sa-lessons/modules/module9/sections/04-devops-culture.md

DevOps культура

Навигация

• 🏠 Главная страница курса
• 📚 Модуль 9

---

Принципы DevOps

1. Collaboration

• Тесное взаимодействие между разработкой и операциями
• Общие цели и метрики
• Культура взаимопомощи

2. Automation

• Автоматизация рутинных процессов
• Infrastructure as Code
• Continuous Integration/Continuous Deployment

3. Monitoring

• Непрерывный мониторинг системы
• Проактивное выявление проблем
• Быстрое восстановление

4. Feedback

• Быстрая обратная связь
• Непрерывное улучшение
• Обучение на ошибках

DevOps Practices

1. Continuous Integration (CI)

# GitHub Actions CI Pipeline
name: CI/CD Pipeline

on:
  push:
    branches: [ main, develop ]
  pull_request:
    branches: [ main ]

jobs:
  test:
    runs-on: ubuntu-latest
    
    steps:
    - uses: actions/checkout@v3
    
    - name: Set up JDK 17
      uses: actions/setup-java@v3
      with:
        java-version: '17'
        distribution: 'temurin'
    
    - name: Cache Maven dependencies
      uses: actions/cache@v3
      with:
        path: ~/.m2
        key: ${{ runner.os }}-m2-${{ hashFiles('**/pom.xml') }}
        restore-keys: ${{ runner.os }}-m2
    
    - name: Run tests
      run: mvn clean test
    
    - name: Generate test report
      uses: dorny/test-reporter@v1
      if: success() || failure()
      with:
        name: Maven Tests
        path: target/surefire-reports/*.xml
        reporter: java-junit

  build:
    needs: test
    runs-on: ubuntu-latest
    
    steps:
    - uses: actions/checkout@v3
    
    - name: Set up JDK 17
      uses: actions/setup-java@v3
      with:
        java-version: '17'
        distribution: 'temurin'
    
    - name: Build with Maven
      run: mvn clean package -DskipTests
    
    - name: Build Docker image
      run: docker build -t myapp:${{ github.sha }} .
    
    - name: Push to registry
      run: |
        echo ${{ secrets.DOCKER_PASSWORD }} | docker login -u ${{ secrets.DOCKER_USERNAME }} --password-stdin
        docker push myapp:${{ github.sha }}

  deploy:
    needs: build
    runs-on: ubuntu-latest
    if: github.ref == 'refs/heads/main'
    
    steps:
    - name: Deploy to production
      run: |
        echo "Deploying to production..."
        # Deployment logic here

2. Continuous Deployment (CD)

# Kubernetes Deployment
apiVersion: apps/v1
kind: Deployment
metadata:
  name: myapp
  labels:
    app: myapp
spec:
  replicas: 3
  selector:
    matchLabels:
      app: myapp
  template:
    metadata:
      labels:
        app: myapp
    spec:
      containers:
      - name: myapp
        image: myapp:latest
        ports:
        - containerPort: 8080
        env:
        - name: SPRING_PROFILES_ACTIVE
          value: "production"
        - name: DATABASE_URL
          valueFrom:
            secretKeyRef:
              name: myapp-secrets
              key: database-url
        resources:
          requests:
            memory: "256Mi"
            cpu: "250m"
          limits:
            memory: "512Mi"
            cpu: "500m"
        livenessProbe:
          httpGet:
            path: /actuator/health
            port: 8080
          initialDelaySeconds: 30
          periodSeconds: 10
        readinessProbe:
          httpGet:
            path: /actuator/health/readiness
            port: 8080
          initialDelaySeconds: 5
          periodSeconds: 5

---
apiVersion: v1
kind: Service
metadata:
  name: myapp-service
spec:
  selector:
    app: myapp
  ports:
  - protocol: TCP
    port: 80
    targetPort: 8080
  type: LoadBalancer

3. Infrastructure as Code (IaC)

# Terraform configuration
terraform {
  required_providers {
    aws = {
      source  = "hashicorp/aws"
      version = "~> 5.0"
    }
  }
}

provider "aws" {
  region = var.aws_region
}

# VPC
resource "aws_vpc" "main" {
  cidr_block           = "10.0.0.0/16"
  enable_dns_hostnames = true
  enable_dns_support   = true

  tags = {
    Name = "${var.project_name}-vpc"
  }
}

# Subnets
resource "aws_subnet" "public" {
  count = length(var.availability_zones)

  vpc_id                  = aws_vpc.main.id
  cidr_block              = "10.0.${count.index + 1}.0/24"
  availability_zone       = var.availability_zones[count.index]
  map_public_ip_on_launch = true

  tags = {
    Name = "${var.project_name}-public-subnet-${count.index + 1}"
  }
}

resource "aws_subnet" "private" {
  count = length(var.availability_zones)

  vpc_id            = aws_vpc.main.id
  cidr_block        = "10.0.${count.index + 10}.0/24"
  availability_zone = var.availability_zones[count.index]

  tags = {
    Name = "${var.project_name}-private-subnet-${count.index + 1}"
  }
}

# Security Groups
resource "aws_security_group" "web" {
  name_prefix = "${var.project_name}-web-"
  vpc_id      = aws_vpc.main.id

  ingress {
    from_port   = 80
    to_port     = 80
    protocol    = "tcp"
    cidr_blocks = ["0.0.0.0/0"]
  }

  ingress {
    from_port   = 443
    to_port     = 443
    protocol    = "tcp"
    cidr_blocks = ["0.0.0.0/0"]
  }

  egress {
    from_port   = 0
    to_port     = 0
    protocol    = "-1"
    cidr_blocks = ["0.0.0.0/0"]
  }

  tags = {
    Name = "${var.project_name}-web-sg"
  }
}

# RDS Database
resource "aws_db_subnet_group" "main" {
  name       = "${var.project_name}-db-subnet-group"
  subnet_ids = aws_subnet.private[*].id

  tags = {
    Name = "${var.project_name}-db-subnet-group"
  }
}

resource "aws_db_instance" "main" {
  identifier = "${var.project_name}-db"

  engine         = "postgres"
  engine_version = "14.7"
  instance_class = var.db_instance_class

  allocated_storage     = 20
  max_allocated_storage = 100
  storage_type          = "gp2"
  storage_encrypted     = true

  db_name  = var.db_name
  username = var.db_username
  password = var.db_password

  vpc_security_group_ids = [aws_security_group.db.id]
  db_subnet_group_name   = aws_db_subnet_group.main.name

  backup_retention_period = 7
  backup_window          = "03:00-04:00"
  maintenance_window     = "sun:04:00-sun:05:00"

  skip_final_snapshot = var.environment != "production"

  tags = {
    Name = "${var.project_name}-db"
  }
}

4. Monitoring and Logging

# Prometheus configuration
global:
  scrape_interval: 15s
  evaluation_interval: 15s

rule_files:
  - "alert_rules.yml"

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']

  - job_name: 'myapp'
    static_configs:
      - targets: ['myapp:8080']
    metrics_path: '/actuator/prometheus'
    scrape_interval: 5s

  - job_name: 'node-exporter'
    static_configs:
      - targets: ['node-exporter:9100']

alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - alertmanager:9093

---
# Grafana dashboard
apiVersion: v1
kind: ConfigMap
metadata:
  name: grafana-dashboard
data:
  dashboard.json: |
    {
      "dashboard": {
        "title": "MyApp Dashboard",
        "panels": [
          {
            "title": "Request Rate",
            "type": "graph",
            "targets": [
              {
                "expr": "rate(http_requests_total[5m])",
                "legendFormat": "{{method}} {{endpoint}}"
              }
            ]
          },
          {
            "title": "Response Time",
            "type": "graph",
            "targets": [
              {
                "expr": "histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))",
                "legendFormat": "95th percentile"
              }
            ]
          },
          {
            "title": "Error Rate",
            "type": "graph",
            "targets": [
              {
                "expr": "rate(http_requests_total{status=~\"5..\"}[5m])",
                "legendFormat": "5xx errors"
              }
            ]
          }
        ]
      }
    }

DevOps Tools

1. Version Control

• Git для управления кодом
• GitFlow для управления ветками
• Pull Request для code review

2. CI/CD

• GitHub Actions
• GitLab CI/CD
• Jenkins
• Azure DevOps

3. Containerization

• Docker для контейнеризации
• Kubernetes для оркестрации
• Helm для управления пакетами

4. Monitoring

• Prometheus для метрик
• Grafana для визуализации
• ELK Stack для логирования
• Jaeger для трассировки

Best Practices

1. Culture

• Создание культуры доверия
• Общие цели и метрики
• Непрерывное обучение

2. Automation

• Автоматизация всех процессов
• Infrastructure as Code
• Self-healing systems

3. Monitoring

• Comprehensive monitoring
• Proactive alerting
• Fast incident response

4. Security

• Security by design
• Automated security testing
• Regular security audits