Comment Monitorer la Santé des Conteneurs Docker

FROM node:18-alpine

WORKDIR /app
COPY . .
RUN npm install

# Configuration du health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
  CMD curl -f http://localhost:3000/health || exit 1

CMD ["npm", "start"]

# Voir le statut de santé
docker inspect --format='{{.State.Health.Status}}' container_name

# Observer les health checks en temps réel
docker events --filter event=health_status

# Lister tous les conteneurs avec statut de santé
docker ps --format "table {{.Names}}\t{{.Status}}"

// Express.js
app.get('/health', (req, res) => {
  res.status(200).json({ status: 'healthy' });
});

app.get('/health', async (req, res) => {
  const health = {
    status: 'healthy',
    timestamp: new Date().toISOString(),
    checks: {}
  };

  // Vérifier la base de données
  try {
    await db.query('SELECT 1');
    health.checks.database = 'ok';
  } catch (err) {
    health.checks.database = 'fail';
    health.status = 'unhealthy';
  }

  // Vérifier Redis
  try {
    await redis.ping();
    health.checks.redis = 'ok';
  } catch (err) {
    health.checks.redis = 'fail';
    health.status = 'unhealthy';
  }

  const statusCode = health.status === 'healthy' ? 200 : 503;
  res.status(statusCode).json(health);
});

version: '3.8'

services:
  web:
    build: .
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    depends_on:
      db:
        condition: service_healthy

  db:
    image: postgres:15
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U postgres"]
      interval: 10s
      timeout: 5s
      retries: 5

# Stats en temps réel
docker stats

# Stats pour des conteneurs spécifiques
docker stats web db redis

# Snapshot unique
docker stats --no-stream

#!/bin/bash
# container-watch.sh

CONTAINER="my-app"
LAST_STARTED=""

while true; do
  STARTED=$(docker inspect --format='{{.State.StartedAt}}' $CONTAINER)

  if [ "$LAST_STARTED" != "" ] && [ "$STARTED" != "$LAST_STARTED" ]; then
    # Conteneur redémarré - envoyer alerte
    curl -X POST "https://your-webhook-url" \
      -d "{\"text\": \"Conteneur $CONTAINER redémarré\"}"
  fi

  LAST_STARTED=$STARTED
  sleep 60
done

# docker-compose.yml
services:
  web:
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

# Observer les erreurs en temps réel
docker logs -f container_name 2>&1 | grep -i error