System for multi-volume, write-behind data storage in a distributed processing system

摘要

A write-behind enablement approach is presented which allows writing data to multiple volumes of storage media associated with one or more server nodes in a distributed processing environment. A client application on a client node writes blocks of data to a first magnetic tape of a first server node until an end of physical storage of the first magnetic tape is reached, without having predetermined the size of the first magnetic storage. Thereafter, the writing of blocks of data is switched to a second magnetic tape, which may be on the first server node or a second server node in the system. The writing and switching process can repeat a number of times across multiple magnetic tapes. Data is written in a write-behind operation and the switching to a new magnetic tape occurs transparent to the client application, and without loss of data. The client and server nodes are adapted to ascertain how many blocks of data were written to the first storage medium, and the second storage medium, and to allow for the client process to write a header label to the second storage medium prior to writing blocks of data thereto.