The latest iteration of IBM’s z/OS workload pricing aims at to lower the cost of running cloud workloads. In a recent announcement, z Systems Workload Pricing for Cloud (zWPC) for z/OS seeks to minimize the impact of new public cloud workload transaction growth on Sub-Capacity license charges. IBM did the same thing with mobile workloads when they started driving up the 4-hour workload averages on the z. As more z workloads interact with public clouds this should start to add up, if it hasn’t already.
Bluemix Garages in the Cloud
As IBM puts it: zWPC applies to any organization that has implemented Sub-Capacity pricing via the basic AWLC or AEWLC pricing mechanisms for the usual MLC software suspects. These include z/OS, CICS, DB2, IMS, MQ and WebSphere Application Server (WAS). An eligible transaction is one classified as Public Cloud-originated, connecting to a z/OS hosted transactional service and/or data source via a REST or SOAP web service. Public cloud workloads are defined as transactions processed by named Public cloud application transactions identified as originating from a recognized Public Cloud offering, including but not limited to, Amazon Web Services (AWS), Microsoft Azure, IBM Bluemix, and more.
IBM appears to have simplified how you identify eligible workloads. As the company notes: zWPC does not require you to isolate the public cloud work in separate partitions, but rather offers an enhanced way of reporting. The z/OS Workload Manager (WLM) allows clients to use WLM classification rules to distinguish cloud workloads, effectively easing the data collection requirements for public cloud workload transactions.
So how much will you save? It reportedly reduces eligible hourly values by 60 percent. The discount produces an adjusted Sub-Capacity value for each reporting hour. What that translates into on your monthly IBM software invoice once all the calculations and fine print are considered amounts to a guess at this point. But at least you’ll save something. The first billing eligible under this program starts Dec. 1, 2016.
DancingDinosaur expects IBM to eventually follow with discounted z/OS workload pricing for IoT and blockchain transactions and maybe even cognitive activity. Right now the volume of IoT and blockchain activity is probably too low to impact anybody’s monthly license charges. Expect those technologies ramp up in coming years with many industry pundits projecting huge numbers—think billions and trillions—that will eventually impact the mainframe data center and associated software licensing charges.
Overall, Workload License Charges (WLC) constitute a monthly software license pricing metric applicable to IBM System z servers running z/OS or z/TPF in z/Architecture (64-bit) mode. The driving principle of WLS amounts to pay-for-what-you-use, a laudable concept. In effect it lowers the cost of incremental growth while further reducing software costs by proactively managing associated peak workload utilization.
Generally, DancingDinosaur applauds anything IBM does to lower the cost of mainframe computing. Playing with workload software pricing in this fashion, however, seems unnecessary. Am convinced there must be simpler ways to lower software costs without the rigmarole of metering and workload distribution tricks. In fact, a small mini-industry has cropped up among companies offering tools to reduce costs, primarily through various ways to redistribute workloads to avoid peaks.
A modification to WLC, the variable WLC (VWLC) called AWLC (Advanced) and the EWLC (Entry), aligns with most of the z machines introduced over the past couple of years. The result, according to IBM, forms a granular cost structure based on MSU (CPU) capacity that applies to VWLC and associated pricing mechanisms.
From there you can further tweak the cost by deploying Sub-Capacity and Soft Capping techniques. Defined Capacity (DC), according to IBM, allows the sizing of an LPAR in MSU such that the LPAR will not exceed the designated MSU amount. Group Capacity Limit (GCL) extends the Defined Capacity principle for a single LPAR to a group of LPARs, allowing MSU resources to be shared accordingly. BTW, a potential downside of GCL is that is one LPAR in the group can consume all available MSUs due to a rogue transaction. Again, an entire mini industry, or maybe no so mini, has emerged to help handle workload and capacity pricing on the z.
At some point in most of the conference pricing sessions the eyes of many attendees glaze over. By Q&A time the few remaining pop up holding a copy of a recent invoice and ask what the hell this or that means and what the f$#%@#$ they can do about it.
Have to admit that DancingDinosaur did not attend the most recent SHARE conference, where pricing workshops can get quite energetic, so cannot attest to the latest fallout. Still, the general trend with mobile and now with cloud pricing discounts should be lower costs.
DancingDinosaur is Alan Radding, a veteran information technology analyst and writer. Please follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing at technologywriter.com and here.