As a seasoned IT performance and capacity specialist, I’ve had to consider some unexpected challenges over the years. September 11th, 2001 and the impacts to travel & transportation that ensued might be similar to what we’re being confronted with today. Regardless, this certainly has been a year that has stretched everyone and I’m sure challenges that weren’t even on the radar in January have landed in your lap. Today I’ll cover two scenarios that you may be dealing with and wondering how you’re are going to meet those challenges.
- Need an answer right away and it’s in an area you are unfamiliar with.
- You need solid advice on optimization opportunities that take little effort to implement.
The scenarios are outlined below. They are real customer interactions of IntelliMagic consultants working with their customers.
XCF Workload Analysis – Now
A somewhat atypical customer request (email) @1:02PM on an otherwise ordinary day:
“Please hop on: https://noname.webex.com/join/jdoe”
That’s it. Good thing I check emails frequently.
A brief outline of the background and outcome:
The customer was reconfiguring a middleware component that would introduce a significant XCF workload, and it had to perform very well. This is something that could affect 20,000 users of their system in the weeks of migration ahead, and a problem was experienced with only 200 testing users–so that is why our customer was looking for a quick assist.
I was able to easily review their XCF infrastructure (the ‘black box’) which is typically something that most folks spend little time looking after and is often misunderstood. He looked at our IntelliMagic Vision reporting available in the Cloud and asked about a report that IntelliMagic Vision’s automatic ratings had highlighted.
After reviewing a Watson & Walker (a key IntelliMagic Partner) article on XCF (subscription required to read), we walked through the XCF reporting and provided our customer the beginnings of an XCF dashboard in only 30 minutes.
Later, some other reports were shared (as links in an email) so that these could be added to the dashboard, if warranted. Figure 2 represents the XCF Tracking Dashboard after those links were added.
Specifics down to XCF member, LPAR traffic, and address space level activity were easily combined in one place for a quick look each morning. Selections like shift, workdays, and other options make the dashboard more meaningful for a particular situation.
The bottom line is that IntelliMagic Vision and other contributors, including our partners, provide nimble and effective responses that help folks rest at night. This customer shared a good appreciation of what IntelliMagic delivers in the software and services by saying: “I love this platform!”
That’s high praise from a demanding customer! How do we do that?
- Our IT and support teams manage to help with all kinds of changeups on the processing and reporting side as new features and functions are rolled out, and as our customers find new ways to surprise us with their data.
- Our consultants are always eager to share and help each other field customer questions.
- Our z/OS performance analysis software is world-class, and our customers don’t always have time to attend our webinars.
We were able to rapidly demonstrate new dashboards to them and show how to quickly edit a report to suit their situation. This was easy because lots of good work went into developing a platform that makes our customers better at many things.
Solid Advice on Sneaky Savings
Some of our customers have us look into their systems daily to keep an eye on Service Class Performance, zIIP eligible work on GPs and many other key infrastructure components. Here’s one example of items we’ve identified and recommended actions that were taken to realize savings:
Shared coupling facility and Dynamic Dispatch=THIN
Observing high usage of CP from spin wait for synchronous CF requests is something that might go unnoticed for a while, especially in a non-production environment. However, regardless of your licensing agreement, this unnecessary overhead can be avoided.
Figure 3 shows a comparison chart for the Average CP Usage for Sync CF Requests. The original CP usage (on the left side) shows CP usage reaching close to 1100ms/s from two LPARS (red, blue).
The right side of the comparison chart shows the results after the client implemented a configuration change for shared coupling facility processors.
This change saved a full CP of overhead. That’s approximately 180 MSU.
The setting: DYNDISP=THIN.
Regardless of your software agreement, this provides ongoing software savings opportunities, while providing more room for productive business growth.
The high synchronous service times had been highlighted, and the change was recommended. When the change was made (7/17) it resulted in a dramatic decrease in CP overhead. The DYNDISP setting was also implemented on another test sysplex which also resulted in lowering overhead. Another consideration may include investigating dedicated CF processors cost, rather than using shared processors.
Let Us Help Relieve Your “Stretch”
As time marches on into 2021, you may want to consider partnering with someone to help. We would welcome an opportunity to be that partner. That’s a bold offer, but we believe these examples back that up!
In the past several months, our team at IntelliMagic has been quietly and quickly responding to our customers’ and others’ needs in the industry with a steady stream of ways to assist you with your work. Starting with IntelliMagic zAcademy training sessions, there have been a number of ways outlined that provide helpful advice, point out opportunities for savings, and demonstrate landmine avoidance.
Everyone wants to know about those disasters looking for a date, and we are here to help with our software and solutions. We can provide timely answers for a broad spectrum of issues. The real-life examples above demonstrated a few of the capabilities our platform and services can provide. If 2020 has you stretched, why not let us help provide some peace of mind by knowing that someone is watching your back.
Start a Free Trial of IntelliMagic Vision for z/OS
Modernize your approach to mainframe performance management by moving away from static reports towards interactive, context-driven analytics for your end-to-end z/OS infrastructure.
Is this z/OS workload change normal? Utilizing z/OS Anomaly Detection
z/OS Anomaly Detection allows analysts to automatically detect workload and application changes, saving them countless hours of manual labor and intensive scrutiny while trying to determine the significance of changes
Is Some Automation Unnecessary Noise or Just Lower Priority Work?
Computers are great at doing what we tell them. They don’t get tired, bored, or complain about the endless work we have them doing. But sometimes automation is running in not so obvious places. Learn some practical guidance for managing those workloads.
What’s New? zEDC and the Nest Accelerator Unit (NXU)
Advancements similar to the NXU are likely to become more commonplace since raw processor speeds have plateaued. Specialized processing drives new metrics to manage an already complex system. What’s affected? How will you keep up?