How to fix Failing Liveness Probe in Kubernetes

kubectl get pod <pod-name> -n <namespace> -o yaml | grep -A 15 "livenessProbe:"
kubectl describe pod <pod-name> -n <namespace>  # Shows probe details

livenessProbe:
  httpGet:
    path: /health
    port: 8080
  initialDelaySeconds: 10  # Wait before first probe
  periodSeconds: 10        # Check every 10 seconds
  timeoutSeconds: 5        # Give 5 seconds to respond
  failureThreshold: 3      # Restart after 3 failures

# For HTTP probe:
kubectl exec -it <pod-name> -n <namespace> -- sh
curl -v http://localhost:8080/health
echo $?  # Check exit code

# For TCP probe:
kubectl exec <pod-name> -- nc -zv localhost 8080

# For exec probe:
kubectl exec <pod-name> -- /bin/health-check.sh
echo $?  # Should be 0 for success

# Check response details:
kubectl exec <pod-name> -- curl -v http://localhost:8080/health | head -20

# Check app logs for health check handling:
kubectl logs <pod-name> -n <namespace> | grep -i health

# Search code for the endpoint:
git grep -i "health\|liveness" -- app/

# For Java:
grep -r "@GetMapping.*health" src/
grep -r "@RequestMapping.*health" src/

# For Node.js:
grep -r "app.get.*health" .
grep -r "router.get.*health" .

# For Python:
grep -r "@app.route.*health" .

@app.route('/health')
def health():
    return {'status': 'ok'}, 200

# Watch pod start:
kubectl logs <pod-name> -n <namespace> -f

# Look for startup messages:
grep -i "listening\|started\|ready" /var/log/app.log

# Measure startup time:
time curl http://localhost:8080/health

# If startup is slow, increase initialDelaySeconds:
kubectl patch deployment <name> -n <namespace> -p '{"spec":{"template":{"spec":{"containers":[{"name":"<container>","livenessProbe":{"initialDelaySeconds":60}}]}}}}'

kubectl describe pod <pod-name> -n <namespace> | grep -E "Limits|Requests"
kubectl top pods <pod-name> -n <namespace>

# Check for OOMKill:
kubectl get pod <pod-name> -n <namespace> -o yaml | grep -i "reason\|exitCode"

# Increase resource limits:
kubectl set resources deployment <name> -n <namespace> \
  --limits=cpu=1,memory=1Gi \
  --requests=cpu=500m,memory=512Mi

# Edit the deployment:
kubectl edit deployment <name> -n <namespace>

# Or patch:
kubectl patch deployment <name> -n <namespace> -p

apiVersion: apps/v1
kind: Deployment
metadata:
  name: stable-app
spec:
  template:
    spec:
      containers:
      - name: app
        image: myapp:latest
        livenessProbe:
          httpGet:
            path: /health
            port: 8080
          initialDelaySeconds: 30   # Longer startup wait
          periodSeconds: 10         # Check less frequently
          timeoutSeconds: 10        # Give more time to respond
          failureThreshold: 5       # Allow 5 failures before restart

# Python/Flask example:
from flask import Flask, jsonify
app = Flask(__name__)

@app.route('/health', methods=['GET'])
def health():
    # Check dependencies
    try:
        # Check database connection
        db.session.execute('SELECT 1')
        # Check cache
        cache.ping()
        # Check other critical services
        return jsonify({'status': 'healthy'}), 200
    except Exception as e:
        print(f"Health check failed: {e}")
        return jsonify({'status': 'unhealthy'}), 503

apiVersion: apps/v1
kind: Deployment
metadata:
  name: healthy-app
spec:
  template:
    spec:
      containers:
      - name: app
        image: myapp:latest
        
        # Readiness: app started and can handle traffic
        readinessProbe:
          httpGet:
            path: /ready
            port: 8080
          initialDelaySeconds: 10
          periodSeconds: 5
          failureThreshold: 2
        
        # Liveness: container is alive (not deadlocked)
        livenessProbe:
          httpGet:
            path: /alive
            port: 8080
          initialDelaySeconds: 30
          periodSeconds: 30
          failureThreshold: 3  # Only restart if truly dead