OpenMPDK/DSS

Disaggregated Storage Solution

40
/ 100
Emerging

This project helps data center architects and infrastructure engineers build their own high-performance object storage systems optimized for massive read bandwidth. It takes commodity server hardware and NVMe drives and turns them into an S3-compatible storage cluster capable of handling extreme data retrieval demands, particularly for AI and machine learning workloads. The end result is a highly scalable, flexible storage solution that can grow compute and storage resources independently.

No commits in the last 6 months.

Use this if you need to build an on-premise, S3-compatible object storage solution that prioritizes ultra-high read bandwidth and independent scaling of storage and compute resources.

Not ideal if you are looking for a simple, plug-and-play storage solution or primarily need write-optimized storage for general-purpose applications.

data-center-architecture object-storage high-performance-computing ai-infrastructure cloud-native-storage
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

41

Forks

9

Language

Shell

License

BSD-3-Clause-Clear

Last pushed

Jan 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mlops/OpenMPDK/DSS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.