kubernetes-patterns

apiVersion: apps/v1
kind: Deployment
metadata:
  name: my-app
  namespace: my-namespace
  labels:
    app: my-app
    version: "1.0.0"
spec:
  replicas: 3
  selector:
    matchLabels:
      app: my-app
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 1          # Allow 1 extra pod during update
      maxUnavailable: 0    # Never reduce below desired count
  template:
    metadata:
      labels:
        app: my-app
        version: "1.0.0"
    spec:
      # Security context at pod level
      securityContext:
        runAsNonRoot: true
        runAsUser: 1001
        fsGroup: 1001
 
      # Graceful shutdown
      terminationGracePeriodSeconds: 30
 
      containers:
        - name: my-app
          image: ghcr.io/org/my-app:1.0.0   # Never use :latest
          imagePullPolicy: IfNotPresent
 
          ports:
            - containerPort: 8080
              protocol: TCP
 
          # Resource requests AND limits are both required
          resources:
            requests:
              cpu: "100m"
              memory: "128Mi"
            limits:
              cpu: "500m"
              memory: "256Mi"
 
          # Container security context
          securityContext:
            allowPrivilegeEscalation: false
            readOnlyRootFilesystem: true
            capabilities:
              drop:
                - ALL
 
          # Probes (see Probes section below)
          startupProbe:
            httpGet:
              path: /health
              port: 8080
            failureThreshold: 30
            periodSeconds: 5
          livenessProbe:
            httpGet:
              path: /health
              port: 8080
            initialDelaySeconds: 0
            periodSeconds: 30
            failureThreshold: 3
          readinessProbe:
            httpGet:
              path: /ready
              port: 8080
            initialDelaySeconds: 5
            periodSeconds: 10
            failureThreshold: 2
 
          # Environment from ConfigMap and Secret
          envFrom:
            - configMapRef:
                name: my-app-config
          env:
            - name: DB_PASSWORD
              valueFrom:
                secretKeyRef:
                  name: my-app-secrets
                  key: db-password
 
          # Writable tmp directory when readOnlyRootFilesystem: true
          volumeMounts:
            - name: tmp
              mountPath: /tmp
 
      volumes:
        - name: tmp
          emptyDir: {}

# Correct pattern: startupProbe covers slow startup,
# then liveness/readiness take over
startupProbe:
  httpGet:
    path: /health
    port: 8080
  failureThreshold: 30  # 30 * 5s = 150s max startup time
  periodSeconds: 5
 
livenessProbe:
  httpGet:
    path: /health
    port: 8080
  periodSeconds: 30
  failureThreshold: 3   # 3 * 30s = 90s before restart
 
readinessProbe:
  httpGet:
    path: /ready         # Separate endpoint: checks DB, cache, etc.
    port: 8080
  periodSeconds: 10
  failureThreshold: 2

# WRONG: initialDelaySeconds without startupProbe
# If the app takes 60s to start, set a startupProbe instead
livenessProbe:
  httpGet:
    path: /health
    port: 8080
  initialDelaySeconds: 60   # BAD: Arbitrary wait, race condition

# ClusterIP (default) — internal-only
apiVersion: v1
kind: Service
metadata:
  name: my-app
  namespace: my-namespace
spec:
  selector:
    app: my-app
  ports:
    - port: 80
      targetPort: 8080
      protocol: TCP
  type: ClusterIP

# LoadBalancer — external traffic (cloud providers)
spec:
  type: LoadBalancer
  ports:
    - port: 443
      targetPort: 8080

apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: my-app
  namespace: my-namespace
  annotations:
    nginx.ingress.kubernetes.io/ssl-redirect: "true"
    cert-manager.io/cluster-issuer: "letsencrypt-prod"
spec:
  ingressClassName: nginx
  tls:
    - hosts:
        - myapp.example.com
      secretName: my-app-tls
  rules:
    - host: myapp.example.com
      http:
        paths:
          - path: /
            pathType: Prefix
            backend:
              service:
                name: my-app
                port:
                  number: 80

apiVersion: v1
kind: ConfigMap
metadata:
  name: my-app-config
  namespace: my-namespace
data:
  LOG_LEVEL: "info"
  APP_ENV: "production"
  MAX_CONNECTIONS: "100"
  # Mount as a file for complex config
  app.yaml: |
    server:
      port: 8080
      timeout: 30s

# Mount ConfigMap as a file
volumes:
  - name: config
    configMap:
      name: my-app-config
      items:
        - key: app.yaml
          path: app.yaml
volumeMounts:
  - name: config
    mountPath: /etc/app
    readOnly: true

