Data layout

OneFS evenly distributes data among a cluster's nodes with layout algorithms that maximize storage efficiency and performance. The system continuously reallocates data to conserve space.

OneFS breaks data down into smaller sections called blocks, and then the system places the blocks in a stripe unit. By referencing either file data or erasure codes, a stripe unit helps safeguard a file from a hardware failure. The size of a stripe unit depends on the file size, the number of nodes, and the protection setting. After OneFS divides the data into stripe units, OneFS allocates, or stripes, the stripe units across nodes in the cluster.

When a client connects to a node, the client's read and write operations take place on multiple nodes. For example, when a client connects to a node and requests a file, the node retrieves the data from multiple nodes and rebuilds the file. You can optimize how OneFS lays out data to match your dominant access pattern—concurrent, streaming, or random.