Linux云计算SRE-第二十一周

构建单节点prometheus，部署node exporter和mongo exporter。构建kibana大盘。包含主机PU使用率，主机MEM使用率，主机网络包速度。mongo db大盘，包含节点在线状态，读操作延迟等

一、实验环境准备

节点信息：
node0 (10.0.0.100)：Prometheus、Grafana、node exporter
node1 (10.0.0.110)：node exporter
node2 (10.0.0.120)：MongoDB、mongo exporter

二、

#1. 安装 Prometheus 和 Grafana

bash 复制代码

操作步骤：
#在 node0 上安装 Prometheus（官方二进制包）
wget https://github.com/prometheus/prometheus/releases/download/v2.53.3/prometheus-2.53.3.linux-amd64.tar.gz
tar -xvf prometheus-2.53.3.linux-amd64.tar.gz
mv prometheus-2.53.3.linux-amd64 /opt/prometheus
ln -s /opt/prometheus/prometheus /usr/local/bin/
ln -s /opt/prometheus/promtool /usr/local/bin/
#浏览器访问:
http://10.0.0.100:9090/
#创建service服务文件
tee /etc/systemd/system/prometheus.service <<EOF
[Unit]
Description=Prometheus Server
Documentation=https://prometheus.io/docs/introduction/overview/
After=network.target

[Service]
Type=simple
User=root
Group=root
ExecStart=/opt/prometheus/prometheus \
  --config.file=/opt/prometheus/prometheus.yml \
  --storage.tsdb.path=/opt/prometheus/data
ExecReload=/bin/kill -HUP \$MAINPID
Restart=on-failure

[Install]
WantedBy=multi-user.target
EOF

#重新加载 systemd 管理器配置
systemctl daemon-reload
#启动并设置开机自启
systemctl start prometheus
systemctl enable prometheus


#安装 Grafana（官方仓库）
curl -fsSL https://apt.grafana.com/gpg.key | gpg --dearmor -o /usr/share/keyrings/grafana.gpg
echo "deb [signed-by=/usr/share/keyrings/grafana.gpg] https://apt.grafana.com stable main" | tee /etc/apt/sources.list.d/grafana.list
apt update && apt install -y grafana
systemctl enable --now grafana-server

#2. 安装 node exporter

脚本 `install_node_exporter.sh`：

bash 复制代码

#!/bin/bash

NODE_EXPORTER_VERSION=1.9.0

NODE_EXPORTER_FILE="node_exporter-${NODE_EXPORTER_VERSION}.linux-amd64.tar.gz"
NODE_EXPORTER_URL=https://github.com/prometheus/node_exporter/releases/download/v${NODE_EXPORTER_VERSION}/${NODE_EXPORTER_FILE}
INSTALL_DIR=/usr/local

HOST=`hostname -I|awk '{print $1}'`


. /etc/os-release

msg_error() {
  echo -e "\033[1;31m$1\033[0m"
}

msg_info() {
  echo -e "\033[1;32m$1\033[0m"
}

msg_warn() {
  echo -e "\033[1;33m$1\033[0m"
}


color () {
    RES_COL=60
    MOVE_TO_COL="echo -en \\033[${RES_COL}G"
    SETCOLOR_SUCCESS="echo -en \\033[1;32m"
    SETCOLOR_FAILURE="echo -en \\033[1;31m"
    SETCOLOR_WARNING="echo -en \\033[1;33m"
    SETCOLOR_NORMAL="echo -en \E[0m"
    echo -n "$1" && $MOVE_TO_COL
    echo -n "["
    if [ $2 = "success" -o $2 = "0" ] ;then
        ${SETCOLOR_SUCCESS}
        echo -n $"  OK  "    
    elif [ $2 = "failure" -o $2 = "1"  ] ;then 
        ${SETCOLOR_FAILURE}
        echo -n $"FAILED"
    else
        ${SETCOLOR_WARNING}
        echo -n $"WARNING"
    fi
    ${SETCOLOR_NORMAL}
    echo -n "]"
    echo 
}


install_node_exporter () {
    if [ ! -f  ${NODE_EXPORTER_FILE} ] ;then
        wget ${NODE_EXPORTER_URL} ||  { color "下载失败!" 1 ; exit ; }
    fi
    [ -d $INSTALL_DIR ] || mkdir -p $INSTALL_DIR
    tar xf ${NODE_EXPORTER_FILE} -C $INSTALL_DIR
    cd $INSTALL_DIR &&  ln -s node_exporter-${NODE_EXPORTER_VERSION}.linux-amd64 node_exporter
    mkdir -p $INSTALL_DIR/node_exporter/bin
    cd $INSTALL_DIR/node_exporter &&  mv node_exporter bin/ 
	id prometheus &> /dev/null || useradd -r -s /sbin/nologin prometheus
	chown -R prometheus.prometheus ${INSTALL_DIR}/node_exporter/
	
      
    cat >  /etc/profile.d/node_exporter.sh <<EOF
export NODE_EXPORTER_HOME=${INSTALL_DIR}/node_exporter
export PATH=\${NODE_EXPORTER_HOME}/bin:\$PATH
EOF

}


node_exporter_service () {
    cat > /lib/systemd/system/node_exporter.service <<EOF
[Unit]
Description=Prometheus Node Exporter
After=network.target

[Service]
Type=simple
ExecStart=$INSTALL_DIR/node_exporter/bin/node_exporter
ExecReload=/bin/kill -HUP \$MAINPID
Restart=on-failure
User=prometheus
Group=prometheus

[Install]
WantedBy=multi-user.target
EOF
    systemctl daemon-reload
    systemctl enable --now node_exporter.service
}


start_node_exporter() { 
    systemctl is-active node_exporter.service
    if [ $?  -eq 0 ];then  
        echo 
        color "node_exporter 安装完成!" 0
        echo "-------------------------------------------------------------------"
        echo -e "访问链接: \c"
        msg_info "http://$HOST:9100/metrics" 
    else
        color "node_exporter 安装失败!" 1
        exit
    fi 
}

install_node_exporter

node_exporter_service

start_node_exporter

部署命令：

bash 复制代码

#在 node0、node1、node2 上执行
bash install_node_exporter.sh
scp install_node_exporter.sh node1:/root
scp install_node_exporter.sh node2:/root
ssh node1 "bash install_node_exporter.sh"
ssh node2 "bash install_node_exporter.sh"

#3. 安装 MongoDB 和 mongo exporter

操作步骤：

bash 复制代码

#在 node2 上安装 MongoDB
curl -fsSL https://www.mongodb.org/static/pgp/server-8.0.asc | gpg -o /usr/share/keyrings/mongodb-server-8.0.gpg --dearmor
echo "deb [ arch=amd64 signed-by=/usr/share/keyrings/mongodb-server-8.0.gpg ] https://repo.mongodb.org/apt/ubuntu jammy/mongodb-org/8.0 multiverse" | tee /etc/apt/sources.list.d/mongodb-org-8.0.list
apt update && apt install -y mongodb-org
systemctl enable --now mongod
#配置 MongoDB 认证
mongosh admin --eval 'db.createUser({ user: "admin", pwd: "123456", roles: [ { role: "root", db: "admin" } ] })'
sed -i '/^security:/a\  authorization: enabled' /etc/mongod.conf
systemctl restart mongod
#安装 mongo exporter
wget https://github.com/percona/mongodb_exporter/releases/download/v0.43.1/mongodb_exporter-0.43.1.linux-amd64.tar.gz
tar -xvf mongodb_exporter-0.43.1.linux-amd64.tar.gz
mv mongodb_exporter-0.43.1.linux-amd64 /opt/mongodb_exporter
chown -R prometheus.prometheus /opt/mongodb_exporter
#创建服务文件
cat > /lib/systemd/system/mongodb_exporter.service <<EOF
[Unit]
Description=MongoDB Exporter
After=network.target

[Service]
Type=simple
ExecStart=/opt/mongodb_exporter/mongodb_exporter --mongodb.uri=admin:123456@localhost:27017
User=prometheus
Group=prometheus
Restart=on-failure

[Install]
WantedBy=multi-user.target
EOF

systemctl daemon-reload
systemctl enable --now mongodb_exporter.service

#4. 配置 Prometheus 抓取规则

bash 复制代码

#修改 Prometheus 配置文件
vim /opt/prometheus/prometheus.yml

scrape_configs:
  - job_name: 'node'
    static_configs:
      - targets: ['10.0.0.100:9100', '10.0.0.110:9100', '10.0.0.120:9100']
  - job_name: 'mongodb'
    static_configs:
      - targets: ['10.0.0.120:9216']
#检查配置文件语法
promtool check config /opt/prometheus/prometheus.yml
#重启 Prometheus
systemctl restart prometheus

#5. 配置 Grafana 仪表盘

http://10.0.0.100:3000 （默认账号/密码：admin/admin）（新密码123456）

添加 Prometheus 数据源：

名称：Prometheus
URL：`http://10.0.0.100:9090`

导入仪表盘：

Node Exporter 仪表盘（ID: 1860）：

导入 ID 1860，包含 CPU、内存、网络指标。

MongoDB 仪表盘（ID: 13387）：

导入 ID 13387，包含节点状态、读写延迟等指标。

自定义配置：

bash 复制代码

   - 网络包速度：
     rate(node_network_receive_bytes_total{device!~"lo|tun.*"}[5m])
     rate(node_network_transmit_bytes_total{device!~"lo|tun.*"}[5m])
     
   - MongoDB 读延迟：
     mongodb_cmd_duration_seconds_count{operation="find"}

三、验证与测试

Prometheus 验证：

curl http://10.0.0.100:9090/targets

应显示所有 exporter 状态为 `UP`。

Grafana 验证：

检查仪表盘数据是否正常显示。
确认 CPU、内存、网络、MongoDB 指标是否更新。
Node Exporter 仪表盘（ID 1860）显示 CPU、内存、网络指标。
MongoDB 仪表盘（ID 13387）显示节点状态、读写延迟等。