TPNG(telegraf+prometheus+grafana+alertmanager)+容器方式部署总结

前言：

prometheus采集数据的的时间间隔建议:小于15s

prometheus检查规则的时间间隔建议:小于15s

实际生产环境中部署的为10s

telegraf采集数据的时间间隔根据采集机器数量决定

当采集交换机数量达到30台以上时建议设置为:110s

数据刷新时间间隔设置为：110s

grafana:设置默认采集prometheus数据时间设置为:10s

达到的效果完美监控linux主机+snmp实现监控交换机。

扩展：

可以在 inputs.snmp 里加入 fieldpass 来实现过滤。针对监控项（自动发现）可以加的过滤参数如下：

1. fieldpass 可以理为匹配该名称监控项才可采集

2. fielddrop  匹配该名称的监控项不进行采集

一. 安装TPNG

#安装 grafana

#!/bin/bash
 
start() {
cat <<EOF
    1.需要用到的命令wget apt-get tar
EOF
}
install_1() {
   install_grafana="grafana-8.5.2.linux-amd64.tar.gz"
   echo "1. 开始检测是否安装grafana"
   ss -ntulp |grep grafana 
if [ $? = 0 ]; then
   echo "绘图软件grafana已安装"
else 
   echo "开始安装grafana$"
   mkdir -p /opt/granfana
   wget https://dl.grafana.com/oss/release/${install_grafana}
   tar -xvzf ${install_grafana} -C /opt/granfana
   [ $? = 0 ] && echo "下载解压完成" || echo "下载解压失败"
fi
}
tuoguan() {
    echo "开始创建grafana托管文件"
    touch /etc/systemd/system/grafana.service
 
cat <<EOF >/etc/systemd/system/grafana.service
[Unit]
Description="grafana"
After=network.target
[Service]
Type=simple
ExecStart=/opt/granfana/grafana-8.5.2/bin/grafana-server web > /opt/granfana/grafana-8.5.2/bin/web.log 
WorkingDirectory=/opt/granfana/grafana-8.5.2/bin #执行文件目录
Restart=always
[Install]
WantedBy=multi-user.target
EOF
systemctl daemon-reload
systemctl enable  grafana
systemctl restart grafana
systemctl status  grafana
}
 
main () {
      start
      install_1
      tuoguan
}
main
 
 
# 安装 alertmanager

#!/bin/bash
 
start() {
cat <<EOF
    1.需要用到的命令wget apt-get tar
EOF
}
install_1() {
    ss -ntulp |grep alertmanager
    VERSION=alertmanager-0.24.0.linux-amd64.tar.gz
if [ $? = 0 ]; then
    echo "alertmanager 已安装"
else
    echo "开始安装 ${VERSION}"
    wget https://github.com/prometheus/alertmanager/releases/download/v0.24.0/${VERSION}
    tar -xvzf ${VERSION} -C /opt/alertmanager
    touch /etc/systemd/system/alertmanager.service
cat <<EOF >/etc/systemd/system/alertmanager.service
[Unit]
Description="alertmanager"
After=network.target
[Service]
ExecStart=/opt/alertmanger/alertmanager-0.24.0.linux-amd64/alertmanager --config.file=/opt/alertmanger/alertmanager-0.24.0.linux-amd64/alertmanager.yml --storage.path=/opt/alertmanger/alertmanager-0.24.0.linux-amd64/data --web.listen-address=:9093 --data.retention=120h
WorkingDirectory=/opt/alertmanger/alertmanager-0.24.0.linux-amd64
Restart=always
[Install]
WantedBy=multi-user.target
EOF
systemctl daemon-reload
systemctl enable  alertmanager
systemctl restart alertmanager
systemctl status  alertmanager
}
main() {
    start
    install_1
}
main
 
 
# 安装 prometheus

#!/bin/bash
# install prometheus
mkdir -p /opt/prometheus
wget https://s3-gz01.didistatic.com/n9e-pub/prome/prometheus-2.28.0.linux-amd64.tar.gz -O prometheus-2.28.0.linux-amd64.tar.gz
tar xf prometheus-2.28.0.linux-amd64.tar.gz
cp -far prometheus-2.28.0.linux-amd64/*  /opt/prometheus/
 
# service 
cat <<EOF >/etc/systemd/system/prometheus.service
[Unit]
Description="prometheus"
Documentation=https://prometheus.io/
After=network.target
[Service]
Type=simple
ExecStart=/opt/prometheus/prometheus  --config.file=/opt/prometheus/prometheus.yml --storage.tsdb.path=/opt/prometheus/data --web.enable-lifecycle --enable-feature=remote-write-receiver