Start of change

Configuring z/OS workload management for Apache Spark

One of the strengths of the z Systems platform and the z/OS operating system is the ability to run multiple workloads at the same time within one z/OS image or across a Parallel Sysplex. Workloads usually have different, often competing, performance and resource requirements that must be balanced to make the best use of an installation's resources, maintain the highest possible throughput, and achieve the best possible system responsiveness. The function that makes this possible is dynamic workload management, which is implemented in the workload management component of z/OS.

With z/OS workload management (WLM), you define performance goals and assign a business importance to each goal. You define the goals for work in business terms, and the system decides how much resource, such as CPU or memory, to assign so as to meet the goal. WLM constantly monitors the system and adapts processing to meet the goals.

You can configure WLM to manage IBM® z/OS® Platform for Apache Spark workloads to optimize system performance.

Note: The following topics discuss some new functions in z/OS Platform for Apache Spark, including the memory limit and honor priority attributes in WLM. The IBM.Function.ApacheSpark fix category and the APSPARKF/K keyword in RETAIN identify the PTFs that enable these new functions.
End of change