Как исправить Service health check failed в CI/CD

 1# Django health check endpoint
 2from django.http import JsonResponse
 3from django.db import connection
 4
 5def health_check(request):
 6    try:
 7        # Проверка подключения к БД
 8        with connection.cursor() as cursor:
 9            cursor.execute("SELECT 1")
10        
11        # Проверка других зависимостей
12        return JsonResponse({
13            'status': 'healthy',
14            'database': 'connected',
15            'timestamp': time.time()
16        })
17    except Exception as e:
18        return JsonResponse({
19            'status': 'unhealthy',
20            'error': str(e)
21        }, status=500)

 1# Dockerfile с health check
 2FROM python:3.11-slim
 3
 4WORKDIR /app
 5COPY requirements.txt .
 6RUN pip install -r requirements.txt
 7
 8COPY . .
 9
10# Настройка health check
11HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
12    CMD curl -f http://localhost:8000/health/ || exit 1
13
14EXPOSE 8000
15CMD ["python", "manage.py", "runserver", "0.0.0.0:8000"]

 1# k8s-deployment.yaml
 2apiVersion: apps/v1
 3kind: Deployment
 4metadata:
 5  name: my-app
 6spec:
 7  replicas: 3
 8  selector:
 9    matchLabels:
10      app: my-app
11  template:
12    metadata:
13      labels:
14        app: my-app
15    spec:
16      containers:
17      - name: my-app
18        image: my-app:latest
19        ports:
20        - containerPort: 8000
21        livenessProbe:
22          httpGet:
23            path: /health/
24            port: 8000
25          initialDelaySeconds: 30
26          periodSeconds: 10
27          timeoutSeconds: 5
28          failureThreshold: 3
29        readinessProbe:
30          httpGet:
31            path: /health/
32            port: 8000
33          initialDelaySeconds: 5
34          periodSeconds: 5
35          timeoutSeconds: 3
36          failureThreshold: 3

 1#!/bin/bash
 2# health-check-script.sh
 3
 4# Проверка CPU
 5cpu_usage=$(top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d'%' -f1)
 6if [ "$cpu_usage" -gt 90 ]; then
 7    echo "High CPU usage: ${cpu_usage}%"
 8    exit 1
 9fi
10
11# Проверка памяти
12memory_usage=$(free | grep Mem | awk '{printf("%.2f", $3/$2 * 100.0)}')
13if [ "$memory_usage" -gt 90 ]; then
14    echo "High memory usage: ${memory_usage}%"
15    exit 1
16fi
17
18# Проверка диска
19disk_usage=$(df / | tail -1 | awk '{print $5}' | cut -d'%' -f1)
20if [ "$disk_usage" -gt 90 ]; then
21    echo "High disk usage: ${disk_usage}%"
22    exit 1
23fi
24
25echo "System resources OK"

 1# .github/workflows/deploy.yml
 2name: Deploy with Health Check
 3on: [push]
 4
 5jobs:
 6  deploy:
 7    runs-on: ubuntu-latest
 8    steps:
 9    - uses: actions/checkout@v3
10    
11    - name: Deploy to staging
12      run: |
13        # Деплой приложения
14        kubectl apply -f k8s/
15    
16    - name: Wait for deployment
17      run: |
18        kubectl rollout status deployment/my-app --timeout=300s
19    
20    - name: Health check
21      run: |
22        # Ждем готовности подов
23        kubectl wait --for=condition=ready pod -l app=my-app --timeout=300s
24        
25        # Проверяем health check endpoint
26        for i in {1..30}; do
27          if curl -f http://staging.myapp.com/health/; then
28            echo "Health check passed"
29            break
30          fi
31          echo "Health check failed, retrying..."
32          sleep 10
33        done
34        
35        if [ $i -eq 30 ]; then
36          echo "Health check failed after 30 attempts"
37          exit 1
38        fi