Skip navigation
Share:|

Today’s mainframe systems run the world’s top industries’ mission-critical workloads. This includes large financial institutions like banks, insurance companies, healthcare organizations, utilities, government, military, and a multitude of other public and private enterprises. 

The beauty of the mainframes lays in its flexibility, stability and security.  Mainframe systems provide the ability to divide the resources of a single machine into multiple, logical partitions (LPARs), capable of running their own independent operating systems.  These LPARs are, in practice, equivalent to separate mainframe systems themselves, and can function independently, or work together as a collection – called sysplex – that cooperate to process computing workloads.  This sysplex design can run large commercial mission-critical workloads continuously and very efficiently.

Each mainframe machine has maximum central processing complex (CPC) capacity – the LPARs running on a given machine collectively use the machine’s CPC capacity.  And capacity is the key word – mainframe systems have the equivalent processing power of multiple rows of multiple commodity servers – and have tremendous transaction throughput capacity. Much higher capacity than those banks of servers – which is why large organizations continue to use this platform – the mighty and majestic mainframe.

Controlling the Majestic Mainframe

Control3.pngphoto credit: romeacrosseurope.com

 

Unlike other computing platforms, a single mainframe system can be configured for a variety of different business needs – performance and cost can be balanced as needed, depending upon the required computing needs.  Whether a business needs to use the full capacity of the system, or to limit the capacity of a test LPAR, or to control the cost of usage-based software, the mainframe can accommodate the needs of the business. 

The mainframe offers “capping” controls that can limit the CPU resource usage of one or more LPARs. Capping is managed either by the Workload Manager (WLM) or the Processor Resource/System Manager (PR/SM). There are 7 effective techniques available to control resource usage – below, we go through each one of them.

Initial Capping (Hard Cap)

The usage of CPC capacity for a given LPAR is based on the weight assigned to it in the Hardware Management Console (HMC) – each LPAR has its share of CPC capacity. However, if an LPAR needs more than its share of CPC capacity, and other LPARs are using less than their shares, the PR/SM can then allocate additional capacity for the capacity-hungry LPAR.

The Initial Capping (IC) setting prevents PR/SM from giving an LPAR more than its share even when there is capacity available in the CPC, meaning the LPAR can never exceeds its share. The IC limit is defined in the HMC as relative weight.

Scope is single LPAR. This capping is managed by the PR/SM.

LPAR Absolute Capping

LPAR absolute capping is a PR/SM-controlled capping limit that applies to a single LPAR. Its limit is defined in the HMC as a fraction of the total number of processors.  This capping is enforced independent of the 4-hour rolling average (4HRA) – the measure of the LPAR’s resource usage – and is applicable to both z/OS LPARs as well as non-z/OS LPARs.

Scope is a single LPAR.

Group Absolute Capping

Group absolute capping similar to the LPAR absolute capping but applies to a defined group of LPARs. This cap limit is defined in the HMC as a fraction of the total number of processors, and is controlled by PR/SM. The combined CPU capacity usage of these groups of LPARs can never exceed the group absolute capping limit at any time.

Scope is a group of LPARs.

Defined Capacity (Soft Capping)

An LPAR receives a Defined Capacity (DC) - its defined maximum capacity - is set in the HMC.  The WLM tracks the 4HRA of the LPAR, and compares it to the LPAR’s DC value. If the LPAR’s 4HRA exceeds its DC value, then it is capped.  The WLM triggers the capping, but it is enforced by the PR/SM. When capping occurs, the workload currently running on the LPAR is delayed.  If the WLM policy is set appropriately, the WLM will run the most critical work and delays the low-importance work.  Capping will be in effect until the resource usage 4HRA drops below the DC value, at which point the LPAR will process workloads without delay.  Since the LPAR’s DC value is compared to the 4HRA (an averaged value), the current CPU usage of this LPAR can go over DC value as long as the average 4 hour rolling value doesn’t exceed the DC limit.

DC only applies to LPARs with shared central processors (CPs); LPARs with dedicated CPs cannot be controlled by DC.  DC (soft capping) cannot be used with Initial Capping control (and vice-versa).

Scope is a single LPAR. This means that the DC value limits the CPU capacity for a single LPAR.

Group Capacity Limit

Similar to DC, group capacity limit (GCL) controls the CPU usage for a group of LPARs on a single CPC. z/OS LPARs can be grouped together in what are called capacity groups.  These LPARs must reside in the same CPC, but not necessarily within the same sysplex. GCL controls all LPARs in the capacity group, and the GCL value is set in HMC. The total 4HRA of all LPARs in a given capacity group cannot exceed the GCL value.  If the 4HRA exceeds the capacity group limit, then the capacity group is capped by the PR/SM, and each member of the group gets its share of resources based on its assigned weight.  As the group 4HRA drops below the GCL, capping is terminated, and the group will process workloads without delay.  While the 4HRA of the group is below the GCL, each LPAR in the group can use the capacity it needs.

