Several people with real world experience responded and generally gave Workload Manager high marks. Several questions were raised during the discussion:

1. Can the Workload Manager force CPU idleness if you configure MinCPU?

2. Is there a danger that system processes get starved for CPU if the sum of the MinCPU for all workgroups exceeds some threshold value?

3. What is the overhead of Workload Manager?

4. What size system do you need for Workload Manager?

A member of the MPE/iX Lab provided answers (paraphrased here).

1. The MinCPU percentage is permissive. That is, if a workgroup cannot use the minimum percentage you assign it, any other process can use that CPU time. Therefore, a MinCPU percentage will never force the system to go idle unless absolutely no process is ready to use the CPU. The MaxCPU percentage cap is restrictive. If you assign a maximum CPU percentage to a workgroup, that cap will be enforced even if it means that the system must be idle if no other workgroups can use the CPU at that time.

2. Because of the fear of starving system processes, the algorithms in the dispatcher were changed so that system processes will override the minimum CPU percentage specifications for workgroups. Therefore, there is no danger of assigning minimum CPU percentages that have such a large total that system processes will be starved.

3. The extra overhead required to enforce CPU minimums and maximums turned out to be about 2 percent in cases where both minimums and maximums were being enforced. However, our tests used workloads that were not as complex as an actual production system might have.

4. The size or speed of the system does not determine the need for the Workload Manager: it is the presence or absence of competing populations of processes that need to be controlled.