服务器指标监控

#!/bin/bash
# ============================================================
# Node Exporter 安装脚本 - 适用于 Debian 13 / Ubuntu
# 版本：v1.9.1
# 作者：胖哥
# 站点：https://digvps.com/
# ============================================================

set -e

VERSION="1.10.2"
ARCH="linux-amd64"
DOWNLOAD_URL="https://github.com/prometheus/node_exporter/releases/download/v${VERSION}/node_exporter-${VERSION}.${ARCH}.tar.gz"

echo "📦 下载 Node Exporter v${VERSION} ..."
wget -q ${DOWNLOAD_URL} -O /tmp/node_exporter.tar.gz

echo "📂 解压文件 ..."
tar -xzf /tmp/node_exporter.tar.gz -C /tmp
cd /tmp/node_exporter-${VERSION}.${ARCH}

echo "🚀 安装二进制到 /usr/local/bin ..."
cp node_exporter /usr/local/bin/
chmod +x /usr/local/bin/node_exporter

echo "👤 创建 nodeusr 用户（如不存在）..."
if ! id "nodeusr" &>/dev/null; then
  useradd --no-create-home --shell /usr/sbin/nologin nodeusr
fi

echo "🧾 创建 systemd 服务文件 ..."
cat >/etc/systemd/system/node_exporter.service <<'EOF'
[Unit]
Description=Prometheus Node Exporter
Documentation=https://github.com/prometheus/node_exporter
After=network-online.target

[Service]
User=nodeusr
Group=nodeusr
Type=simple
ExecStart=/usr/local/bin/node_exporter \
  --web.listen-address=":9100" 

Restart=on-failure

[Install]
WantedBy=multi-user.target
EOF

echo "🔄 重新加载 systemd 守护进程 ..."
systemctl daemon-reload

echo "▶️ 启动 Node Exporter 服务 ..."
systemctl enable --now node_exporter

echo "✅ Node Exporter 安装完成！"
echo "------------------------------------------------------------"
echo "访问地址: http://<服务器IP>:9100/metrics"
echo "服务状态: systemctl status node_exporter"
echo "日志查看: journalctl -u node_exporter -f"
echo "------------------------------------------------------------"

groups:
  - name: node_down
    rules:
      - alert: NodeDown
        expr: up{job="node-exporter"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "💀 节点 {{ $labels.instance }} 离线"
          description: "Exporter 无法连接（可能服务器宕机或网络故障）"

groups:
  - name: node_cpu
    rules:
      - alert: HighCPUUsage
        expr: 100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 90
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: "🔥 CPU 使用率过高 ({{ $labels.instance }})"
          description: "当前 CPU 使用率超过 90%"

groups:
  - name: node_memory
    rules:
      - alert: HighMemoryUsage
        expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 90
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: "💾 内存使用率过高 ({{ $labels.instance }})"
          description: "当前内存使用率已超过 90%"

groups:
  - name: node_memory
    rules:
      - alert: HighMemoryUsage
        expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 90
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: "💾 内存使用率过高 ({{ $labels.instance }})"
          description: "当前内存使用率已超过 90%"

groups:
  - name: node_disk
    rules:
      # 1) 磁盘使用率过高（Warning / Critical）
      - alert: DiskUsageHigh
        expr: |
          100 * (1 - node_filesystem_avail_bytes{fstype!~"tmpfs|overlay|squashfs|devtmpfs|nsfs|tracefs|cgroup2.*|autofs|proc|sysfs|bpf|ramfs"}
                     / node_filesystem_size_bytes{fstype!~"tmpfs|overlay|squashfs|devtmpfs|nsfs|tracefs|cgroup2.*|autofs|proc|sysfs|bpf|ramfs"}) > 90
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "📦 磁盘使用率过高 ({{ $labels.instance }} {{ $labels.mountpoint }})"
          description: "磁盘使用率 > 90% 持续 5 分钟；当前值={{ $value | printf \"%.1f\" }}%"

