Sunday, 18 May 2008

Saving money on mainframes

Mainframes have always been expensive. The hardware is expensive in the first place, and the software is expensive to run on it. That’s the main reason given by many organizations for migrating off the mainframe – it’s too expensive. A couple of Windows laptops and a bit of freeware downloaded off the Internet and you’re back in business!! Well, the old Dinosaur Myth publication put that sort of logic in its place years ago, and, although the publication is a good few years out-of-date now, the theory behind it is still correct.

And for people who have never seen the Dinosaur Myth, you can still download a copy from

So, we’re left with the unenviable conclusion that all computing is expensive, it’s just whether you’re prepared to pay the money up front or you’re forced to pay out later.

This rather grim conclusion would lead one to ask, is there any way of saving money? And the answer is a pleasing "Yes". Traditionally, mainframes have a General Purpose Processor (GPP) that performs all the processing on the computer. Usage of that processor has been measured in Millions of Instructions Per Second (MIPS) and that has given IBM an easy way to charge for their computers – on how much work you are making them do, ie how many MIPS they are using. It’s a bit like charging for van hire by how many miles the van goes while it is being rented. What users really wanted was some other processing engine that could do some processing and reduce the MIPS used by the GPP. IBM came up with such a solution. They invented (and of course sold) specialty processors. I’m talking here about zIIP (System z9 Integration Information Processor) and zAAP (System z Application Assist Processor). Basically, any workloads run on these specialty engines do not form part of an organization’s contracted mainframe processing capacity. So their use results in a reduction in that organization’s Total Cost of Ownership (TCO). As a consequence, not only do they get reduced software costs, they also get additional processing capacity – and that can be used to eliminate or delay the next upgrade

It’s a bit of a swings and roundabouts situation though. An organization needs to pay for a specialty processor, and it needs to buy software that can make use of the specialty processor, and then it can start saving money – I hear the sound of Excel Pivot tables being used to present the result of what can be quite a complicated calculation. But is there any software that can make use of this hardware? We know about DB2, but that’s from IBM. What else is there? DataDirect’s Shadow software has been around for a little while, and last week NEON Enterprise Software announced that Version 5.1 of its Eclipse Reorganization Utilities for IMS will.

NEON claims in its press release that by using Eclipse Reorganization Utilities, it is possible for customers to experience capacity gains of more than 70 percent for some IMS database maintenance processing.

Now that more software is becoming available to exploit specialty engines, it does seem that users could have a way to save money on their mainframes.