# Create secret from literal (CLI, then store in Vault/SOPS)
kubectl create secret generic my-app-secrets \
  --from-literal=db-password='s3cr3t' \
  --namespace=my-namespace \
  --dry-run=client -o yaml | kubectl apply -f -

apiVersion: v1
kind: Secret
metadata:
  name: my-app-secrets
  namespace: my-namespace
type: Opaque
# Values are base64-encoded (NOT encrypted — use Sealed Secrets or ESO for real encryption)
data:
  db-password: czNjcjN0  # base64 of 's3cr3t'

resources:
  requests:       # Scheduler uses this to place the pod
    cpu: "100m"   # 100 millicores = 0.1 CPU
    memory: "128Mi"
  limits:         # Container is killed/throttled above this
    cpu: "500m"
    memory: "256Mi"

# WRONG: No requests or limits — unpredictable scheduling, OOM evictions
containers:
  - name: app
    image: myapp:latest
    # Missing resources: {} — this is dangerous in production
 
# WRONG: Limits without requests — requests default to limits, over-reserves capacity
resources:
  limits:
    cpu: "2"
    memory: "1Gi"
  # requests missing — will default to limits values

# ServiceAccount with token disabled — safest default
apiVersion: v1
kind: ServiceAccount
metadata:
  name: my-app-sa
  namespace: my-namespace
automountServiceAccountToken: false   # No K8s API token injected into pods

# Reference in Deployment — no token, no API access
spec:
  template:
    spec:
      serviceAccountName: my-app-sa
      automountServiceAccountToken: false   # Belt-and-suspenders: also set at pod level

# 1. ServiceAccount — enable token for this SA
apiVersion: v1
kind: ServiceAccount
metadata:
  name: my-app-sa
  namespace: my-namespace
automountServiceAccountToken: true    # Token required: app calls K8s API

# 2. Role — grant only what the app needs (namespace-scoped)
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  name: my-app-role
  namespace: my-namespace
rules:
  - apiGroups: [""]
    resources: ["configmaps"]
    verbs: ["get", "list", "watch"]    # Read-only, specific resource
  - apiGroups: [""]
    resources: ["secrets"]
    resourceNames: ["my-app-secrets"]  # Restrict to specific secret by name
    verbs: ["get"]

# 3. Bind Role to ServiceAccount
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  name: my-app-rolebinding
  namespace: my-namespace
subjects:
  - kind: ServiceAccount
    name: my-app-sa
    namespace: my-namespace
roleRef:
  kind: Role
  apiGroup: rbac.authorization.k8s.io
  name: my-app-role

# 4. Reference SA in Deployment
spec:
  template:
    spec:
      serviceAccountName: my-app-sa
      # automountServiceAccountToken defaults to true from SA — token is injected

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: my-app-hpa
  namespace: my-namespace
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: my-app
  minReplicas: 2      # Always at least 2 for HA
  maxReplicas: 10
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 70    # Scale up when avg CPU > 70%
    - type: Resource
      resource:
        name: memory
        target:
          type: Utilization
          averageUtilization: 80

apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
  name: my-app-pdb
  namespace: my-namespace
spec:
  minAvailable: 2           # OR use maxUnavailable: 1
  selector:
    matchLabels:
      app: my-app

# Create namespace with resource quotas
kubectl create namespace my-namespace
 
# Apply ResourceQuota to limit namespace consumption
kubectl apply -f - <<EOF
apiVersion: v1
kind: ResourceQuota
metadata:
  name: my-namespace-quota
  namespace: my-namespace
spec:
  hard:
    requests.cpu: "4"
    requests.memory: 4Gi
    limits.cpu: "8"
    limits.memory: 8Gi
    pods: "20"
EOF

# One-off Job (DB migration, data processing)
apiVersion: batch/v1
kind: Job
metadata:
  name: db-migrate
  namespace: my-namespace
spec:
  backoffLimit: 3          # Retry up to 3 times on failure
  ttlSecondsAfterFinished: 3600   # Auto-delete after 1h
  template:
    spec:
      restartPolicy: OnFailure    # Never for Jobs (not Always)
      containers:
        - name: migrate
          image: ghcr.io/org/my-app:1.0.0
          command: ["python", "manage.py", "migrate"]
          resources:
            requests:
              cpu: "100m"
              memory: "256Mi"

