# 使用变量管理版本号，便于升级
VERSION="2.53.3"
# 下载 Prometheus 二进制压缩包
wget https://github.com/prometheus/prometheus/releases/download/v${VERSION}/prometheus-${VERSION}.linux-amd64.tar.gz
# 解压
tar zxf prometheus-${VERSION}.linux-amd64.tar.gz
# 创建统一存放目录 /opt/prometheus/ 之后回存放安装 Prometheus、Alertmanager、Grafana、node_exporter
mkdir -p /opt/prometheus/
# 重命名
mv prometheus-${VERSION}.linux-amd64 /opt/prometheus/prometheus
# 创建专门的prometheus用户  禁止登录系统
useradd -M -s /usr/sbin/nologin prometheus
# 新增数据目录创建与授权
mkdir -p /opt/prometheus/prometheus/data
chown -R prometheus:prometheus /opt/prometheus/

# 1
id prometheus
uid=1003(prometheus) gid=1003(prometheus) þ=1003(prometheus)
# 2
cat /etc/passwd | grep prometheus
prometheus:x:1003:1003::/home/prometheus:/usr/sbin/nologin

cat > /etc/systemd/system/prometheus.service << 'EOF'
[Unit]
Description=Prometheus Server
Documentation=https://prometheus.io/docs/introduction/overview/
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=prometheus
Group=prometheus
Restart=on-failure
ExecStart=/opt/prometheus/prometheus/prometheus \
  --config.file=/opt/prometheus/prometheus/prometheus.yml \
  --storage.tsdb.path=/opt/prometheus/prometheus/data \
  --storage.tsdb.retention.time=60d \
  --web.enable-lifecycle \
  --web.listen-address=0.0.0.0:9090
LimitNOFILE=65536
StandardOutput=journal
StandardError=journal

[Install]
WantedBy=multi-user.target
EOF
# 确保权限 再次授权
chown -R prometheus:prometheus /opt/prometheus/

# 应用所有配置后执行
systemctl daemon-reload
# 将服务设置为在系统启动时自动启动, --now: 立即启动该服务
systemctl enable --now prometheus
# 查看状态
systemctl status prometheus
# 验证服务端口
ss -tunlp | grep 9090
# 使用 journalctl 查看 Prometheus 服务的详细日志，以获取更多的错误信息
journalctl -u prometheus.service
# 或者查看最近的日志
journalctl -u prometheus.service --since "5 minutes ago"
# 重启prometheus
systemctl restart prometheus

# 使用变量管理版本
VERSION="0.28.1"
# 下载
wget https://github.com/prometheus/alertmanager/releases/download/v${VERSION}/alertmanager-${VERSION}.linux-amd64.tar.gz
# 解压
tar zxf alertmanager-${VERSION}.linux-amd64.tar.gz
# 重命名
mv alertmanager-${VERSION}.linux-amd64 /opt/prometheus/alertmanager
# 创建数据目录并授权
mkdir -p /opt/prometheus/alertmanager/data
chown -R prometheus:prometheus /opt/prometheus/

cat > /etc/systemd/system/alertmanager.service << 'EOF'
[Unit]
Description=Alert Manager
Documentation=https://prometheus.io/docs/alerting/latest/alertmanager/
Wants=network-online.target
After=network-online.target

[Service]
Type=simple
User=prometheus
Group=prometheus
ExecStart=/opt/prometheus/alertmanager/alertmanager \
  --config.file=/opt/prometheus/alertmanager/alertmanager.yml \
  --storage.path=/opt/prometheus/alertmanager/data \
  --web.listen-address=0.0.0.0:9093
Restart=always
LimitNOFILE=65536
StandardOutput=journal
StandardError=journal

[Install]
WantedBy=multi-user.target
EOF

# 重载服务配置
systemctl daemon-reload

# 启动服务
systemctl enable --now alertmanager

# 验证端口
ss -tunlp | grep 9093

# 查看日志
journalctl -u alertmanager -f --since "2 minutes ago"

# Web控制台访问
http://<SERVER_IP>:9093

cat > /opt/prometheus/prometheus/alert.yml << 'EOF'
groups:
- name: Prometheus alert
  rules:
  - alert: 服务告警
    expr: up{job!="alertmanager"} == 0  # 排除自身监控
    for: 3m                             # 延长检测时间避免抖动
    labels:
      severity: critical
      region: "{{ $labels.instance }}"
    annotations:
      summary: "服务实例 {{ $labels.instance }} 故障"
      description: "{{ $labels.job }} 在 {{ $labels.instance }} 已宕机超过3分钟"
EOF

