As data volumes grow faster than budgets it becomes important to control costs for data storage by identifying data by attributes of age, owner, and size quickly. Often a performance limited, human intensive, and prone to error, we will demonstrate tools and tactics to address massive data sprawl.
In this presentation we will present how we:
- Lowered cost of storage by 5.7x.
- Minimized time archiving data while avoiding common pitfalls.
- Automated data movement and maximized network utilization with Globus APIs.
- Find, copy, and compress data 10-50x than classic tools while being backwards compatible.