Cloud Native Distributed File System And Object Storage


CubeFS  is a cloud-native storage platform that has been commonly used as the underlying storage infrastructure for online applications, database or data processing services and machine learning jobs orchestrated by Kubernetes. An advantage of doing so is to separate storage from compute – one can scale up or down based on the workload and independent of the other, providing total flexibility in matching resources to the actual storage and compute capacity required at any given time.


Some of the Use Cases for CubeFS:

  1. Replacing the local file system, and realizing infinitely expandable storage without physical boundaries, such as AI Platform、Nginx Logs、MySQL Backup etc.
  2. Big data storage to achieve separation of storage and computing, such as Spark、Hadoop、Hive etc.
  3. Persistent Volumes for containerized applications in large scale container platforms.


User Quotes:


OPPO Cloud General Manager, OPPO

The scale of data storage continues to rise, OPPO requiring “safer”, “more stable”, “higher performance”, and “lower cost” storage solutions. CubeFS products integrate the entire Kubernetes, easy to use, and low maintenance costs. Continuous innovation in the ecology allows us to create value for more businesses.



Senior technical expert,JD.COM’s file storage team has been working hard for many years to continuously optimize CubeFS, improve performance and add more practical functions, so that CubeFS can support more complex application scenarios. While supporting the application of, we also contribute to the open source community.



Senior Director of Operations,NetEase

We choose CubeFS because it has stable use cases in the production environment in other companies. In NetEase, CubeFS is a good solution to the separation of elasticseach computing and storage and the problem of poor scalability and unscalable throughput when using local storage for machine learning business, and it can be seen that the project is continuing. Introduce features such as ec, caching, etc. that attract us to continue using.



Principal Engineer, SmartMore

We need a powerful distributed file system to support our large number of data sets, we need to mount the file system to many clients, and at the same time require scalable metadata, the S3 protocol is also essential, and we also hope to be able to Secondary development to better meet our needs, and these, CubeFS can give us.