Project Status: Completed; all services are available through RIS.
Project Manager: Randy Gadell, rgadell@wustl.edu
This project’s goal is to build a Community Good, Scalable, and Distributed Storage Network Infrastructure with Long-Term Archival Capability for Research Computing. Washington University’s Enterprise Risk Management process identified big data as a strategic risk and the WUSTL Research Computing IT Governance Committee has identified research storage as its top priority per its Strategic Plan.
This is the next logical evolution of the strategic initiative to implement a robust, high-performance and integrated cyber-infrastructure to facilitate knowledge sharing, increase collaboration, minimize redundancy, and capital outlays while providing a foundation for “Large Data” research.
This effort will leverage existing technical expertise within Research Infrastructure Services (RIS) and data management expertise of the University Library. In addition, this collaboration with representative experts in other research domains seeks to not only address the storage needs of researchers, but also deliver storage-as-a-service to address the institutional responsibilities of the University to manage data access, access and retention compliance, enforce data use policies, and appropriately fund data consumption. The storage service will be comprised of multiple tiers to increase performance while lowering costs. These storage services will provide:
- Centralized storage management, engineering, and technical support
- Daily incremental, weekly and monthly backups
- Optional cross-data center data replication
- The first 5TB per researcher at subsidized cost
- Active Archive (lower tier, lower costs)
- Policy driven migration from Active Tier after fixed period of inactivity
- Implement approximately 5PB (petabytes) of storage over 3 years
- First 5 terabytes(TB) of high-performance storage are university subsidized and provided at no costs to Researchers
- Researchers may share their allocation with their team or collaborators
- Storage amounts above 5TB will be available on a sliding costs scale
- Storage is high performance and accessible via the high-speed WashU Research Network (WURN) or via the common network
- Storage services include full back-ups
- Engineering and design services are available for special data feed and storage needs
| Milestones | Completion Date |
| Project Approval | March 2017 |
| Phase one hardware and services ordered | September 2017 |
| Pilot use cases and testing | Feb – Apr 2018 |
| General availability | May 2018 |
| Phase 2 planning begins – Additional features & services | June 2018 |
| Phase 2 Purchasing -Storage capacity and performance enhancements | July-August 2020 |
| Phase 2 testing begins | September 2020 |
| Principal Researcher and Staff Training | On-going |
| General Availability of Phase 2 | September 2020 |
| Team Member | Title | Role |
| James Fitzpatrick, Ph.D. | Professor of Neuroscience | Chair of Infrastructure and Applications Subcommittee |
| Randy Gadell | Project Manager | Program / Project Manager |
| Craig Pohl | Senior Director, RIS | Technical Lead |
Chair
Jenny Lodge, Ph.D.
Vice Chancellor, Research
Stephanie Reel
Vice Chancellor, CIO
Phillip Payne, Ph.D.
Prof of Internal Medicine, Gen Medical Sciences
Albert Lai, Ph.D.
Chief Research Information Officer
Tau Ju
Professor, Computer Science and Engineering
Craig Pohl
Sr. Director Research Infrastructure Services
Denise Stephens
Vice Provost and University Librarian
Randy Gadell
IRIS Program Manager, OCIO PPMO