CubeFS
Distributed filesystem and object storage system built for cloud-native, large-scale data-intensive applications.
- Actively maintained
- Foundation-backed
- Well documented
- Permissive license
Overview
CubeFS provides both file and object storage interfaces over a distributed, horizontally scalable cluster, originally built at JD.com to handle large-scale data workloads including big data analytics, AI training data, and container-native storage. It's a CNCF-hosted project with multi-tenancy and multi-zone deployment support.
CubeFS is a fit for teams running large-scale data-intensive workloads - big data, AI training data pipelines - who need distributed file and object storage together, an alternative in the same space as Ceph and JuiceFS already in this catalog with a different architectural origin.
Why it's in this catalog
Catalog rating: ★★☆☆☆ (2/5)
Cloud-native distributed file/object storage; overlaps with several existing storage options.
- Emerging
- Foundation-governed
- Categories
- Storage
- Languages
- Go
- License
- Apache-2.0
Related Projects
JuiceFS
Apache-2.0Distributed POSIX filesystem that stores data on object storage like S3, combining familiar filesystem semantics with cloud-scale storage.
Actively maintained
- Storage
Ceph
LGPL-2.1Industry-standard distributed storage system providing object, block, and file storage from a single unified cluster.
Actively maintained
- Storage
Alluxio
Apache-2.0Data orchestration layer that sits between compute engines and storage systems, caching data for faster, unified access across the two.
Actively maintained
- Storage
SeaweedFS
Apache-2.0Distributed file and object storage system built to store and serve billions of files fast, speaking S3, POSIX, and lakehouse (S3 Tables) protocols.
Actively maintained
- Storage
Spotted an error? Suggest an edit on GitHub.