global:
  # ResolveTimeout is the time after which an alert is declared resolved
  # if it has not been updated.
  resolve_timeout: 5m
  # The smarthost and SMTP sender used for mail notifications.
  smtp_smarthost: 'smtp.exmail.qq.com:25'
  smtp_from: 'yang.lei@belle.com.cn'
  smtp_auth_username: 'yang.lei@belle.com.cn'
  smtp_auth_password: 'xxx'
  smtp_require_tls: false

# The directory from which notification templates are read.
templates: 
- '/etc/alertmanager/template/*.tmpl'

# The root route on which each incoming alert enters.
route:
  # The labels by which incoming alerts are grouped together. For example,
  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would
  # be batched into a single group.
  group_by: ['alertname', 'cluster', 'service']

  # When a new group of alerts is created by an incoming alert, wait at
  # least 'group_wait' to send the initial notification.
  # This way ensures that you get multiple alerts for the same group that start
  # firing shortly after another are batched together on the first 
  # notification.
  # 分组等待时间
  group_wait: 30s

  # When the first notification was sent, wait 'group_interval' to send a batch
  # of new alerts that started firing for that group.
  # 分组的时间间隔
  group_interval: 1m

  # If an alert has successfully been sent, wait 'repeat_interval' to
  # resend them.
  # 重复报警的时间间隔
  repeat_interval: 3m 

  # A default receiver
  # 发给定义的 receiver
  receiver: team-X-mails

  # All the above attributes are inherited by all child routes and can 
  # overwritten on each.

  # The child route trees.
  routes:
  # This routes performs a regular expression match on alert labels to
  # catch alerts that are related to a list of services.
  - match_re:
      service: ^(foo1|foo2|baz)$
    receiver: team-X-mails
    # The service has a sub-route for critical alerts, any alerts
    # that do not match, i.e. severity != critical, fall-back to the
    # parent node and are sent to 'team-X-mails'
    routes:
    - match:
        severity: critical
      receiver: team-X-pager
  - match:
      service: files
    receiver: team-Y-mails

    routes:
    - match:
        severity: critical
      receiver: team-Y-pager

  # This route handles all alerts coming from a database service. If there's
  # no team to handle it, it defaults to the DB team.
  - match:
      service: database
    receiver: team-DB-pager
    # Also group alerts by affected database.
    group_by: [alertname, cluster, database]
    routes:
    - match:
        owner: team-X
      receiver: team-X-pager
    - match:
        owner: team-Y
      receiver: team-Y-pager


# Inhibition rules allow to mute a set of alerts given that another alert is
# firing.
# We use this to mute any warning-level notifications if the same alert is 
# already critical.
inhibit_rules:
- source_match:
    severity: 'critical'
  target_match:
    severity: 'warning'
  # Apply inhibition if the alertname is the same.
  equal: ['alertname', 'cluster', 'service']


receivers:
- name: 'team-X-mails'
  email_configs:
  # 收件人地址 想发送多个人可以这样写test1@qq.com,test2@qq.com
  - to: 'yang.lei@belle.com.cn'
    send_resolved: true
    html: ''
    headers: 
      Subject: "[报警触发]测试环境"

- name: 'team-X-pager'
  email_configs:
  - to: 'team-X+alerts-critical@example.org'
  pagerduty_configs:
  - service_key: <team-X-key>

- name: 'team-Y-mails'
  email_configs:
  - to: 'team-Y+alerts@example.org'

- name: 'team-Y-pager'
  pagerduty_configs:
  - service_key: <team-Y-key>

- name: 'team-DB-pager'
  pagerduty_configs:
  - service_key: <team-DB-key>
  
- name: 'team-X-hipchat'
  hipchat_configs:
  - auth_token: <auth_token>
    room_id: 85
    message_format: html
    notify: true

# 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:
      - '172.20.32.38:9093'

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  - "/etc/prometheus/alert.rules"
  # - "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'

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
      - targets: ['localhost:9090']
        labels:
          instance: prometheus

  - job_name: 'mysql'
    scrape_interval: 15s
    static_configs:
      - targets:
        - '172.20.32.38:9104'
        labels:
          instance: db1

  - job_name: 'node'
    scrape_interval: 15s
    static_configs:
      - targets:
        - '172.20.32.38:9100'
        labels:
          instance: node1

groups:
- name: example   #报警规则的名字
  rules:
  # Alert for any instance that is unreachable for >5 minutes.
  - alert: InstanceDown     #检测job的状态，持续1分钟metrices不能访问会发给altermanager进行报警
    expr: up == 1
    for: 1m    #持续时间
    labels:
      serverity: page
      status : yellow
    annotations:
      summary: "Instance  up"
      description: " of job  has been up for more than 1 minutes."
  - alert: NodeMemoryUsage
    expr: (node_memory_MemTotal - (node_memory_MemFree+node_memory_Buffers+node_memory_Cached )) / node_memory_MemTotal * 100 > 2
    for: 1m
    labels:
      severity: warning 
    annotations:
      summary: ": High Memory usage detected 可用内存不足"
      description: ": Memory usage is above 80% (current value is: "