CC*DNI DIBBs: Data Analysis and Management Building Blocks for Multi-Campus Cyberinfrastructure through Cloud Federation
posterposted on 22.01.2020 by Rich Wolski, Thomas Furlani, David Lifka
Poster sessions are particularly prominent at academic conferences. Posters are usually one frame of a powerpoint (or similar) presentation and are represented at full resolution to make them zoomable.
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.