Since its acquisition Cognos in 2007 IBM has revived the notion of BI on the mainframe. DancingDinosaur first took this up here last October. With Cognos 8 running on Linux on System z the idea finally became viable. The introduction of the System z Solution Edition dubbed Enterprise Linux Server allowed the idea of BI on z to become practical from a cost standpoint.
In 2009, IBM began promoting the idea of BI on the z by citing an earlier study by Nucleus Research, in which the researchers declared that Cognos on z “makes it easy for companies to deploy BI to a broader user population, while minimizing the resulting workload for IT departments.” IBM touts the study here.
This May IBM was ready to brief industry analysts on its own comprehensive comparative TCO analysis of BI using Cognos 8 on the System z versus the x86. This is a consolidation scenario that projected the results over five years and adjusted for typical growth over that time. The study was pretty exhaustive, looking at BI use cases ranging from 100 users to 50,000 users. It included the standard hardware and system and application software costs as well as power/cooling, floor space, maintenance, connectivity, system administration, and high availability costs while accounting for periodic tech refresh during the five year period.
Since this was a total cost of ownership (TCO) study, not a cost of acquisition study, the result was what anyone who has been following DancingDinosaur would expect. At 100 users, the 5-year TCO for the x86 environment was $3 million compared to just over $1 million for the System z. By years four and five, the costs leveled out with the z maintaining a nearly $200,000 annual advantage.
At 10,000; 20,000; and 50,000 users an interesting change started to appear. The System z continued to have the lowest TCO; at 50,000 users the z cost $17 million versus $30 million for the x86 environment, but the cost difference greatly narrowed by the fourth and fifth years. The cost difference in those later years, however, did not narrow nearly as much when it came to the high availability x86 environment. High availability in the x86 world continued to cost about $3 million more a year.
This shouldn’t be too surprising. The z comes with extensive redundancy and built-in high availability. With the x86 environment you have to build those capabilities in initially and then maintain it going forward. This adds to the hardware and software costs and to the administration costs. Without high availability, the cost of the z and x86 platform reach near parity over time; with high availability, which you definitely need with thousands of users on the system, the z maintains its advantage with no hint of convergence in the trend lines.
With every IT budget cycle someone suggests eliminating the mainframe in favor of a set of distributed, highly virtualized x86 servers. For some it will be an appropriate move. However, they had better figure out how they are going to deliver the high availability they automatically get from the mainframe. In the x86 world, you have to buy it, build it, and maintain it yourself.
They also don’t think about the cost of moving their applications to the distributed platform. DancingDinosaur will take that up another time.