Swap
From Adapt
SWAP, the Simple Web-Accessible Storage
Overview
SWAP provides a simple mechanism to distribute data across multiple partitions or servers while providing simple mechanism to retrieve all data.
Below is a set of key design goals for SWAP:
- Data must be easily accessible in the absence of ANY software. (Operating System excluded)
- No centralized metadata server.
- Provide http access to data.
SWAP organizes data into individual collections called file groups. Each file group is split into several parts called slices. These slices are places on different SWAP servers. Data is organized using directories and files within a slice. This means that the path within a slice on a server is the same as the path within SWAP. Data is spread between multiple nodes based on the hash of its path name.
The following diagram shows how data is spread among different slices in SWAP:
