KubernetesClusterAutoScalerProfile

Detect similar node groups and balance the number of nodes between them. Defaults to false.

Maximum number of empty nodes that can be deleted at the same time. Defaults to 10.

Expander to use. Possible values are least-waste, priority, most-pods and random. Defaults to random.

Maximum number of seconds the cluster autoscaler waits for pod termination when trying to scale down a node. Defaults to 600.

Maximum time the autoscaler waits for a node to be provisioned. Defaults to 15m.

Maximum Number of allowed unready nodes. Defaults to 3.

Maximum percentage of unready nodes the cluster autoscaler will stop if the percentage is exceeded. Defaults to 45.

For scenarios like burst/batch scale where you don't want CA to act before the kubernetes scheduler could schedule all the pods, you can tell CA to ignore unscheduled pods before they're a certain age. Defaults to 10s.

How long after the scale up of AKS nodes the scale down evaluation resumes. Defaults to 10m.

How long after node deletion that scale down evaluation resumes. Defaults to the value used for scan_interval.

How long after scale down failure that scale down evaluation resumes. Defaults to 3m.

How long a node should be unneeded before it is eligible for scale down. Defaults to 10m.

How long an unready node should be unneeded before it is eligible for scale down. Defaults to 20m.

Node utilization level, defined as sum of requested resources divided by capacity, below which a node can be considered for scale down. Defaults to 0.5.

How often the AKS Cluster should be re-evaluated for scale up/down. Defaults to 10s.

If true cluster autoscaler will never delete nodes with pods with local storage, for example, EmptyDir or HostPath. Defaults to true.

If true cluster autoscaler will never delete nodes with pods from kube-system (except for DaemonSet or mirror pods). Defaults to true.