Mainframe Cost Optimization Solutions

IT costs are rising every year. Part of the cause is business growth in a growing economic environment, which continually drives up operations costs. But it doesn’t stop there; the introduction of mobile has made a significant contribution as well – easier access breeds increased transaction workloads.

DataKinetics mainframe cost optimization solutions can be applied quickly, and can help you to control those rising costs, no matter what the cause. Traditional cost cutting techniques like tuning or migration are highly risky, ineffective or very costly themselves. DataKinetics solutions are low-risk, low-complexity and highly effective.

When applied where needed, you will be able to realize cost saving without having to compromise on performance.

We’ve helped 20% of the Fortune 50 with controlling mainframe costs, and we can help you, too.

Cost on the Mainframe

The mainframe is widely regarded as the best platform on the planet for running large-scale transaction processing because that is what it was designed for. No other platform can compete with the throughput performance of the mainframe. It is also the most cost-effective platform for these large-scale operations. However, there is a problem – and it is in fact, cost.

It is not the cost of the platform. The mainframe is a very cost-effective platform in large-scale transaction-intensive environments, and this is backed by several industry experts. The dollar issue at hand is related to the constantly rising costs. And these rising costs are due to increased workloads from business growth – nobody is against increased business, but processing more business transactions just costs more.

Contemporary cost control solutions

IT organizations have been dealing with increasing costs since the beginning of business computing. Their methods have changed over the years – from clawing back costs from internal departments, to replacing older computing systems with newer (and less costly?) computing systems, to simply capping computing spending irrespective of the impact on the business, among other things.

The typical way to deal with rising demands on the mainframe is to plan for regular system upgrades – for more MSU and CPU capacity. IT organizations run a two- to five-year cycle of system upgrades. This satisfies the need for more computing power to handle the rising demand on the systems, but it does nothing to help control costs.

It also includes a mix of measure like scheduling, trying to use as much zIIP as possible, initiating sub-capacity pricing and performance capping scenarios, various tuning techniques, and outright platform migration. These solutions offer varying degrees of effectiveness; it’s just a matter of how much you’re willing to spend on time, energy, risk, and money.

In-memory cost optimization of mainframe applications

High-performance mainframe in-memory technology can be used to make your existing applications more cost-effective – particularly those in environments experiencing ultra-high transaction processing rates, like batch reconciliation or especially intense online transaction processing. It augments the database.

This technology works by allowing select data to be accessed using a much shorter code path than most data. The typical DB2 code path requires 10,000 to 100,000 machine cycles – and that includes any type of buffered access. Data accessed using high-performance in-memory technology uses only 400 machine cycles.

Small amounts of data that gets accessed for most or all transactions – account numbers, phone numbers, etc., are copied into high-performance in-memory tables. From there, it is accessed via a small, tight API. All other data access is unchanged. No changes are required to application code or to the database.

Actual customer results show how effective it is within various business verticals. In each all cases, CPU usage (and therefore monthly operational cost) was reduced significantly for the applicable application(s) that were cost-optimized.

Capacity management, control and automation

Large companies running intense transaction processing environments will most likely continue to rely heavily on the mainframe, as it provides the best performance/security/cost ratio. On the other side of the coin, IBM’s Monthly Licensing Charge (MLC) consistently makes up the largest component of the budget for mainframe installations – anywhere from 30% to 50% – and continues to rise, on average, by about 4% every year. Certainly, that makes cost optimization a top priority – or it should.

IBM provides powerful cost and pricing control mechanisms to help contain mainframe monthly licensing charges: sub capacity pricing for z Systems hardware, flexible licensing charge options (like AWLC, PSLC, zNALC, CMLC, MWP, zWPC , etc.), and IBM Soft Capping. But managing these tools is largely a manual process that can be both challenging and risky. Worse, it can be a challenge to effectively control these costs without suffering either performance capping or risking inadvertent cost increases.

Fortunately, solutions exist that will help IT organizations to effectively handle mainframe workloads by more efficiently employing current system capacity. Better than that, they can handle current workloads and newer workloads using the CPU resources that they are now paying for.

This solution can dynamically automate mainframe soft capping, making the process much more flexible and predictable—without actually capping any business-critical application processing. IT organizations can avoid capping altogether by dynamically controlling LPAR defined capacity limits, and leveraging available capacity from other LPARs, to essentially provide capacity on demand.

In this way, it is possible to ensure that critical processing will not be capped, while allowing capping on lower priority LPARs – LPARs dedicated to development, test, staging, etc., or lower priority workloads. Using this technology, it is possible to reduce resource usage (and associated costs) by 10 to 15% or more. Perhaps more valuable than that is the ability to curtail long-term growth in MSU usage. The Before and After graphs show how Soft Capping Automation can lower the frequency of system upgrades over time within a growing workload environment. In this case, a customer was able to extend the upgrade cycle from every three years to every four years.

IT business intelligence

IT organizations collect tremendous amounts of data about their own computing resources every day – both mainframe, midrange servers locally, or in third-party datacenters.  So much data is collected, that it could be considered their own “IT Big Data.”  And with the right toolsets, this IT data can be used to reduce the cost of your datacenter operations.

IT business intelligence solutions provide valuable information to decision makers at all levels – this includes SMF and other data from your mainframe systems, MXG, Win32 and WMI, SSH data from your server farms, along with corporate business and IT costing information. All this information, presented graphically, can show the various workloads over time, with associated cost shown as well.

IT business intelligence can also show which departments are using IT resources, and how much that is costing. This information could help to re-prioritize processing based on the new-found transparency of departmental spending patterns.

Conclusion

Mainframe cost optimization solutions provide a way to reverse the trend of large-scale IT cost increases, and to help the overall financial picture for those organizations running mainframe systems. The solutions mitigate one of the major perceived risks of staying on the mainframe: the ongoing operational cost.  By leveraging existing IT investments, IT organizations can achieve improved throughput capacity and overall system performance, a sharp decrease in cost-per-transaction and ongoing operations costs, and greatly enhanced market responsiveness—for much less than the cost of competing solutions.

These solutions are low-risk and budget-friendly; independently, they provide good cost savings, but together they provide very significant cost savings.  They also provide short-term ROI immediately, coupled with long-term cost savings and improved efficiency, enabling improved overall IT cost control and strategic business flexibility. Just the prescription needed for the malady of ever-increasing IT costs.

Download a whitepaper:

For more information, see these articles on the Planet Mainframe blog: