||This article needs additional citations for verification. (July 2009)|
NonStop can refer to the line of HP Integrity NonStop computers, the line of Tandem NonStop computers that preceded them, or the NonStop OS operating system that is designed for them. NonStop systems are based on an integrated hardware/software stack. They are self-healing systems designed with redundant components and automatic reconfiguration in the event of a component failure, to prevent against "single-point failures" (see Reliability engineering). The systems run the NonStop OS operating system and the database management systems NonStop SQL and Enscribe.
Originally introduced in 1976 by Tandem Computers Inc., the line was later owned by Compaq (from 1997) and Hewlett-Packard (since 2003). In 2005, the current product line of HP Integrity NonStop servers, based on Intel Itanium microprocessors, was introduced.
Early NonStop applications had to be specially coded to be fault-tolerant. That obstacle was removed in 1983 with the introduction of the Transaction Monitoring Facility (TMF), which handles the various aspects of fault tolerance on the system level, transparent to the application.
NonStop OS 
NonStop OS is a message-based operating system designed for software fault tolerance. It works with process pairs and ensures that backup processes in different CPUs take over in case of a process or CPU failure. Data integrity is maintained during those takeovers; no transactions or data are lost or corrupted.
NonStop Hardware 
The HP Integrity NonStop computers are a line of fault-tolerant server computers, optimized for transaction processing and providing an extreme level of availability and data integrity. Average availability levels of 99.999% have been observed. NonStop systems feature a massive parallel processing (MPP) architecture and provide linear scalability. Each CPU (systems can be expanded up to over 4000 CPUs) runs its own copy of the OS. This is a "share nothing" arrangement, and no "diminishing returns" occur as more processors are added.
Due to the integrated hardware/software stack and a single system image for even the largest configurations, system management requirements for NonStop systems are rather low. In most deployments there is just a single production server, not a complex server farm.
Most customers also have a backup server in a remote location for disaster recovery. There are standard products to keep the data of the production and the backup server in sync, hence there is fast takeover and no data loss also in a disaster situation with the production server being disabled or destroyed.
HP also developed a data warehouse and business intelligence server line, HP Neoview, based on the NonStop line. It acted as a database server, providing NonStop OS and NonStop SQL, but lacked the transaction processing functionality of the original NonStop systems. The line was retired, and no longer marketed, as of January 24, 2011.
||This article includes a list of references, but its sources remain unclear because it has insufficient inline citations. (July 2009)|
- "Compare system availability in the real world". Hewlett-Packard. October 2006. Retrieved 2010-08-07.
- Morgan, Timothy Prickett, The Register "HP euthanizes Neoview data warehouse iron: Itanium death", The Register, Hardware, 24th January 2011
- Siewiorek, Daniel P.; Swarz, Robert S. (1998). Reliable Computer Systems, A K Peters, Ltd., ISBN 1-56881-092-X. pp. 586–625.
- Horst, R.W. (February 1995). "TNet: a reliable system area network". IEEE Micro.
- Horst, Robert W.; Harris, Richard L.; Jardine, Robert L. (1990). "Multiple instruction issue in the NonStop Cyclone processor". Proceedings of the 17th Annual International Symposium on Computer Architecture. pp. 216–226.
- Bernick, D. (2005). "NonStop advanced architecture". Proceedings of the 2005 International Conference on Dependable Systems and Networks.
- Kim, Won (March 1984). "Highly available systems for database applications". ACM Computing Surveys.