# 拉取镜像
docker pull jasonrivers/nagios:latest

# 运行容器
docker run -d \
    --name nagios \
    -p 8080:80 \
    -v /opt/nagios/config:/opt/nagios/etc \
    -v /opt/nagios/plugins:/opt/nagios/libexec/custom \
    -v /opt/nagios/var:/opt/nagios/var \
    -e NAGIOSADMIN_PASSWD=nagiosadmin \
    jasonrivers/nagios:latest

# 访问 Web 界面
# http://localhost:8080/nagios/
# 用户名: nagiosadmin
# 密码: nagiosadmin (可通过环境变量修改)

# docker-compose.yml
version: '3.8'

services:
  nagios:
    image: jasonrivers/nagios:latest
    container_name: nagios
    restart: unless-stopped
    ports:
      - "8080:80"
    environment:
      - NAGIOSADMIN_PASSWD=YourSecurePassword
      - [email protected]
    volumes:
      - ./config/nagios.cfg:/opt/nagios/etc/nagios.cfg
      - ./config/objects:/opt/nagios/etc/objects
      - ./config/conf.d:/opt/nagios/etc/conf.d
      - ./config/resource.cfg:/opt/nagios/etc/resource.cfg
      - ./plugins:/opt/nagios/libexec/custom
      - ./var/nagios:/opt/nagios/var
      - ./var/perfdata:/opt/nagios/var/perfdata
    networks:
      - monitoring
    healthcheck:
      test: ["CMD", "curl", "-f", "-u", "nagiosadmin:${NAGIOSADMIN_PASSWD}", "http://localhost/nagios/cgi-bin/status.cgi"]
      interval: 30s
      timeout: 10s
      retries: 3

  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    restart: unless-stopped
    ports:
      - "3000:3000"
    volumes:
      - grafana-data:/var/lib/grafana
    networks:
      - monitoring

  influxdb:
    image: influxdb:2.7
    container_name: influxdb
    restart: unless-stopped
    ports:
      - "8086:8086"
    volumes:
      - influxdb-data:/var/lib/influxdb2
    environment:
      - DOCKER_INFLUXDB_INIT_MODE=setup
      - DOCKER_INFLUXDB_INIT_USERNAME=admin
      - DOCKER_INFLUXDB_INIT_PASSWORD=YourInfluxPassword
      - DOCKER_INFLUXDB_INIT_ORG=monitoring
      - DOCKER_INFLUXDB_INIT_BUCKET=nagios
    networks:
      - monitoring

networks:
  monitoring:
    driver: bridge

volumes:
  grafana-data:
  influxdb-data:

# 启动服务
docker-compose up -d

# 查看日志
docker-compose logs -f nagios

# 停止服务
docker-compose down

# 重启服务
docker-compose restart nagios

# config/nagios.cfg 关键配置
log_file=/opt/nagios/var/nagios.log
object_cache_file=/opt/nagios/var/objects.cache
status_file=/opt/nagios/var/status.dat
command_file=/opt/nagios/var/rw/nagios.cmd
state_retention_file=/opt/nagios/var/retention.dat

cfg_dir=/opt/nagios/etc/objects/
cfg_dir=/opt/nagios/etc/conf.d/

# config/objects/commands.cfg
define command {
    command_name    check_nrpe
    command_line    $USER1$/check_nrpe -H $HOSTADDRESS$ -c $ARG1$ -a $ARG2$
}

define command {
    command_name    check_custom
    command_line    $USER2$/custom/$ARG1$ $ARG2$
}

# 方式一：使用外部命令
echo "[$(date +%s)] RESTART_NAGIOS" >> /opt/nagios/var/rw/nagios.cmd

# 方式二：Docker exec 重载
docker exec nagios /opt/nagios/bin/nagios -v /opt/nagios/etc/nagios.cfg
docker restart nagios

# 方式三：docker-compose 重载
docker-compose restart nagios

# 挂载插件目录
# docker-compose.yml
volumes:
  - ./plugins:/opt/nagios/libexec/custom

# 确保插件有执行权限
chmod +x ./plugins/*.sh
chmod +x ./plugins/*.py

# 在容器内测试插件
docker exec nagios /opt/nagios/libexec/custom/check_custom.sh -H localhost -w 80 -c 95

# Dockerfile.custom
FROM jasonrivers/nagios:latest

# 安装额外的依赖
RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip \
    fping \
    snmp \
    && rm -rf /var/lib/apt/lists/*