      - alert: DiskUsageHigh
        expr: |
          100 * (1 - node_filesystem_avail_bytes{fstype!~"tmpfs|overlay|squashfs|devtmpfs|nsfs|tracefs|cgroup2.*|autofs|proc|sysfs|bpf|ramfs"}
                     / node_filesystem_size_bytes{fstype!~"tmpfs|overlay|squashfs|devtmpfs|nsfs|tracefs|cgroup2.*|autofs|proc|sysfs|bpf|ramfs"}) > 80
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "📦 磁盘使用率偏高 ({{ $labels.instance }} {{ $labels.mountpoint }})"
          description: "磁盘使用率 > 80% 持续 10 分钟；当前值={{ $value | printf \"%.1f\" }}%"

      # 2) inode 使用率过高（防止“有空间但没 inode”）
      - alert: InodeUsageHigh
        expr: |
          100 * (1 - node_filesystem_files_free{fstype!~"tmpfs|overlay|squashfs|devtmpfs|nsfs|tracefs|cgroup2.*|autofs|proc|sysfs|bpf|ramfs"}
                     / node_filesystem_files{fstype!~"tmpfs|overlay|squashfs|devtmpfs|nsfs|tracefs|cgroup2.*|autofs|proc|sysfs|bpf|ramfs"}) > 80
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "📁 inode 使用率偏高 ({{ $labels.instance }} {{ $labels.mountpoint }})"
          description: "inode 使用率 > 80% 持续 10 分钟；当前值={{ $value | printf \"%.1f\" }}%"

global:
  resolve_timeout: 5m

  # 邮件全局配置
  smtp_smarthost: 'smtp.gmail.com:587'
  smtp_from: 'alert@example.com'
  smtp_auth_username: 'alert@example.com'
  smtp_auth_password: 'your_password_here'

route:
  # 根路由定义
  receiver: 'telegram'                 # 👈 默认分发到 all 这个 receiver
  group_by: ['alertname']         # 按告警名分组
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 1h

  # 这里可以做条件分发（示例）
  # routes:
  #   - match:
  #       severity: critical
  #     receiver: 'telegram'
  #   - match:
  #       severity: warning
  #     receiver: 'email'

receivers:
  # 🔔 同时发送邮件 + Telegram 的复合接收器
  - name: 'all'
    email_configs:
      - to: 'admin@example.com'
        send_resolved: true
    telegram_configs:
      - bot_token: '123456789:ABCDEF_xxxxx'
        chat_id: -1001234567890
        parse_mode: 'HTML'
        send_resolved: true
        message: |-
          🚨 <b>{{ .Status | toUpper }}</b> - {{ .CommonLabels.alertname }}
          主机: {{ .CommonLabels.instance }}
          严重性: {{ .CommonLabels.severity }}
          详情: {{ .CommonAnnotations.summary }}
          描述: {{ .CommonAnnotations.description }}
          <i>触发时间: {{ .StartsAt }}</i>

  # 你也可以定义单独渠道备用
  - name: 'email'
    email_configs:
      - to: 'ops@example.com'
        send_resolved: true

  - name: 'telegram'
    telegram_configs:
      - bot_token: '123456789:ABCDEF_xxxxx'
        chat_id: -1001234567890
        parse_mode: 'Markdown'
        send_resolved: true
        message: |-
          🚨 *{{ .Status | toUpper }}* - {{ .CommonLabels.alertname }}

          主机: {{ .CommonLabels.instance }}
          严重性: {{ .CommonLabels.severity }}
          详情: {{ .CommonAnnotations.summary }}
          描述: {{ .CommonAnnotations.description }}

          触发时间: {{ .StartsAt }}

services:
  dashboard:
    image: ghcr.io/nezhahq/nezha
    container_name: nezha-dashboard
    restart: always
    volumes:
      - ./data:/dashboard/data
    ports:
      - 8008:8008

debug: false
realipheader: ""
language: zh_CN
sitename: DigVPS.COM
jwtsecretkey: 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
agentsecretkey: WYGjFRqQPhcBCfmfPoXMjXUNIanxceKw
listenport: 8008
listenhost: ""
installhost: DigVPS.COM #客户端需要连接的服务器域名或者IP，请改为你自己的。
tls: true
location: Asia/Shanghai
enableplainipinnotification: false
enableipchangenotification: false
ipchangenotificationgroupid: 0
cover: 1
ignoredipnotification: ""
ignoredipnotificationserverids: {}
avgpingcount: 2
dnsservers: ""
customcode: ""
customcodedashboard: ""