This monitor tracks the aggregated CPU usage of the whole cluster. The value is calculated by averaging the CPU performance counter values of all nodes.
Sustained high CPU usage is usually caused by CPU intensive jobs occupying most or all nodes on the cluster. If most or all nodes of the cluster are occupied for an extended period of time, other jobs may need to wait in the queue for a longer duration than usual. It may be beneficial to also monitor job wait time when CPU usage is high for an extended period of time.
Use job policies to manage the load. You can also add more nodes to increase the capacity of the cluster.