Within the capacity group, in addition to its group share, each LPAR in the group can be assigned a DC. In such cases, either the calculated group share or the DC is used to cap, whichever is less. 

Scope is a group of LPARs belonging to the same CPC.

Resource Group Capping

Resource Group (RG) capping provides the ability to control the maximum and the minimum CPU capacity given to the service classes (workloads) that are connected to a given RG. If workloads of a RG exceeds the maximum limit, then WLM caps the CPU usage of the RG.

WLM manages the workloads using the goals defined in the service definition.  If a workload is not meeting its defined goal, the WLM assign more resources to it when needed.  In that process, the WLM may remove resources from other workloads that are meeting their goals.  The RG minimum and maximum values set the limits to this CPU goal management.  A minimum value prevents the WLM from taking away resources, while a maximum value prevents the WLM from providing additional resources even if the workload is not meeting its goal.

Scope is sysplex wide. The service classes that are in a RG should belong to the LPARs that are in the same sysplex.  However, LPARs themselves can span multiple CPCs.

Absolute MSU Capping

WLM-controlled Absolute MSU capping is similar to PR/SM controlled initial (hard) capping – it is permanent capping controlled by the WLM.  The difference is that absolute MSU capping is specified in MSUs (the DC of the LPAR), whereas hard capping is specified in relative weight.

The limit value is derived from that DC and the LPAR group capacity.

Scope is a single LPAR.

Intelligent capping (iCap)

If you are into capping for cost control, then BMC offers dynamic solution - Intelligent capping (iCap)

Intelligent Capping for zEnterprise (iCap) is a mainframe software solution that dynamically automates and optimizes defined capacity settings to lower IBM Monthly License Cost (MLC) costs by 2%-5% or more saving customers millions of dollars, while mitigating risk to the business. After analyzing CPU usage and WLM workload, iCap automatically manages changes to defined capacity settings based on workload profiles, enabling customers to lower costs. BMC Intelligent Capping for zEnterprise removes the manual effort from managing capping limits, while optimizing capacity usage across LPARs or groups of LPARs. The solution dynamically aligns workload allocations based on utilization needs, workload importance, and customer policy profiles

For more information (including a 2 min short video on how iCap works) please visit http://www.bmc.com/it-solutions/intelligent-capping-zenterprise.html

 

Summary

Mainframe systems provide tremendous capabilities, and run the world’s largest and most complex commercial workloads.  Yet it remains highly flexible, and is able to handle the unique business needs and workloads required for a wide range of businesses.  To facilitate this high degree of business flexibility, there are exist 7 different techniques available to control the mighty and majestic mainframe. If you want to automate capping to control cost then BMC offer unique solution - Intelligent capping (iCap)

 

Author: Hemanth Rama is a senior software engineer at BMC Software. He has 11+ years of working experience in IT. He holds 1 patent and 2 pending patent applications. He works on BMC Mainview for z/OS, CMF Monitor, Sysprog Services product lines and has lead several projects. More recently he is working on Intelligent Capping for zEnterprise (iCap) product which optimizes MLC cost. He holds master degree in computer science from Northern Illinois University. He writes regularly on LinkedIn pulse, BMC communities and his personal blog. [[LINK: https://path2siliconvalley.wordpress.com/  ]]

 

Share:|

Yes my friends. Innovation in mainframes is happening right here in Silicon Valley at BMC Software. While everyone is chasing the next big, disruptive unicorn like Uber or Airbnb, BMC engineers are quietly disrupting the mainframe industry with new customer-driven innovation.

Curiously, most non-mainframe technology professionals are unaware of opportunities to innovate on mainframe software.  They think mainframes are age-old dinosaurs that occupy entire rooms, use card punch input, and require bits and bytes programming.  Things have changed a lot over the years.  The same mainframes that are now the size of your refrigerator run the most critical work of our top industries today. This includes large financial institutions like banks, insurance companies, health care, utilities, government, military, and a multitude of other public and private enterprises.  Mainframes are a multi-billion dollar industry. Innovations that are achieved have huge positive impacts in the industry and the global economy. BMC engineers have done precisely that – created innovation that moves waves in the mainframe industry

The Challenge

First, let’s take a look at one key challenge that the mainframe industry faces today. Many surveys have revealed that the biggest challenge of companies with mainframes today is the increasing cost. Mainframe costs include several components, but the largest portion involves IBM monthly license charge [MLC] costs stand out (See Figure 1) What’s more, MLC costs increase 4-7% annually. This would give any CFO a nightmare!

mc

For decades, IBM mainframe customers have manually managed mainframe workload capping strategies, constantly shifting workload allocations to manage costs and meet business demand. But these techniques are manual, risky and error prone and often don’t provide desired results.