# 安装 Python 插件依赖
RUN pip3 install requests psutil

# 复制自定义插件
COPY plugins/ /opt/nagios/libexec/custom/
RUN chmod +x /opt/nagios/libexec/custom/*

# 复制自定义配置
COPY config/ /opt/nagios/etc/

# 设置权限
RUN chown -R nagios:nagios /opt/nagios/

EXPOSE 80
CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/supervisord.conf"]

# 构建自定义镜像
docker build -t my-nagios:latest -f Dockerfile.custom .

# 使用自定义镜像
docker-compose up -d

#!/bin/bash
# check_docker_container.sh - 检查 Docker 容器状态

STATE_OK=0
STATE_WARNING=1
STATE_CRITICAL=2
STATE_UNKNOWN=3

CONTAINER=$1
DOCKER_HOST=${2:-unix:///var/run/docker.sock}

# 获取容器状态
STATUS=$(curl -s --unix-socket /var/run/docker.sock "http://localhost/containers/${CONTAINER}/json" | python3 -c "
import sys, json
data = json.load(sys.stdin)
print(data['State']['Status'])
" 2>/dev/null)

if [ -z "$STATUS" ]; then
    echo "CRITICAL: Container '${CONTAINER}' not found"
    exit $STATE_CRITICAL
fi

if [ "$STATUS" = "running" ]; then
    # 检查健康状态
    HEALTH=$(curl -s --unix-socket /var/run/docker.sock "http://localhost/containers/${CONTAINER}/json" | python3 -c "
import sys, json
data = json.load(sys.stdin)
health = data['State'].get('Health', {})
print(health.get('Status', 'none'))
" 2>/dev/null)

    if [ "$HEALTH" = "unhealthy" ]; then
        echo "CRITICAL: Container '${CONTAINER}' is unhealthy"
        exit $STATE_CRITICAL
    fi

    echo "OK: Container '${CONTAINER}' is running | status=1"
    exit $STATE_OK
else
    echo "CRITICAL: Container '${CONTAINER}' is ${STATUS} | status=0"
    exit $STATE_CRITICAL
fi

#!/bin/bash
# check_docker_stats.sh - 检查容器资源使用

CONTAINER=$1
CPU_WARN=$2
CPU_CRIT=$3
MEM_WARN=$4
MEM_CRIT=$5

# 获取容器统计信息
STATS=$(docker stats --no-stream --format \
    "{{.CPUPerc}}\t{{.MemPerc}}\t{{.NetIO}}\t{{.BlockIO}}" \
    $CONTAINER 2>/dev/null)

if [ -z "$STATS" ]; then
    echo "CRITICAL: Unable to get stats for container '${CONTAINER}'"
    exit 2
fi

CPU=$(echo "$STATS" | awk '{print $1}' | tr -d '%')
MEM=$(echo "$STATS" | awk '{print $2}' | tr -d '%')
NET=$(echo "$STATS" | awk '{print $3}')
DISK=$(echo "$STATS" | awk '{print $4}')

# 阈值判断
if (( $(echo "$CPU > $CPU_CRIT" | bc -l) )) || (( $(echo "$MEM > $MEM_CRIT" | bc -l) )); then
    echo "CRITICAL: CPU=${CPU}%, MEM=${MEM}% | cpu=${CPU}%;${CPU_WARN};${CPU_CRIT} mem=${MEM}%;${MEM_WARN};${MEM_CRIT}"
    exit 2
elif (( $(echo "$CPU > $CPU_WARN" | bc -l) )) || (( $(echo "$MEM > $MEM_WARN" | bc -l) )); then
    echo "WARNING: CPU=${CPU}%, MEM=${MEM}% | cpu=${CPU}%;${CPU_WARN};${CPU_CRIT} mem=${MEM}%;${MEM_WARN};${MEM_CRIT}"
    exit 1
else
    echo "OK: CPU=${CPU}%, MEM=${MEM}% | cpu=${CPU}%;${CPU_WARN};${CPU_CRIT} mem=${MEM}%;${MEM_WARN};${MEM_CRIT}"
    exit 0
fi

# 命令定义
define command {
    command_name    check_docker_container
    command_line    $USER2$/check_docker_container.sh $ARG1$
}

define command {
    command_name    check_docker_stats
    command_line    $USER2$/check_docker_stats.sh $ARG1$ $ARG2$ $ARG3$ $ARG4$ $ARG5$
}

# 服务定义
define service {
    use                     generic-service
    host_name               docker-host-01
    service_description     Nagios Container
    check_command           check_docker_container!nagios
}

define service {
    use                     generic-service
    host_name               docker-host-01
    service_description     Nagios Container Resources
    check_command           check_docker_stats!nagios!80!95!80!95
}

define service {
    use                     generic-service
    host_name               docker-host-01
    service_description     Grafana Container
    check_command           check_docker_container!grafana
}