基于docker部署prometheus监控平台

docker pull prom/prometheus

mkdir -p /data/prometheus
mkdir /data/prometheus/data
chown 777 /data/prometheus/data
mkdir /data/prometheus/rules

chown 777 /data/prometheus/prometheus.yml

vim /data/prometheus/prometheus.yml

# my global config
global:
  scrape_interval:     15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
  - static_configs:
    - targets: [‘193.168.253.42:9093‘]
      # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global ‘evaluation_interval‘.
rule_files:
  - "node_down.yml"
  # - "first_rules.yml"
  # - "second_rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it‘s Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: ‘prometheus‘
    static_configs:
    - targets: [‘localhost:9090‘]- job_name: ‘node‘
    scrape_interval: 8s
    static_configs:
      - targets: [‘193.168.253.42:9100‘]

docker run  -d -p 9090:9090 -v /data/prometheus/data:/prometheus -v /data/prometheus:/etc/prometheus --name pro prom/prometheus

docker pull grafana/grafana

docker run -p -d  3000:3000 --name grafana grafana/grafana

tar xzf node_exporter-0.18.1.linux-amd64.tar.g 
mv node_exporter-0.18.1.linux-amd64 /data/node_exporter

cd /data/node_exporter
./node_exporter

[Unit]
Description=node_exporter
After=network.target 

[Service]
ExecStart=/data/node_exporter/node_exporter
Restart=on-failure

[Install]
WantedBy=multi-user.target

#  systemctl daemon-reload
#  systemctl enable node_exporter
#  systemctl start node_exporter
#  systemctl status node_exporter

docker pull prom/alertmanager

mkdir -p /data/alertmanager/storage
mkdir  /data/alertmanager/template
chown 777 /data/alertmanager/storage

global:
  smtp_smarthost: ‘smtp.qq.com:465‘       #smtp地址
  smtp_from: ‘258xxx9221@qq.com‘          #谁发邮件
  smtp_auth_username: ‘258xxx9221@qq.com‘ #邮箱用户
  smtp_auth_password: ‘xxxxxxx‘           #邮箱smtp授权码
  smtp_require_tls: false

templates:  #定义模板
  - ‘template/*.tmp1‘
route:
  group_by: [‘alertname‘] #分组名
  group_wait: 30s         #当收到警报，等待30秒看是否还有警报，如果有就一起发出去
  group_interval: 5m      # 发送警告间隔时间
  repeat_interval: 3h     # 重复报警的间隔时间
  receiver: mail          # 全局报警组，这个参数是必选的，和下面报警组名要相同

receivers:
- name: ‘mail‘            # 报警组名
  email_configs:
  - to: ‘{{ template "email.to" . }}‘ #发送给谁
    html: ‘{{ template "email.to.html" . }}‘
    send_resolved: true

#告警抑制
inhibit_rules:
  - source_match:
      severity: ‘critical‘
    target_match:
      severity: ‘warning‘
    equal: [‘alertname‘, ‘dev‘, ‘instance‘]

vim /data/alertmanager/template/email.tmpl

{{ define "email.from" }}11111111@qq.com{{ end }}
{{ define "email.to" }}22222222@qq.com{{ end }}
{{ define "email.to.html" }}
{{ range .Alerts }}
=========start==========<br>
告警程序: prometheus_alert <br>
告警级别: {{ .Labels.severity }} 级 <br>
告警类型: {{ .Labels.alertname }} <br>
故障主机: {{ .Labels.instance }} <br>
告警主题: {{ .Annotations.summary }} <br>
告警详情: {{ .Annotations.description }} <br>
触发时间: {{ .StartsAt.Format "2019-08-04 16:58:15" }} <br>
=========end==========<br>
{{ end }}
{{ end }}

docker run -d   -p 9093:9093   --name alertmanager   --restart=always   -v /data/alertmanager:/etc/alertmanager   -v /data/alertmanager/storage:/alertmanager   prom/alertmanager

cd /data/prometheus/rules

vim node_down.yml

groups:
- name: node-up
  rules:
  - alert: node-up
    expr: up{job="node-exporter"} == 0
    for: 15s
    labels:
      severity: 1
      team: node
    annotations:
      summary: "{{ $labels.instance }} 已停止运行!"
      description: "{{ $labels.instance }} 检测到异常停止！请重点关注！！！"

groups:
- name: example
  rules:
  - alert: NodeMemoryUsage
    expr: (1 - (node_memory_MemAvailable_bytes / (node_memory_MemTotal_bytes))) * 100 > 80
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "{{$labels.instance}}: High Memory usage detected"
      description: "{{$labels.instance}}: Memory usage is above 80% (current value is:{{ $value }})"

docker restart pro

expr: (1 - (node_memory_MemAvailable_bytes / (node_memory_MemTotal_bytes))) * 100 > 10

docker restart pro

docker logs -f alertmanager