prometheus 安装

wget https://github.com/prometheus/prometheus/releases/download/v2.45.2/prometheus-2.45.2.linux-amd64.tar.gz
tar -zxvf prometheus-2.45.2.linux-amd64.tar.gz /opt/
#创建一个用户
useradd -M -s /usr/sbin/nologin promethues
root@promethues203:~# useradd -M -s /usr/sbin/nologin prometheus
root@promethues203:~# id prometheus
uid=1000(promethues) gid=1000(promethues) groups=1000(prometheus)
root@promethues203:~# 
#授权
root@promethues203:~# chown prometheus:prometheus -R /opt/prometheus-2.45.2.linux-amd64/

#创建prometheus.service服务

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

[Service]
Type=simple
User=prometheus
Group=prometheus
Restart=on-failure
ExecStart=/opt/prometheus-2.45.2.linux-amd64/prometheus \
  --config.file=/opt/prometheus-2.45.2.linux-amd64/prometheus.yml \
  --storage.tsdb.path=/opt/prometheus-2.45.2.linux-amd64/data \
  --storage.tsdb.retention.time=60d \
  --web.enable-lifecycle

[Install]
WantedBy=multi-user.target
EOF
``` 

systemctl start prometheus 
#页面显示正常
prometheus：http://10.121.1.203:9090/graph
监控指标：http://10.121.1.203:9090/metrics

安装监控alertmanager
wget https://github.com/prometheus/alertmanager/releases/download/v0.26.0/alertmanager-0.26.0.linux-amd64.tar.gz
tar -zxvf alertmanager-0.26.0.linux-amd64.tar.gz -C /opt
chown prometheus.prometheus -R /opt/alertmanager-0.26.0.linux-amd64

#创建prometheus.service服务

``` 
cat >> /etc/systemd/system/alertmanager.service << "EOF"
[Unit]
Description=Alertmanager
After=network-online.target
After=network-online.target

[Service]
Type=simple
User=prometheus
Group=prometheus
ExecStart=/opt/alertmanager-0.26.0.linux-amd64/alertmanager \
  --config.file=/opt/alertmanager-0.26.0.linux-amd64/alertmanager.yml \
  --storage.path=/opt/alertmanager-0.26.0.linux-amd64/data 

Restart=always
[Install]
WantedBy=multi-user.target
EOF
``` 

启动服务
systemctl start alertmanager

http://10.121.1.203:9093/

修改配置，把alertmanager 告警加入到prmetheus中
/opt/prometheus-2.45.2.linux-amd64/prometheus.yml
```
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          # - alertmanager:9093
          #增加altermanager的地址
           - 10.121.1.203:9093
           
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"
  #增加警告文件名
   - "alert.yml"

```

增加触发器配置文件
```
cat > /opt/prometheus-2.45.2.linux-amd64/alert.yml <<"EOF"
groups:
- name: prometheus alert
  rules:
  #对任何实例操过30s无法联系的情况发出警告
  - alert: 服务告警
    expr: up == 0
    for: 30s
    labels:
      severity: critical
    annotations:
      instance: "{{ $labels.instance }}"
      description: "{{ $labels.job }} 服务关闭"
EOF
```

检查是否有问题
``` 
root@promethues203:/opt/prometheus-2.45.2.linux-amd64# ./promtool check config prometheus.yml 
Checking prometheus.yml
  SUCCESS: 1 rule files found
 SUCCESS: prometheus.yml is valid prometheus config file syntax

Checking alert.yml
  SUCCESS: 1 rules found

root@promethues203:/opt/prometheus-2.45.2.linux-amd64# 
```

重启prometheus 热加载
``` 
systemctl restart prometheus
#重载
curl -X POST http://localhost:9090/-/reload
```

安装grafana
https://grafana.com/grafana/download

``` 
wget https://dl.grafana.com/enterprise/release/grafana-enterprise-10.2.3.linux-amd64.tar.gz
tar -zxvf grafana-enterprise-10.2.3.linux-amd64.tar.gz -C /opt/
chown prometheus:prometheus -R /opt/grafana-v10.2.3/
```
创建服务
```
cat >> /etc/systemd/system/grafana-server.service << "EOF"
[Unit]
Description=Grafana server
Documentation=http://docs.grafana.org

[Service]
Type=simple
User=prometheus
Group=prometheus
Restart=on-failure
ExecStart=/opt/grafana-v10.2.3/bin/grafana-server \
  --config=/opt/grafana-v10.2.3/conf/defaults.ini \
  --homepath=/opt/grafana-v10.2.3 

[Install]
WantedBy=multi-user.target
EOF
```

systemctl start grafana-server
http://10.121.1.203:3000/login  admin/admin

安装node_exporter

```
wget https://github.com/prometheus/node_exporter/releases/download/v1.7.0/node_exporter-1.7.0.linux-amd64.tar.gz
tar -zxvf node_exporter-1.7.0.linux-amd64.tar.gz -C /opt/
```

chown prometheus:prometheus -R /opt/node_exporter-1.7.0.linux-amd64

node_exporter 服务

``` 
cat >> /etc/systemd/system/node_exporter.service << "EOF"
[Unit]
Description=node_exporter
Documentation=http://prometheus.io
After=network.target

[Service]
Type=simple
User=prometheus
Group=prometheus
ExecStart=/opt/node_exporter-1.7.0.linux-amd64/node_exporter
Restart=on-failure
[Install]
WantedBy=multi-user.target
EOF
```
systemctl daemon-reload
systemctl restart node_exporter
http://10.121.1.203:9100/metrics

修改prometheus 添加node_exporter

node_exporter 
```
cat >> /opt/prometheus-2.45.2.linux-amd64/prometheus.yml <<"EOF"
   # node-exporter配置
  - job_name: "node_exporter"
    scrape_interval: 15s
    static_configs:
      - targets: ["10.121.1.203:9100"]
        labels:
          instance: Prometheus server
EOF
```
重启下prometheus
curl -X POST http://10.121.1.203:9090/-/reload

grafana 添加数据源

```Home>Connections>Data sources>prometheus 添加prometheus
```

添加node_exporter dashboard 模板
下载模板地址 ： https://grafana.com/grafana/dashboards/1860-node-exporter-full
10.121.1.203:3000

导入路径 Home 》Dashboards 》Import dashboard