# 进入安装目录
cd /opt/prometheus/prometheus

# 使用 promtool 检查配置（需确认工具存在）
./promtool check config prometheus.yml

# 预期输出：
Checking prometheus.yml
  SUCCESS: 1 rule files found
 SUCCESS: prometheus.yml is valid prometheus config file syntax

Checking alert.yml
  SUCCESS: 1 rules found

# 方法1：通过API热加载（需启动时启用 --web.enable-lifecycle）
curl -X POST http://localhost:9090/-/reload

# 方法2：通过systemd重启（保证配置持久化）
systemctl restart prometheus

# 验证规则加载
curl http://localhost:9090/api/v1/rules | jq .

# 使用变量管理版本
VERSION="11.5.2"
wget https://dl.grafana.com/enterprise/release/grafana-enterprise-${VERSION}.linux-amd64.tar.gz
tar -zxvf grafana-enterprise-${VERSION}.linux-amd64.tar.gz
mv grafana-${VERSION} /opt/prometheus/grafana

# 创建必要目录并授权
mkdir -p /opt/prometheus/grafana/{data,logs}
chown -R prometheus:prometheus /opt/prometheus/

cat > /etc/systemd/system/grafana.service << 'EOF'
[Unit]
Description=Grafana Server
Documentation=https://grafana.com/docs/
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=prometheus
Group=prometheus
Environment="GF_PATHS_HOME=/opt/prometheus/grafana"
Environment="GF_PATHS_CONFIG=/opt/prometheus/grafana/conf"
Environment="GF_PATHS_DATA=/opt/prometheus/grafana/data"
Environment="GF_PATHS_LOGS=/opt/prometheus/grafana/logs"
ExecStart=/opt/prometheus/grafana/bin/grafana-server \
  --config=/opt/prometheus/grafana/conf/defaults.ini \
  --homepath=/opt/prometheus/grafana
LimitNOFILE=65536
Restart=on-failure
StandardOutput=journal
StandardError=journal

[Install]
WantedBy=multi-user.target
EOF

# 应用配置
systemctl daemon-reload
systemctl enable --now grafana
systemctl status grafana

# 验证端口
ss -tunlp | grep 3000

# 查看日志
journalctl -u grafana -f --since "2 minutes ago"

# 初始访问
echo "访问地址：http://$(hostname -I | awk '{print $1}'):3000"
echo "初始账号：admin/admin（首次登录需修改）"

# 使用变量管理版本
VERSION="1.9.0"
wget https://github.com/prometheus/node_exporter/releases/download/v${VERSION}/node_exporter-${VERSION}.linux-amd64.tar.gz
tar zxf node_exporter-${VERSION}.linux-amd64.tar.gz
[ -d /opt/prometheus/ ] || mkdir -p /opt/prometheus/
mv node_exporter-${VERSION}.linux-amd64 /opt/prometheus/node_exporter

# 同Prometheus机器一台或者已经有prometheus用户忽略此操作
# 创建专门的prometheus用户  禁止登录系统
cat /etc/passwd | grep -q prometheus || useradd -M -s /usr/sbin/nologin prometheus

# 创建数据目录并授权
mkdir -p /opt/prometheus/node_exporter/data
chown -R prometheus:prometheus /opt/prometheus/

cat > /etc/systemd/system/node_exporter.service << 'EOF'
[Unit]
Description=Node Exporter
Documentation=https://prometheus.io/docs/guides/node-exporter/
After=network.target

[Service]
User=prometheus
Group=prometheus
ExecStart=/opt/prometheus/node_exporter/node_exporter \
  --web.listen-address=0.0.0.0:9100 \
  --collector.systemd \
  --collector.systemd.unit-whitelist="(ssh|docker|prometheus).service"
Restart=on-failure
RestartSec=30s
LimitNOFILE=65536
StandardOutput=journal
StandardError=journal

[Install]
WantedBy=multi-user.target
EOF

# 应用配置
systemctl daemon-reload
systemctl enable --now node_exporter
systemctl status node_exporter
# 验证端口
ss -tunlp | grep 9100

# 指标采集测试
curl -s http://localhost:9100/metrics | grep 'node_'

# 查看日志
journalctl -u node_exporter -f --since "2 minutes ago"

curl -X POST http://localhost:9090/-/reload

# 定义版本变量
VERSION="1.9.0"

# 下载并解压（注意：CentOS 6默认无wget需安装）
yum install -y wget
wget https://github.com/prometheus/node_exporter/releases/download/v${VERSION}/node_exporter-${VERSION}.linux-amd64.tar.gz
tar zxf node_exporter-${VERSION}.linux-amd64.tar.gz

