# Cluster overview
kubectl get nodes
kubectl get pods -A | grep -v Running

# Specific namespace
kubectl get pods -n <namespace>
kubectl get events -n <namespace> --sort-by='.lastTimestamp' | tail -20

# Resource usage
kubectl top nodes
kubectl top pods -n <namespace>

kubectl get pod <pod-name> -n <namespace> -o wide
kubectl describe pod <pod-name> -n <namespace>

kubectl describe pod <pod-name> -n <namespace> | grep -A 10 Events

# Check resource requests vs available
kubectl describe nodes | grep -A 5 "Allocated resources"

# Check pending pod requests
kubectl get pod <pod> -o yaml | grep -A 10 resources

# Check container logs (current)
kubectl logs <pod-name> -n <namespace>

# Check previous container logs
kubectl logs <pod-name> -n <namespace> --previous

# Check exit code
kubectl describe pod <pod-name> -n <namespace> | grep -A 3 "Last State"

kubectl describe pod <pod-name> -n <namespace> | grep -A 5 Events

# Create image pull secret
kubectl create secret docker-registry regcred \
  --docker-server=<registry> \
  --docker-username=<user> \
  --docker-password=<password> \
  -n <namespace>

# Reference in pod spec
spec:
  imagePullSecrets:
  - name: regcred

kubectl describe pod <pod-name> -n <namespace> | grep -i oom
kubectl get pod <pod-name> -n <namespace> -o yaml | grep -A 5 lastState

resources:
  limits:
    memory: '512Mi' # Increase this
  requests:
    memory: '256Mi'

kubectl top pod <pod-name> -n <namespace> --containers

# Check readiness probe
kubectl describe pod <pod-name> -n <namespace> | grep -A 10 Readiness

# Check probe endpoint manually
kubectl exec <pod-name> -n <namespace> -- wget -qO- localhost:<port>/health

readinessProbe:
  httpGet:
    path: /health
    port: 8080
  initialDelaySeconds: 10 # Give app time to start
  periodSeconds: 5
  timeoutSeconds: 3 # Increase if needed
  failureThreshold: 3

# Get detailed container status
kubectl get pod <pod-name> -n <namespace> -o jsonpath='{.status.containerStatuses[*]}'

# Check init containers
kubectl logs <pod-name> -n <namespace> -c <init-container-name>

# Check service endpoints
kubectl get endpoints <service-name> -n <namespace>

# Check service selector matches pod labels
kubectl get svc <service-name> -n <namespace> -o yaml | grep selector -A 5
kubectl get pods -n <namespace> --show-labels

# Test connectivity from another pod
kubectl run debug --rm -it --image=busybox -- wget -qO- <service>:<port>

# Check DNS resolution from pod
kubectl exec <pod> -n <namespace> -- nslookup <service-name>
kubectl exec <pod> -n <namespace> -- nslookup <service-name>.<namespace>.svc.cluster.local

# Check CoreDNS is running
kubectl get pods -n kube-system -l k8s-app=kube-dns

# Check node conditions
kubectl describe nodes | grep -A 5 Conditions

# Check node resource usage
kubectl top nodes

# Find resource-heavy pods
kubectl top pods -A --sort-by=memory | head -20

# Check PVC status
kubectl get pvc -n <namespace>

# Check PV status
kubectl get pv

# Describe for events
kubectl describe pvc <pvc-name> -n <namespace>

# Pod debugging
kubectl logs <pod> -n <ns>                    # Current logs
kubectl logs <pod> -n <ns> --previous         # Previous container logs
kubectl logs <pod> -n <ns> -c <container>     # Specific container
kubectl logs <pod> -n <ns> --tail=100 -f      # Follow logs

# Interactive debugging
kubectl exec -it <pod> -n <ns> -- /bin/sh     # Shell into container
kubectl exec <pod> -n <ns> -- env             # Check environment
kubectl exec <pod> -n <ns> -- cat /etc/hosts  # Check DNS

# Resource inspection
kubectl get pod <pod> -n <ns> -o yaml         # Full pod spec
kubectl describe pod <pod> -n <ns>            # Events and status
kubectl get events -n <ns> --sort-by='.lastTimestamp'

# Cluster-wide
kubectl get pods -A | grep -v Running         # Non-running pods
kubectl top pods -A --sort-by=cpu             # CPU usage
kubectl top pods -A --sort-by=memory          # Memory usage