How to fix DaemonSet rollout stuck, pod not rolling to new template in Kubernetes

# Check rollout status:
kubectl rollout status daemonset -n <namespace> <name>

# Get full DaemonSet details:
kubectl describe daemonset -n <namespace> <name> | tail -30

# Check which nodes are updated:
kubectl get pods -n <namespace> -l <label> -o wide | grep <daemonset>

# Look for status conditions
kubectl get daemonset -n <namespace> <name> -o yaml | grep -A 10 status:

# Get current DaemonSet definition:
kubectl get daemonset -n <namespace> <name> -o yaml > current.yaml

# Check image:
cat current.yaml | grep image:

# Check if image exists and is accessible:
kubectl run -it --rm debug --image=<new-image> -- echo "Image works"

# Check pod spec for obvious errors:
kubectl get daemonset -n <namespace> <name> -o json | jq .spec.template.spec

# Find a new pod that's stuck:
kubectl get pods -n <namespace> -l <label> -o wide

# Check pod status:
kubectl describe pod -n <namespace> <new-pod-name>

# Check logs:
kubectl logs -n <namespace> <new-pod-name> --all-containers=true

# If pod is crashing:
kubectl logs -n <namespace> <new-pod-name> --previous

# Check events for specific errors:
kubectl describe pod -n <namespace> <new-pod-name> | grep -A 20 Events:

# Check all node resource status:
kubectl top nodes

# Detailed view of a specific node:
kubectl describe node <node-name>

# Check for resource pressure conditions:
kubectl get nodes -o json | jq '.items[] | {name:.metadata.name, conditions:.status.conditions[]}'

# If node is under pressure, free resources:
# - Drain and evict non-critical pods
# - Increase node size
# - Use cluster autoscaler to add nodes

# Option 1: Rollback to previous version
kubectl rollout undo daemonset -n <namespace> <name>

# Option 2: Fix template and update
kubectl set image daemonset/<name> <container>=<new-image> -n <namespace>

# Option 3: Edit YAML directly
kubectl edit daemonset -n <namespace> <name>
# Fix the image or config, save and exit

# Verify the fix works:
kubectl rollout status daemonset -n <namespace> <name>

kubectl edit daemonset -n <namespace> <name>

spec:
  updateStrategy:
    type: RollingUpdate
    rollingUpdate:
      maxUnavailable: 1  # Allow 1 pod unavailable per node during update

# Find the stuck node:
kubectl get pods -n <namespace> -o wide | grep <old-image>

# Delete the old pod (forces DaemonSet to recreate it):
kubectl delete pod -n <namespace> <old-pod-name>

# Watch the new pod creation:
kubectl get pods -n <namespace> -w

# Wait for it to be Ready, then continue:
kubectl rollout status daemonset -n <namespace> <name>

# Check rollout is complete:
kubectl rollout status daemonset -n <namespace> <name>

# Verify all pods have new image:
kubectl get pods -n <namespace> -l <label> -o wide --sort-by=.spec.containers[0].image

# Check DaemonSet metrics:
kubectl get daemonset -n <namespace> <name>
# Desired, Current, Ready should all match

# All pods should show the new image in 'IMAGE' column