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. The reliability is improved because of the hardware redundancy noted above, and the scalability is achieved because hardware resources can be reallocated among the virtual machines as needed out of total system capacity.

Mainframes can add system capacity nondisruptively, instantly, and granularly — what IBM marketing, with justification, describes as "on demand computing." Modern mainframes, notably the IBM mainframe zSeries and System z9 servers, offer at least three major levels of virtualization: logical partitions (LPARs, via PR/SM), virtual machines (primarily via z/VM), and the protected and virtual addressing and workload management of their operating systems, notably z/OS. Together, these virtualization technologies support business-friendly mixed workloads, including Linux and Java, in a highly reliable and efficient manner.




Whether the acquisition cost of a mainframe makes sense will depend on its return on investment (ROI). Mainframe 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 understandably take that view, and so do some independent analysts. (Hewlett-Packard also continues to manufacture its own mainframe, the NonStop system originally created by Tandem.) However, the majority view is that mainframes are uniquely valuable (and cost-effective) for many businesses and governments. IBM's zSeries and System z9 revenues are growing, despite declining prices, suggesting that view is indeed widespread among technology buyers.

There's no question that mid-tier servers are improving. Logical partitioning, at least in basic form, is now found in many high-end Unix-based servers. However, all servers are improving, not just non-mainframe servers. For example, zSeries/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 rare feature, also found in Tandem Computers, 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.

Undoubtedly debates will continue about the mainframe's value — and, for that matter, about the value of other computing platforms, such as the PC. The debate began with the 1964 introduction of the IBM System/360 and has continued for over 40 years.

The mainframe market is exhibiting economic characteristics familiar to observers of other markets such as semiconductors and large airliners. All these markets have tremendous economies of scale and require huge capital investments to compete, resulting in just a small handful of large vendors. Yet these markets are extremely competitive because technology leadership can be fragile and because these markets are disproportionately sensitive to macroeconomic demand changes. Businesses and governments tend to delay or defer capital investments, such as mainframe purchases, during economic recessions.

When discussing the mainframe market it's no exaggeration to say that IBM defines it. As of early 2006, IBM mainframes dominate the market at well over 90% market share. The company started shipping the market's most powerful mainframe, the System z9-109, in late 2005 and spent a breathtaking $1.2 billion developing it. IBM also lowered the price substantially, effectively decreasing software prices by 10%, memory prices by 20%, and Linux and Java processor prices by about 25%. Despite IBM's mainframe might, IBM is not the only vendor. Unisys still manufactures ClearPath mainframes, based on earlier Sperry and Burroughs product lines, and a recent survey suggests its customers are loyal. Fujitsu's current product line, the Nova, is rebranded Unisys ES7000 hardware, while their Amdahl 31-bit product line is fast fading and never stood a chance against IBM's 64-bit technology. Hitachi co-developed the affordable (under $40,000 value as of early 2006) 64-bit zSeries 800 with IBM to share expenses. Hewlett-Packard continues to sell its unique NonStop systems which it acquired with Tandem Computers. Bull's DPS mainframes are still on the European market. Industry rumors abound that another entrant (or reentrant) will start shipping IBM-compatible machines.

Unisys and HP are increasingly relying on commodity Intel CPUs rather than custom processors in order to reduce development expenses, and that strategy should help Unisys and HP improve their margins. In contrast, IBM is pouring billions into developing new, homegrown technologies, and so far that investment strategy is paying generous dividends thanks to customer interest. It also helps differentiate IBM's products, especially relating to hardware optimization to boost the performance of specific software (like Linux and Java).

Mainframe acquisition prices vary, but current model IBM mainframes start at about $100,000 (System z9 BC Model A01, U.S. 2006 reported price, excluding disk and tape storage and software). That price is somewhat misleading, however, because IBM mainframe processors are "owned forever" — customers only pay a frame charge for a model upgrade and do not have to repurchase processor capacity. Prices also generally include generous maintenance and service terms that are quite unlike other computers.

There is an exceptionally active market for used mainframes, much like the aircraft market.