Management, please read and reward your true heroes
Often when you do the right things in performance and capacity management, your work goes unnoticed and unappreciated. In fact, if you are consistently pro-active with your storage performance and capacity management processes, you will have few opportunities to be in the spotlight. This is because pro-active management reduces the number of crises and, consequently, the need for heroic action!
For those who want to live dangerously, consider avoiding the following activities:
- Monitor storage for performance risk. More than just determining whether your storage has exceeded response time goals, also regularly analyze the actual storage system throughput against storage controller capability to understand how close you are to the performance cliff.
- Define Storage Performance Service Level Objectives (SLOs) for response time for different tiers with your business units and closely monitor the SLOs for each tier. Use pro-active analysis to determine whether the SLOs for a tier are endangered and make the appropriate adjustments to preserve SLO compliance (e.g. – adding spindles to the endangered tier).
- Monitor storage for imbalances in the front-end adapters and ports due to improper zoning, insufficient host-ports or improperly configured speeds on the fabric path. Provide recommendations to engineering to resolve imbalances, improve throughput, and reduce the probable impact to SLOs (e.g. – redistributing workload across existing ports to spread traffic more evenly).
- Monitor capacity trends to determine which tiers and pools are going to run out of space and provide regular and timely feedback to the storage management team about needed adjustments.
- Analyze the access density of the hosts to determine if they are utilizing the appropriate storage tier needed to meet SLOs at the lowest possible costs, e.g. move hosts with lots of capacity and very little I/O from higher to lower performance tiers.
While the title of this blog is a bit tongue-in-cheek, the tension between the ego affirming opportunities provided by reactive heroics and the ego depriving reality of proactive performance and capacity management is real. So why not reward storage management for meeting SLOs? If there is a cost of missing SLOs, then certainly there is a real reward for meeting them. Too often SLOs are only used in the negative sense. Rewarding storage management for identifying and reducing performance risk in the environment is a more positive approach. Providing the right tools and personnel to complete the job properly could make every day heroics routine.
For more information about pro-actively managing your storage performance and capacity please visit https://www.intellimagic.com
IBM z15 Announcement Highlights and How to Take Advantage
The z15 (with a General Availability date of 9/23/2019) offers up to 190 CPU cores (vs. 170 on z14) and 40 TB of usable memory (vs. 32 on z14), in addition to processor cache and overall performance improvements.
Top Performance Strategies for Black Friday, Cyber Monday, and other Peak Periods
Learn about performance strategies to handle your peak periods, like Black Friday and Cyber Monday, so that your infrastructure is able to deliver the required availability.
How to Learn (Almost Anything) from RMF & SMF Data
Learn how to gain a vision for how rapidly you could leverage easy visibility into RMF and SMF data to expand your understanding of how the z/OS ecosystem operates.
Subscribe to our Newsletter
Subscribe to our newsletter and receive monthly updates about the latest industry news and high quality content, like webinars, blogs, white papers, and more.