Modern z/OS installations can be complex with many potential bottlenecks. This case study shows how IntelliMagic Vision may be used to easily find the root cause of a z/OS performance issue related to overloaded back-end drives. In fact, regular usage of IntelliMagic Vision can help you completely avoid issues like the one described here. Watch this case study and see how IntelliMagic Vision can deliver concrete benefits to your z/OS shop.

Video Transcript

In this video I’m going to demonstrate how IntelliMagic Vision may be used to isolate and resolve a performance problem in a large z/OS environment.

In this case the problem was reoccurring during a specific overnight time period. Many critical applications were suffering due to the slow down. We will show you how Vision was used to determine root cause and help define a concrete action plan.

Users were complaining about application slow downs during the overnight batch time period. Looking at the DASD during that period, we see elevated but not peak response times.

Next, we look at throughput along with response time and notice a spike in the total MB/sec at the same time as the elevated response time.

Splitting this out by Disk Storage System we notice that one particular unit stands out in terms of the response time peak.

The IntelliMagic Vision Dashboard clearly flags this storage system as having backend disk drive response time issues. It also points out that the throughput for this storage system is at a warning level. In fact if the dashboard had been regularly scanned, it is likely this problem could have been avoided altogether.

Drilling down from the dashboard, we see that the drive read response times are very high during the same time frame as the problem. Thus, it is likely that some of the drives are overloaded.

Drilling down to the storage pools we see that two of the six pools on this storage system are performing poorly. The other pools are all healthy.

Drilling down to the RAID arrays on one of the pools we find that the pool has only 4 RAID arrays in it. Possible solutions include adding more arrays to the pool or upgrading to faster disks or SSDs.

By looking at the back-end activity on the storage pools, we notice that during the problem time the write activity is highly increased on the problematic pools.

On the application side we can isolate the increase in back-end write load to just two LCUs. Rebalancing the workload is another option to resolve the problem.

This case study illustrates how IntelliMagic Vision made it easy to resolve this problem in a fast and efficient manner. As a result, further application slow downs would be avoided and staff would be free to work on other pressing matters.

If you would like to find out more about IntelliMagic Vision for your environment, please email us at info@intellimagic.com

Related

Blog

What’s New with IBM DS8900F?

Release 9.1 for the DS8900F storage array contains numerous product improvements that should be interesting and useful to any shop that has DS8900F installed or is considering it.

Read more
Blog

Understanding How Logical Workloads Behave On Physical Hardware

If you find elevated response time on a logical volume, how do you know which physical drives may be causing it?

Read more
Blog

AI: Too Much of a Good Thing

Solution providers will continue to entice us with bigger and better real-time analytics. Some of these should be employed, but first try to understand the logic you may be activating when you implement.

Read more

Go to Resources

Sign Up for a Free Trial

Experience firsthand the deepest visibility into your z/OS systems, processors, network, disk and tape environments. Whether you’re in the early stages of product research, evaluating competitive solutions, or trying to solve a problem, we’re happy to help you get the information you need to move forward with your IT initiatives.