For starters, mainframe computers are large, multi-processor computing devices able to perform thousands of tasks every second. Work on mainframe computers is often measured in millions of service units (MSUs), which is a measure of the processor (CPU) capacity used to execute the work. Mainframe customers are often charged for their software that runs on a mainframe based on peak MSU usage through a Monthly Software License Charge (MLC). To determine the MLC, the mainframe operating system generates monthly reports that determine the customer’s system usage (in MSUs) during every hour of the previous month using a rolling average (e.g., a 4-hour rolling average) recorded by each LPAR or a capacity group for the customer. The hourly usage metrics are then aggregated together to derive the total monthly, hourly peak utilization for the customer, which is used to calculate the bill for the customer.

To control costs, staff might assign each LPAR or capacity group a consumption limit (Defined Capacity or Group Capacity Limit), and it cannot use more MSUs than allotted in its respective consumption limit. But this may result in some work not receiving the CPU resources it needs, in effect slowing down the execution and completion of that work. This may have very undesirable effects on important workloads. Since meeting performance objectives of high importance work is deemed a necessary part of shifting resources, customers tend to raise capacity limits to meet the demand and avoid outage to their clients. But raising the capacity limit even for as little as an hour can increase MLC costs substantially.

Today’s Solution

When this challenge was presented, five bright engineers from BMC Software (Hemanth Rama, Edward Williams, Phat Tran, Robert Perini and Steven DeGrange) proposed a dynamic solution that automates and reduces the MLC cost while mitigating the risk to critical business workloads.

The solution they proposed was so innovative that a patent was granted for their outstanding work.

DYNAMIC WORKLOAD CAPPING
PATENT ISSUANCE #9342372
GRANTED ON  MAY 17, 2016.
http://patft1.uspto.gov/netacgi/nph-Parser?patentnumber=9342372

Let me give you an overview of this innovation first before I explain the details for the inquisitive minds.

An overview of Dynamic workload capping architecture

PatentArtech.png

Innovation solves the problem by dynamically changing LPAR defined capacity and Group capacity limits values by taking into account the dynamic changing of workload importance. This is done by interacting with Workload Manager (WLM) component of operating system that runs on each LPAR, for the breakdown of MSU use by WLM service class, period and importance class, then grouping by importance class and aggregating information across the multiple operating LPARs and across multiple SYSPLEX groupings, whose CPU capacity is being managed.

The result is a dynamic capping solution that reduces MLC costs while mitigating risk to critical business workloads.

Let’s walk through an example of how this innovation can make a big difference in saving cost while also mitigating risk.

problem

In this example,

  • There LPARS – LPAR1,  LPAR2 and LPAR3
  • the red line represents the Defined Capacity (DC) for each LPAR
  • the orange fill is (low)importance 5 workload and
  • the red-ish fill is (high) importance 1 workload.

Problem:

Each LPAR has it’s own static DC. LPAR1 has a lot of high importance work and it’s being capped. But LPAR2 and LPAR3 have free capacity, not capped and running  lot of low importance work. The max 4HRA for this scenario is 811 MSU

Today, someone would have to watch these LPARs and manually adjust the DCs to allow the high imp work to run and make decisions about how to balance with other LPARs – 24×7 – impractical!

With innovation:

Now let’s bring in patented solution  to manage these same 3 LPARs with the same amount of work.  You can see that the configuration is monitored constantly and DCs are no longer a static straight line but rather adjusted dynamically to maximize capacity for important workloads. The result – No more capping of high importance work! capacity automatically transferred from LPAR2 and LPAR3 to LPAR 1 to allow high imp work to process at the expense of some low imp work on LPAR2 and LPAR3.

Not only is there no capping of high imp work but the overall MSU usage was lowered to 650 (from 811) by dynamic sharing capacity across the LPARs.

This innovation solution lead to a innovate product - BMC intelligent capping (iCap)

Intelligent Capping for zEnterprise (iCap) is a mainframe software solution that dynamically automates and optimizes defined capacity settings to lower IBM Monthly License Cost (MLC) costs by 2%-5% or more saving customers millions of dollars, while mitigating risk to the business. After analyzing CPU usage and WLM workload, iCap automatically manages changes to defined capacity settings based on workload profiles, enabling customers to lower costs. BMC Intelligent Capping for zEnterprise removes the manual effort from managing capping limits, while optimizing capacity usage across LPARs or groups of LPARs. The solution dynamically aligns workload allocations based on utilization needs, workload importance, and customer policy profiles

iCap architecture

icaparch

For more information (including a 2 min short video on how iCap works) please visit http://www.bmc.com/it-solutions/intelligent-capping-zenterprise.html

Now let’s see what industry and customers are saying about it.

cust

There are many more customers who saw significant savings with iCap.

Stay tuned!  BMC engineers are saying more to come – disruptive innovation that is!

Filter Blog

By date:
By tag: