# 创建监控配置
$ mkdir -p monitoring
$ cd monitoring
$ cat > docker-compose.yml << 'EOF'
version: '3'
services:
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
    ports:
      - "8080:8080"
    restart: always
  prometheus:
    image: prom/prometheus:latest
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./alert.rules.yml:/etc/prometheus/alert.rules.yml
    ports:
      - "9090:9090"
    restart: always
  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"
    restart: always
EOF

$ cat > prometheus.yml << 'EOF'
global:
  scrape_interval: 15s

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

rule_files:
  - "alert.rules.yml"

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
    - targets: ['localhost:9090']
  - job_name: 'cadvisor'
    static_configs:
    - targets: ['cadvisor:8080']
EOF

$ cat > alert.rules.yml << 'EOF'
groups:
- name: container_alerts
  rules:
  - alert: ContainerHighCPU
    expr: (sum by (container_name) (rate(container_cpu_usage_seconds_total{name!=""}[5m])) / sum by (container_name) (container_spec_cpu_quota{name!=""} / container_spec_cpu_period{name!=""})) * 100 > 80
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Container high CPU usage"
      description: "Container {{ $labels.container_name }} CPU usage is above 80% for 5 minutes"
  - alert: ContainerHighMemory
    expr: (sum by (container_name) (container_memory_usage_bytes{name!=""})) / (sum by (container_name) (container_spec_memory_limit_bytes{name!=""})) * 100 > 80
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Container high memory usage"
      description: "Container {{ $labels.container_name }} memory usage is above 80% for 5 minutes"
EOF

# 启动监控服务
$ docker-compose up -d

Creating network "monitoring_default" with the default driver
Creating monitoring_cadvisor_1    ... done
Creating monitoring_prometheus_1  ... done
Creating monitoring_grafana_1     ... done

# 访问Grafana
# 打开浏览器访问 http://localhost:3000
# 登录Grafana（默认用户名/密码：admin/admin）
# 添加Prometheus数据源（URL：http://prometheus:9090）
# 导入Docker容器监控仪表板（ID：193）

风哥提示：使用Prometheus和Grafana可以实现容器的实时监控和数据可视化，便于及时发现和解决问题。

4.2 日志管理实战

案例：使用ELK Stack收集和分析容器日志

# 创建日志管理配置
$ mkdir -p logging
$ cd logging
$ cat > docker-compose.yml << 'EOF'
version: '3'
services:
  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:7.17.0
    environment:
      - discovery.type=single-node
      - ES_JAVA_OPTS=-Xms1g -Xmx1g
    ports:
      - "9200:9200"
    volumes:
      - es_data:/usr/share/elasticsearch/data
    restart: always
  logstash:
    image: docker.elastic.co/logstash/logstash:7.17.0
    volumes:
      - ./logstash.conf:/usr/share/logstash/pipeline/logstash.conf
    ports:
      - "5044:5044"
    restart: always
  kibana:
    image: docker.elastic.co/kibana/kibana:7.17.0
    ports:
      - "5601:5601"
    restart: always
  filebeat:
    image: docker.elastic.co/beats/filebeat:7.17.0
    volumes:
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - ./filebeat.yml:/usr/share/filebeat/filebeat.yml
    restart: always
volumes:
  es_data:
EOF

$ cat > logstash.conf << 'EOF'
input {
  beats {
    port => 5044
  }
}

filter {
  if [docker][container][name] {
    mutate {
      add_field => { "container_name" => "%{[docker][container][name]}" }
    }
  }
}

output {
  elasticsearch {
    hosts => ["elasticsearch:9200"]
    index => "filebeat-%{+YYYY.MM.dd}"
  }
}
EOF

$ cat > filebeat.yml << 'EOF'
filebeat.inputs:
- type: container
  paths:
    - /var/lib/docker/containers/*/*.log
  processors:
    - add_docker_metadata: ~

output.logstash:
  hosts: ["logstash:5044"]
EOF

# 启动日志管理服务
$ docker-compose up -d

Creating network "logging_default" with the default driver
Creating logging_elasticsearch_1 ... done
Creating logging_logstash_1      ... done
Creating logging_kibana_1        ... done
Creating logging_filebeat_1      ... done

# 访问Kibana
# 打开浏览器访问 http://localhost:5601
# 配置索引模式（Pattern：filebeat-*）
# 在Discover页面查看和分析容器日志

# 创建告警配置
$ mkdir -p alerting
$ cd alerting
$ cat > docker-compose.yml << 'EOF'
version: '3'
services:
  alertmanager:
    image: prom/prometheus:latest
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml
    ports:
      - "9093:9093"
    restart: always
EOF

$ cat > alertmanager.yml << 'EOF'
global:
  resolve_timeout: 5m

route:
  group_by: ['alertname']
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 1h
  receiver: 'email'

receivers:
- name: 'email'
  email_configs:
  - to: 'alerts@example.com'
    from: 'prometheus@example.com'
    smarthost: 'smtp.example.com:587'
    auth_username: 'prometheus'
    auth_password: 'password'
    require_tls: true

inhibit_rules:
  - source_match:
      severity: 'critical'
    target_match:
      severity: 'warning'
    equal: ['alertname', 'dev', 'instance']
EOF

# 启动告警服务
$ docker-compose up -d

Creating network "alerting_default" with the default driver
Creating alerting_alertmanager_1 ... done

# 配置Prometheus与Alertmanager集成
$ cat > prometheus.yml << 'EOF'
global:
  scrape_interval: 15s

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

rule_files:
  - "alert.rules.yml"

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
    - targets: ['localhost:9090']
  - job_name: 'cadvisor'
    static_configs:
    - targets: ['cadvisor:8080']
EOF

$ docker run \
    --name prometheus \
    --network alerting_default \
    -v $(pwd)/prometheus.yml:/etc/prometheus/prometheus.yml \
    -v $(pwd)/alert.rules.yml:/etc/prometheus/alert.rules.yml \
    -p 9090:9090 \
    -d \
    prom/prometheus:latest