How can you safely and effectively exclude a node from an active Kubernetes cluster?

To safely and effectively remove a node from an active Kubernetes cluster, follow these steps:

1. Drain the node — puts the node into a state where no new pods are scheduled on it, and existing pods are gracefully terminated and rescheduled on other nodes:

kubectl drain <node-name> --ignore-daemonsets --delete-local-data

• --ignore-daemonsets allows daemonset pods to remain on the node.
• --delete-local-data deletes pods with local data, if any.

2. Verify that all pods are evacuated:

kubectl get pods --all-namespaces -o wide | grep <node-name>

3. Remove the node from the cluster (if necessary):

kubectl delete node <node-name>

This way, you first properly shut down the pods on the node, preventing data loss and failures, and then remove the node from the cluster.