Unstructured Data Management and Metadata For Files and Objects
Starfish is a unique and versatile application for managing files and objects at any scale, ranging from departmental file shares to the world’s largest supercomputing file systems.
A Global File Catalog
metadata-driven & integrated with
Reporting & Analytics
Scale-out
Automation Engine
Parallel
Data Mover
End-user Data
Management
Media Spotlight:
Inside the Chargeback System That Made Harvard’s Storage Sustainable
By charging labs for storage use, Harvard’s Research Computing team slashed hoarding, optimized data management, and built a sustainable model without throttling science.
Starfish Use Cases: What Can We Solve For You Today?
Solve your specific problem. And then discover how easy it is to do holistic data management across hundreds of petabytes and billions of files with a single platform.
Storage Management
Archiving & Tiering
Data Protection
Chargeback / Cost Accounting
ROT Cleanup / Capacity Reclamation
Discovery – Analytics – Aging
Data & Asset Management
AI/ML Training & Inference
Tagging, Classification, Curation
Scientific Instrument Workflows
Data Processing Pipelines
FAIR Data Management
Storage Device Agnostic
Starfish works with all enterprise NAS and HPC file systems
Starfish works with all of the leading S3-style object stores
For a full list of object stores
By giving our users clear visibility and reports into what data they have, how it is being used, and who is using their storage allocation, we enable them to get serious about what they need to keep and what can be moved to cold storage or deleted. From what we have seen so far, they will be able to purge upwards of 20PB of existing data.”
Raminder Singh
Associate Director Data Science & Research Facilitation
Harvard University Research Computing
The Starfish Advantage
Four reasons why you get more value with Starfish
Massive Scalability
Starfish supports billions of files and hundreds of Petabytes. It thrives in some of the world’s largest and most demanding supercomputing sites and distributed enterprises.
Extensible Metadata
Starfish’s unique approach to metadata enriches your understanding of how file collections relate to your business or science. Know what you have, how much, how many, how new, how old. Take appropriate action based on discoveries.
Integrated Data Mover
Starfish’s integrated data mover scales out to tackle any size workload, even across geographies. Starfish supports all modalities of data movement: archiving, backup/restore, replication, migration, and workflows.
End User Empowerment
Storage consumers can add tags to files and directories, quantify their own storage consumption, navigate their file collections, and actively participate in their own data management.