Distributed file systems: concepts and examples
ACM Computing Surveys (CSUR)
The parallel I/O architecture of the high-performance storage system (HPSS)
MSS '95 Proceedings of the 14th IEEE Symposium on Mass Storage Systems
The IEEE Storage System Standards Working Group overview and status
MSS '95 Proceedings of the 14th IEEE Symposium on Mass Storage Systems
| Hi-index | 0.00 |
A mass storage system or MSS is a collection of software, computing elements, input-output, and data storage components that jointly automate the archiving, storage, management, and retrieval of very large quantities of digital information. A typical high-end mass storage system may store from hundreds of terabytes(1012 bytes) to petabytes(1015 bytes) of data contained in millions of files. The MSS provides access to those files to client computer systems ranging from desktop workstations (q.v.) to supercomputers (q.v.) at speeds from megabits per second over a local area network to gigabits per second over high-speed I/O channels. Mass storage systems are not automated backup systems, although they may be used as a component of such systems. Mass storage systems are not automated tape management systems, although some early ones evolved from such systems, and most incorporate sophisticated tape management algorithms. Mass storage systems are not distributed file systems, although users may indirectly access an MSS through front-end distributed file system servers. Examples of early mass storage systems are the Common File System or CFS developed at Los Alamos National Labs, Unitree from Lawrence Livermore National Labs, and the National Center for Atmospheric Research (NCAR) MSS, each of which was developed in the mid-1980s.