Health Checks & Readiness Probes

# Kubernetes Deployment — health probe configuration
spec:
  containers:
  - name: order-service
    image: myregistry/order-service:1.2.3

    # Startup probe — runs first; liveness/readiness only start after this succeeds
    startupProbe:
      httpGet:
        path: /actuator/health/liveness
        port: 8081
      failureThreshold: 30    # 30 × 10s = 5 minutes for JVM to start
      periodSeconds: 10

    # Liveness probe — checked throughout lifetime; failure → restart
    livenessProbe:
      httpGet:
        path: /actuator/health/liveness
        port: 8081
      initialDelaySeconds: 0    # startup probe handles the delay
      periodSeconds: 10
      failureThreshold: 3

    # Readiness probe — failure → removed from load balancer
    readinessProbe:
      httpGet:
        path: /actuator/health/readiness
        port: 8081
      initialDelaySeconds: 5
      periodSeconds: 5
      failureThreshold: 3

# application.yml — expose liveness + readiness via Actuator
management:
  health:
    livenessState:
      enabled: true
    readinessState:
      enabled: true
  endpoint:
    health:
      group:
        liveness:
          include: livenessState
        readiness:
          include: "readinessState,db,redis"  # db+redis failure → not ready

// Programmatically change readiness state
@Component
@RequiredArgsConstructor
public class DatabaseWarmupRunner implements ApplicationRunner {

    private final ApplicationEventPublisher events;
    private final DataSource dataSource;

    @Override
    public void run(ApplicationArguments args) throws Exception {
        try {
            // Verify DB connection and warm up the connection pool
            dataSource.getConnection().close();
            // All good — signal ready for traffic
            events.publishEvent(new AvailabilityChangeEvent<>(this, ReadinessState.ACCEPTING_TRAFFIC));
        } catch (Exception e) {
            log.error("DB not available — staying in REFUSING_TRAFFIC state", e);
            events.publishEvent(new AvailabilityChangeEvent<>(this, ReadinessState.REFUSING_TRAFFIC));
        }
    }
}

# application.yml — graceful shutdown
server:
  shutdown: graceful
spring:
  lifecycle:
    timeout-per-shutdown-phase: 25s   # wait up to 25s for in-flight requests

# Kubernetes — terminationGracePeriodSeconds > Spring timeout
spec:
  terminationGracePeriodSeconds: 30   # 30s > 25s Spring timeout
  containers:
  - name: order-service
    lifecycle:
      preStop:
        exec:
          command: ["sh", "-c", "sleep 5"]  # give K8s 5s to drain from LB

# Shutdown sequence:
# 1. K8s sends SIGTERM → pod.Status.Phase = Terminating
# 2. Endpoints controller removes pod from Service (eventual, ~2-5s)
# 3. preStop hook: sleep 5s (overlap window for LB draining)
# 4. Spring graceful shutdown: stop accepting new requests
# 5. Wait up to 25s for in-flight requests to complete
# 6. Spring context closes (@PreDestroy, connection pools drained)
# 7. SIGKILL if still running after terminationGracePeriodSeconds