Anatomy of an Append Operation

Let’s learn how GFS handles an append operation.

Record append operation is optimized in a unique way that distinguishes GFS from other distributed file systems. In a normal write, the client specifies the offset at which data is to be written. Concurrent writes to the same region can experience race conditions, and the region may end up containing data fragments from multiple clients. In a record append, however, the client specifies only the data. GFS appends it to the file at least once atomically (i.e