# 移动二进制文件到标准路径（修正原文档路径错误）
mv node_exporter-${VERSION}.linux-amd64/node_exporter /usr/local/bin/

# 创建专用系统用户
useradd --no-create-home --shell /sbin/nologin node_exporter

# 设置二进制文件权限
chown node_exporter:node_exporter /usr/local/bin/node_exporter
chmod 755 /usr/local/bin/node_exporter

#!/bin/bash
### BEGIN INIT INFO
# 提供的服务:        node_exporter
# 需要启动的服务:     $network $syslog - 确保在网络和日志服务启动后再启动 node_exporter
# 需要停止的服务:     $network $syslog - 在停止 node_exporter 前确保网络和日志服务已停止
# 默认启动级别:       2 3 4 5 - 多用户模式和图形界面模式下自动启动
# 默认停止级别:       0 1 6 - 关机、单用户模式和重启时自动停止
# 简短描述:          Prometheus Node Exporter - 监控系统硬件和操作系统指标的 Prometheus 导出器
# 注意:             防火墙要对Prometheus服务器开放9100端口
### END INIT INFO

RETVAL=0
PROG="node_exporter"
EXEC="/usr/local/bin/node_exporter"
LOCKFILE="/var/lock/subsys/$PROG"
LOGFILE="/var/log/node_exporter.log"
OPTIONS="--web.listen-address=:9100"

# 确保锁文件目录存在
[ -d /var/lock/subsys ] || mkdir -p /var/lock/subsys

# 加载系统初始化函数库
if [ -f /etc/rc.d/init.d/functions ]; then
    . /etc/rc.d/init.d/functions
else
    echo "错误: /etc/rc.d/init.d/functions 文件不存在"
    exit 1
fi

start() {
    if [ -f $LOCKFILE ]; then
        echo "$PROG 已经在运行!"
        return 1
    fi

    echo -n $"正在启动 $PROG: "
    
    # 安全启动方案：通过 sudo 切换用户并重定向日志
    sudo -u node_exporter nohup $EXEC $OPTIONS >> $LOGFILE 2>&1 &
    RETVAL=$?
    
    [ $RETVAL -eq 0 ] && touch $LOCKFILE && success || failure
    echo
    return $RETVAL
}

stop() {
    echo -n $"正在停止 $PROG: "
    killproc $EXEC
    RETVAL=$?
    [ $RETVAL -eq 0 ] && rm -f $LOCKFILE && success || failure
    echo
    return $RETVAL
}

restart() {
    stop
    sleep 2
    start
}

case "$1" in
    start)  start ;;
    stop)   stop ;;
    restart) restart ;;
    status) status $PROG ;;
    *)      echo "用法: $0 {start|stop|restart|status}"; exit 1 ;;
esac

exit $RETVAL

# 设置执行权限
chmod +x /etc/init.d/node_exporter

# 创建日志文件并授权
touch /var/log/node_exporter.log
chown node_exporter:node_exporter /var/log/node_exporter.log

# 配置开机启动
chkconfig --add node_exporter
chkconfig node_exporter on

# 启动服务
service node_exporter start

# 验证服务状态
service node_exporter status

# 检查端口监听
netstat -tlnp | grep 9100

# 查看日志
tail -f /var/log/node_exporter.log

# 测试指标采集
curl -s http://127.0.0.1:9100/metrics | head -n 5

# 克隆仓库
cd /opt/ && git clone https://gitee.com/jerrryWang/prometheus.git

# 创建专用系统用户
useradd -M -s /usr/sbin/nologin prometheus

# 创建数据目录结构
mkdir -p /opt/prometheus/{prometheus/data,alertmanager/data,grafana/{data,logs},node_exporter/data}

# 设置目录权限
chown -R prometheus:prometheus /opt/prometheus

# 复制systemd服务文件
cp /opt/prometheus/*.service /etc/systemd/system/

# 重载服务配置
systemctl daemon-reload

# 启动所有服务
systemctl enable --now {prometheus,alertmanager,grafana,node_exporter}

# 验证服务状态
ss -tunlp | grep -E "9090|9093|3000|9100"

# 查看服务状态
systemctl status prometheus alertmanager grafana node_exporter

# 热重载配置（Prometheus）
curl -X POST http://localhost:9090/-/reload