In the helm readme, the default command includes --set persistence.enabled=true. However, with this parameter included on a k8s environment that doesn't have auto PV provisioning, the NIM will fail to deploy and the pod will stay in a pending state.
Warning FailedScheduling 2m25s default-scheduler 0/1 nodes are available: pod has unbound immediate PersistentVolumeClaims. preemption: 0/1 nodes are available: 1 Preemption is not helpful for scheduling..
Recommend either removing that flag or adding more explanation to the user to explain the storage requirement expected of the k8s environment.
In the helm readme, the default command includes
--set persistence.enabled=true. However, with this parameter included on a k8s environment that doesn't have auto PV provisioning, the NIM will fail to deploy and the pod will stay in a pending state.Recommend either removing that flag or adding more explanation to the user to explain the storage requirement expected of the k8s environment.