Prometheus + Grafana + AlertManger 相关整理

global:
  scrape_interval: 15s
  evaluation_interval: 15s 
alerting:
  alertmanagers:
  - static_configs:
    - targets:
       - localhost:9093
rule_files:
  - "/opt/prometheus_env/prometheus-2.34.0.linux-amd64/alarm_rules.yml"
scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']
        labels:
          instance: 'prometheus'
  - job_name: 'linux'
    static_configs:
      - targets: ['localhost:9100']
        labels:
          instance: 'localhost'
  - job_name: 'pushgateway'
    static_configs:
      - targets: ['localhost:9091']
        labels:
          instance: 'pushgateway'

groups:
- name: node
  rules:
  - alert: server_status
    expr: up{} == 0 
    for: 15s
    annotations:
      summary: "机器{{ $labels.instance }} 挂了"
      description: "请立即查看问题!"

global:
  resolve_timeout: 5m
  smtp_smarthost: 'smtp.exmail.qq.com:465' # 定义163邮箱服务器端
  smtp_from: '您的qq邮箱账号'  #来自哪个邮箱发的
  smtp_auth_username: '您的qq邮箱账号' 邮箱验证
  smtp_auth_password: '邮箱密码'   # 邮箱授权码，不是登录密码
  smtp_require_tls: false   # 是否启用tls
route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 3m  # 发送告警后间隔多久再次发送，减少发送邮件频率
  receiver: 'mail'    #发送的告警媒体
receivers:
- name: 'mail'        # 接收者配置，这里要与接收媒体一致
  email_configs: 
  - to: '接收人的qq邮箱' #发送给谁的邮箱，多个人多行列出
#inhibit_rules:
#  - source_match:
#      severity: 'critical'
#    target_match:
#      severity: 'warning'
#    equal: ['alertname', 'dev', 'instance']

cd /usr/lib/systemd/system

[Unit]
Description=Prometheus Push Gateway
After=network.target
[Service]
ExecStart=/opt/prometheus_env/pushgateway-1.4.2.linux-amd64/pushgateway
User=root
[Install]
WantedBy=multi-user.target

[Unit]
Description=Prometheus Node Exporter
After=network.target
[Service]
ExecStart=/opt/prometheus_env/node_exporter-1.3.1.linux-amd64/node_exporter
User=root
[Install]
WantedBy=multi-user.target

[Unit]
Description=Prometheus Service
After=network.target
[Service]
ExecStart=/opt/prometheus_env/prometheus-2.34.0.linux-amd64/prometheus \
--config.file=/opt/prometheus_env/prometheus-2.34.0.linux-amd64/prometheus.yml \
--web.read-timeout=5m  \
--web.max-connections=10 \
--storage.tsdb.retention=15d \
--storage.tsdb.path=/prometheus/data \
--query.max-concurrency=20 \
--query.timeout=2m
User=root
[Install]
WantedBy=multi-user.target

[Unit]
Description=Grafana
After=network.target
[Service]
ExecStart=/opt/prometheus_env/grafana-8.4.7/bin/grafana-server \
 --config=/opt/prometheus_env/grafana-8.4.7/conf/defaults.ini \
 --homepath=/opt/prometheus_env/grafana-8.4.7
[Install]
WantedBy=multi-user.target

[Unit]
Description=Prometheus alertmanager
After=network.target
[Service]
ExecStart=/opt/prometheus_env/alertmanager-0.24.0.linux-amd64/alertmanager \
--storage.path=/opt/prometheus_env/alertmanager-0.24.0.linux-amd64/data \
--config.file=/opt/prometheus_env/alertmanager-0.24.0.linux-amd64/alertmanager.yml
User=root
[Install]
WantedBy=multi-user.target

systemctl daemon-reload

systemctl start pushgateway
systemctl start node_exporter
systemctl start prometheus
systemctl start grafana
systemctl start alertmanager

systemctl enable pushgateway
systemctl enable node_exporter
systemctl enable prometheus
systemctl enable grafana
systemctl enable alertmanager

systemctl status pushgateway

firewall-cmd --zone=public --add-port=3000/tcp --permanent

firewall-cmd --reload

netstat -tunlp | grep 9090

ps -elf|grep promethues

for i in `seq 1 $(cat /proc/cpuinfo |grep "physical id" |wc -l)`; do dd if=/dev/zero of=/dev/null & done
## top命令去查询进程并杀掉 !