# CronJob
apiVersion: batch/v1
kind: CronJob
metadata:
  name: cleanup-job
  namespace: my-namespace
spec:
  schedule: "0 2 * * *"         # 2am daily
  concurrencyPolicy: Forbid      # Don't run if previous still running
  successfulJobsHistoryLimit: 3
  failedJobsHistoryLimit: 1
  jobTemplate:
    spec:
      template:
        spec:
          restartPolicy: OnFailure
          containers:
            - name: cleanup
              image: ghcr.io/org/cleanup:1.0.0
              resources:
                requests:
                  cpu: "50m"
                  memory: "64Mi"

# --- Pod status and logs ---
kubectl get pods -n my-namespace
kubectl get pods -n my-namespace -o wide          # Show node assignment
kubectl describe pod <pod-name> -n my-namespace   # Events and state details
kubectl logs <pod-name> -n my-namespace           # Current logs
kubectl logs <pod-name> -n my-namespace --previous  # Logs from crashed container
kubectl logs <pod-name> -n my-namespace -c <container>  # Multi-container pod
 
# --- Execute into a running container ---
kubectl exec -it <pod-name> -n my-namespace -- sh
kubectl exec -it <pod-name> -n my-namespace -- bash
 
# --- Check resource usage ---
kubectl top pods -n my-namespace
kubectl top nodes
 
# --- Deployment operations ---
kubectl rollout status deployment/my-app -n my-namespace
kubectl rollout history deployment/my-app -n my-namespace
kubectl rollout undo deployment/my-app -n my-namespace      # Rollback
kubectl rollout undo deployment/my-app --to-revision=2 -n my-namespace
 
# --- Scale manually ---
kubectl scale deployment my-app --replicas=5 -n my-namespace
 
# --- Inspect events (cluster-wide issues) ---
kubectl get events -n my-namespace --sort-by='.lastTimestamp'
 
# --- Port-forward for local debugging ---
kubectl port-forward pod/<pod-name> 8080:8080 -n my-namespace
kubectl port-forward svc/my-app 8080:80 -n my-namespace
 
# --- Dry-run to validate YAML ---
kubectl apply -f deployment.yaml --dry-run=client
kubectl apply -f deployment.yaml --dry-run=server   # Validates against live cluster

# CrashLoopBackOff: container keeps crashing
kubectl logs <pod-name> --previous -n my-namespace  # Check crash logs
kubectl describe pod <pod-name> -n my-namespace     # Check exit code & OOMKilled
 
# ImagePullBackOff: can't pull image
kubectl describe pod <pod-name> -n my-namespace     # Check Events section
# Causes: wrong image tag, missing imagePullSecret, private registry
 
# Pending pod: not scheduled
kubectl describe pod <pod-name> -n my-namespace
# Causes: insufficient resources, no matching node selector, taint/toleration mismatch
 
# OOMKilled: out of memory
# Increase memory limits, check for memory leaks
kubectl describe pod <pod-name> -n my-namespace | grep -A5 "Last State"

# BAD: Using :latest tag — non-deterministic deployments
image: myapp:latest
 
# GOOD: Pin to a specific immutable tag (SHA or semver)
image: ghcr.io/org/myapp:1.4.2
# or
image: ghcr.io/org/myapp@sha256:abc123...
 
# ---
 
# BAD: Running as root
securityContext: {}    # Defaults to root
 
# GOOD: Non-root with explicit UID
securityContext:
  runAsNonRoot: true
  runAsUser: 1001
 
# ---
 
# BAD: No resource limits — one pod can starve the entire node
containers:
  - name: app
    image: myapp:1.0.0
    # No resources defined
 
# GOOD: Always set requests and limits
resources:
  requests:
    cpu: "100m"
    memory: "128Mi"
  limits:
    cpu: "500m"
    memory: "256Mi"
 
# ---
 
# BAD: Storing plaintext secrets in ConfigMaps
apiVersion: v1
kind: ConfigMap
data:
  DB_PASSWORD: "mysecretpassword"   # NEVER — use Secret or external secrets manager
 
# ---
 
# BAD: ClusterAdmin for application service accounts
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
roleRef:
  kind: ClusterRole
  name: cluster-admin    # Grants god-mode to your app
 
# ---
 
# BAD: minAvailable: 0 in PDB — defeats the purpose
spec:
  minAvailable: 0
 
# ---
 
# BAD: restartPolicy: Always in a Job (causes infinite restart loop)
spec:
  restartPolicy: Always   # Use OnFailure or Never for Jobs