Data Storage
The storage cluster clients and each Ceph OSD use the Controlled Replication Under Scalable Hashing (CRUSH) algorithm to efficiently calculate the data location without relying on a centralized query table. Its advanced functions include
The Ceph storage cluster receives data from the Ceph client and stores the data as objects, regardless of whether the data comes from the Ceph block device, Ceph object storage, Ceph file system, or librados-based customized implementation. Each object is a file in the file system and is stored on object storage devices. The Ceph OSDs process read and write operations on storage devices.
The Ceph OSDs store all data as objects in a flat namespace without a directory hierarchy. An object contains an identifier, binary data, and metadata composed of name/value pairs. The metadata semantics depend entirely on Ceph clients.