prometheus.rules

# example prometheus alerting rules

groups:
- name: gopherwatch
  rules:
  - alert: gopherwatch-security-error
    expr: rate(gopherwatch_tlog_security_errors[1h]) > 0
    annotations:
      summary: transparency log security error
    labels:
      page: always

  - alert: gopherwatch-panic
    expr: increase(gopherwatch_panics_total[1h]) > 0
    annotations:
      summary: unhandled panic
    labels:
      page: workhours

  - alert: gropherwatch-tlog-records
    expr: rate(gopherwatch_tlog_records[5m]) == 0
    for: 4h
    annotations:
      summary: no new records in tlog for 4 hours
    labels:
      page: workhours

  - alert: gropherwatch-tlog-processed
    expr: rate(gopherwatch_tlog_processed[5m]) == 0
    for: 4h
    annotations:
      summary: no records from tlog processed for 4 hours
    labels:
      page: workhours

  - alert: gropherwatch-submission-errors
    expr: rate(gopherwatch_message_submit_errors_total[5m]) > 0
    annotations:
      summary: errors while submitting email for delivery
    labels:
      page: workhours

  - alert: gropherwatch-incoming-processing-errors
    expr: rate(gopherwatch_incoming_process_errors_total[5m]) > 0
    annotations:
      summary: errors while processing received messages, like dsns
    labels:
      page: workhours

  - alert: gropherwatch-webapi-result-errors
    expr: rate(gopherwatch_webapi_results_total{result!="ok"}[5m]) > 0
    annotations:
      summary: errors making webapi calls
    labels:
      page: workhours