From 1952 into the late 1960s, IBM manufactured and marketed several large computer models, known as the IBM 700/7000 series. The first-generation 700s were based on vacuum tubes, while the later, second-generation 7000s used transistors. These machines established IBM's dominance in electronic data processing. IBM had two model categories: one (701, 704, 709, 7090, 7040) for engineering and scientific use, and one (702, 705, 7080, 7070, 7010) for commercial or data processing use. IBM initially sold its computers without any software, expecting customers to write their own; and programs were manually initiated, one at a time. This followed the model IBM had earlier established with their unit record equipment. Later IBM provided compilers for the newly developed higher-level programming languages Fortran and COBOL. The need to make the most efficient use of these multi-million dollar machines led to the introduction of simple operating systems, or job monitors. The two categories, scientific and commercial, generally used common peripherals but had completely different instruction sets, and there were incompatibilities even within each category. As software became more complex and important, the cost of supporting it on so many different designs became burdensome.
The second generation products were a mainstay of IBM's business and IBM continued to make them for several years after the introduction of the System/360. (Some IBM 7094s remained in service into the 1980s.)
Prior to System/360, IBM also sold computers smaller in scale, that were not considered mainframes, though still bulky and expensive by modern standards. These included:
* IBM 650 (vacuum tube logic, decimal architecture, business and scientific)
* IBM RAMAC 305 (vacuum tube logic, first computer with disk storage; see: Early IBM disk storage)
* IBM 1400 series (business data processing; very successful and many 1400 peripherals were used with the 360s)
* IBM 1620 (decimal architecture, engineering, scientific, and education)
IBM had difficulty getting customers to upgrade from the smaller machines to the mainframes because so much software had to be rewritten. The 7010 was introduced in 1962 as a mainframe-sized 1410. The later Systems 360 and 370 could emulate the 1400 machines. A desk size machine with a different instruction set, the IBM 1130, was released concurrent with the System/360 to address the 1620's niche. It used the same EBCDIC character encoding as the 360 and was mostly programmed in Fortran, which was relatively easy to adapt to larger machines.
Nearly all mainframes have the ability to run (or "host") multiple operating systems and thereby operate not as a single computer but as a number of virtual machines. In this role, a single mainframe can replace dozens or even hundreds of smaller servers, reducing management and administrative costs while providing greatly improved scalability and reliability.
Mainframes can add system capacity nondisruptively and granularly. Modern mainframes, notably the IBM zSeries and System z9 servers, offer three levels of virtualization: logical partitions (LPARs, via the PR/SM facility), virtual machines (via the z/VM operating system), and through its operating systems (notably z/OS with its key-protected address spaces and sophisticated goal-oriented workload scheduling, but also Linux and Java).
Mainframe return on investment (ROI), like any other computing platform, is dependent on its ability to scale, support mixed workloads, reduce labor costs, deliver uninterrupted service for critical business applications, and several other risk-adjusted cost factors. Some argue that the modern mainframe is not cost-effective. Sun Microsystems, Hewlett-Packard, and Dell unsurprisingly take that view at least at times, and so do some independent analysts. However, the general consensus (held by Gartner and other independent analysts) is that the modern mainframe often has unique value and superior cost-effectiveness, especially for large scale enterprise computing. In fact, Hewlett-Packard also continues to manufacture its own mainframe, the NonStop system originally created by Tandem. Logical partitioning is now found in many high-end UNIX-based servers, and many vendors are promoting virtualization technologies, in many ways validating the mainframe's design accomplishments.
IBM Mainframes also have unique execution integrity characteristics for fault tolerant computing. System z9 servers execute each instruction twice, compare results, and shift workloads "in flight" to functioning processors, including spares, without any impact to applications or users. This feature, also found in HP's NonStop systems, is known as lock-stepping, because both processors take their "steps" (i.e. instructions) together. Not all applications absolutely need the assured integrity that these systems provide, but many do, such as financial transaction processing.
Answered By: navmac - 2/6/2007 |