providing flexibility in support of multi-discipline scientific workflows, elasticity by sharing resources, Open XDMoD cloud metrics and accounting, and an allocations model whose goal is to provide a fair exchange mechanism for resource access between and across multiple institutions. Most recently, Dartmouth joined the federation and we welcome inquiries from other universities and research centers.