服务器监控工具推荐

# 下载并解压 Node Exporter 1.8.2
wget https://github.com/prometheus/node_exporter/releases/download/v1.8.2/node_exporter-1.8.2.linux-amd64.tar.gz
tar xf node_exporter-1.8.2.linux-amd64.tar.gz
sudo mv node_exporter-1.8.2.linux-amd64/node_exporter /usr/local/bin/

# 创建 systemd 服务
sudo tee /etc/systemd/system/node_exporter.service > /dev/null <<'EOF'
[Unit]
Description=Prometheus Node Exporter
After=network.target

[Service]
User=nobody
ExecStart=/usr/local/bin/node_exporter \
  --web.listen-address=:9100 \
  --collector.systemd \
  --collector.processes \
  --no-collector.wifi
Restart=on-failure

[Install]
WantedBy=multi-user.target
EOF

sudo systemctl daemon-reload
sudo systemctl enable --now node_exporter
curl -s localhost:9100/metrics | grep node_load1

wget https://github.com/prometheus/prometheus/releases/download/v2.54.1/prometheus-2.54.1.linux-amd64.tar.gz
tar xf prometheus-2.54.1.linux-amd64.tar.gz
sudo mv prometheus-2.54.1.linux-amd64 /opt/prometheus

sudo tee /opt/prometheus/prometheus.yml > /dev/null <<'EOF'
global:
  scrape_interval: 15s
  evaluation_interval: 15s

alerting:
  alertmanagers:
    - static_configs:
        - targets: ['localhost:9093']

rule_files:
  - /opt/prometheus/rules/*.yml

scrape_configs:
  - job_name: 'node'
    static_configs:
      - targets:
          - '10.0.0.11:9100'
          - '10.0.0.12:9100'
        labels:
          env: production
EOF

sudo tee /etc/systemd/system/prometheus.service > /dev/null <<'EOF'
[Unit]
Description=Prometheus Server
After=network.target
[Service]
ExecStart=/opt/prometheus/prometheus \
  --config.file=/opt/prometheus/prometheus.yml \
  --storage.tsdb.path=/opt/prometheus/data \
  --storage.tsdb.retention.time=30d \
  --web.listen-address=:9090
Restart=on-failure
[Install]
WantedBy=multi-user.target
EOF

sudo systemctl daemon-reload && sudo systemctl enable --now prometheus

# /opt/prometheus/rules/node.yml
groups:
  - name: node-health
    rules:
      - alert: NodeDown
        expr: up == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "实例 {{ $labels.instance }} 已失联 1 分钟"

      - alert: HighCPUUsage
        expr: 100 - (avg by(instance)(rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "{{ $labels.instance }} CPU 使用率持续 5 分钟高于 85%"

      - alert: DiskWillFillIn4Hours
        expr: predict_linear(node_filesystem_free_bytes{fstype!~"tmpfs"}[6h], 4*3600) < 0
        for: 10m
        labels:
          severity: critical
        annotations:
          summary: "{{ $labels.mountpoint }} 按当前增速 4 小时内将写满"

sudo apt install -y grafana
sudo systemctl enable --now grafana-server
# 默认监听 :3000，初始账号 admin / admin，登录后立即改密码
# 添加数据源：http://localhost:9090，然后 Import 面板 ID 1860

# 官方一键脚本（推荐用 --stable-channel）
wget -O /tmp/netdata-kickstart.sh https://get.netdata.cloud/kickstart.sh
sh /tmp/netdata-kickstart.sh --stable-channel --disable-telemetry

sudo systemctl enable --now netdata
# 仅本机访问时改为监听回环，需要用 SSH 隧道访问
sudo sed -i 's/# bind to = \*/bind to = 127.0.0.1/' /etc/netdata/netdata.conf
sudo systemctl restart netdata
curl -s localhost:19999/api/v1/info | head -5

docker run -d --restart=always -p 3001:3001 \
  -v uptime-kuma:/app/data \
  --name uptime-kuma \
  louislam/uptime-kuma:1

# 或 docker compose
cat > docker-compose.yml <<'EOF'
services:
  uptime-kuma:
    image: louislam/uptime-kuma:1
    restart: always
    ports:
      - "3001:3001"
    volumes:
      - /opt/uptime-kuma/data:/app/data
      - /var/run/docker.sock:/var/run/docker.sock
EOF
docker compose up -d

# Rocky Linux 9 / RHEL 9，Zabbix 7.0
rpm -Uvh https://repo.zabbix.com/zabbix/7.0/rhel/9/x86_64/zabbix-release-latest.el9.noarch.rpm
dnf clean all
dnf install -y zabbix-server-mysql zabbix-web-mysql zabbix-nginx-conf zabbix-sql-scripts zabbix-agent2

# 建库（MySQL 8.4）
mysql -uroot -p -e "create database zabbix character set utf8mb4 collate utf8mb4_bin;
create user zabbix@localhost identified by '<你的密码>';
grant all privileges on zabbix.* to zabbix@localhost;"

zcat /usr/share/zabbix-sql-scripts/mysql/server.sql.gz | mysql -uzabbix -p zabbix
sed -i 's/^# DBPassword=/DBPassword=<你的密码>/' /etc/zabbix/zabbix_server.conf
systemctl enable --now zabbix-server zabbix-agent2 nginx php-fpm