Starting with z/OS® Release V1R4 and JES2 V1R4, and z/OS V1R5 with JES V1R5 WLM is enhanced to improve the balancing of WLM managed batch initiators between systems of a sysplex. While in earlier releases a balancing of initiators between high and low loaded systems was only done when new initiators were started, this is now done when initiators are already available. On highly utilized systems, the number of initiators is reduced while new ones are started on low utilized systems. This enhancement can improve sysplex performance with better use of the processing capability of each system. WLM attempts to distribute the initiators across all members in the sysplex to reduce batch work on highly used systems while taking care that jobs with affinities to specific systems are not hurt by WLM decisions. Initiators are stopped on systems that are utilized over 95% when another system in the sysplex offers the required capacity for such an initiator. WLM also increases the number of initiators more aggressively when a system is low utilized and jobs are waiting for execution.
Batch Initiator Balancing improves the performance and throughput of batch workload over the sysplex. Its intention is not to reach an equally balanced distribution of batch jobs over the LPARs of a sysplex. That is why initiator balancing only comes into effect, when at least one of the systems of the sysplex has a CPU utilization of more than 95%, while other systems have more idle capacity. When the most loaded system has still enough idle capacity to run batch jobs without CPU constraints, it would not improve the total batch throughput if initiators were moved away from that system to other systems, even if the other systems had more idle CPU capacity.