awesome-prometheus-alerts/dist/rules/haproxy/haproxy-exporter-v1.yml

groups:

- name: HaproxyExporterV1

  rules:

    - alert: HaproxyDown
      expr: 'haproxy_up == 0'
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: HAProxy down (instance {{ $labels.instance }})
        description: "HAProxy down\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyHighHttp4xxErrorRateBackend
      expr: 'sum by (backend) (rate(haproxy_server_http_responses_total{code="4xx"}[1m])) / sum by (backend) (rate(haproxy_server_http_responses_total[1m])) > 5'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: HAProxy high HTTP 4xx error rate backend (instance {{ $labels.instance }})
        description: "Too many HTTP requests with status 4xx (> 5%) on backend {{ $labels.fqdn }}/{{ $labels.backend }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyHighHttp5xxErrorRateBackend
      expr: 'sum by (backend) (rate(haproxy_server_http_responses_total{code="5xx"}[1m])) / sum by (backend) (rate(haproxy_server_http_responses_total[1m])) > 5'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: HAProxy high HTTP 5xx error rate backend (instance {{ $labels.instance }})
        description: "Too many HTTP requests with status 5xx (> 5%) on backend {{ $labels.fqdn }}/{{ $labels.backend }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyHighHttp4xxErrorRateServer
      expr: 'sum by (server) (rate(haproxy_server_http_responses_total{code="4xx"}[1m]) * 100) / sum by (server) (rate(haproxy_server_http_responses_total[1m])) > 5'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: HAProxy high HTTP 4xx error rate server (instance {{ $labels.instance }})
        description: "Too many HTTP requests with status 4xx (> 5%) on server {{ $labels.server }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyHighHttp5xxErrorRateServer
      expr: 'sum by (server) (rate(haproxy_server_http_responses_total{code="5xx"}[1m]) * 100) / sum by (server) (rate(haproxy_server_http_responses_total[1m])) > 5'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: HAProxy high HTTP 5xx error rate server (instance {{ $labels.instance }})
        description: "Too many HTTP requests with status 5xx (> 5%) on server {{ $labels.server }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyServerResponseErrors
      expr: 'sum by (server) (rate(haproxy_server_response_errors_total[1m]) * 100) / sum by (server) (rate(haproxy_server_http_responses_total[1m])) > 5'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: HAProxy server response errors (instance {{ $labels.instance }})
        description: "Too many response errors to {{ $labels.server }} server (> 5%).\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyBackendConnectionErrors
      expr: 'sum by (backend) (rate(haproxy_backend_connection_errors_total[1m])) > 100'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: HAProxy backend connection errors (instance {{ $labels.instance }})
        description: "Too many connection errors to {{ $labels.fqdn }}/{{ $labels.backend }} backend (> 100 req/s). Request throughput may be too high.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyServerConnectionErrors
      expr: 'sum by (server) (rate(haproxy_server_connection_errors_total[1m])) > 100'
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: HAProxy server connection errors (instance {{ $labels.instance }})
        description: "Too many connection errors to {{ $labels.server }} server (> 100 req/s). Request throughput may be too high.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyBackendMaxActiveSession
      expr: '((sum by (backend) (avg_over_time(haproxy_backend_max_sessions[2m]) * 100) / sum by (backend) (avg_over_time(haproxy_backend_limit_sessions[2m])))) > 80'
      for: 2m
      labels:
        severity: warning
      annotations:
        summary: HAProxy backend max active session (instance {{ $labels.instance }})
        description: "HAproxy backend {{ $labels.fqdn }}/{{ $labels.backend }} is reaching session limit (> 80%).\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyPendingRequests
      expr: 'sum by (backend) (haproxy_backend_current_queue) > 0'
      for: 2m
      labels:
        severity: warning
      annotations:
        summary: HAProxy pending requests (instance {{ $labels.instance }})
        description: "Some HAProxy requests are pending on {{ $labels.fqdn }}/{{ $labels.backend }} backend\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyHttpSlowingDown
      expr: 'avg by (backend) (haproxy_backend_http_total_time_average_seconds) > 1'
      for: 1m
      labels:
        severity: warning
      annotations:
        summary: HAProxy HTTP slowing down (instance {{ $labels.instance }})
        description: "Average request time is increasing\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyRetryHigh
      expr: 'sum by (backend) (rate(haproxy_backend_retry_warnings_total[1m])) > 10'
      for: 2m
      labels:
        severity: warning
      annotations:
        summary: HAProxy retry high (instance {{ $labels.instance }})
        description: "High rate of retry on {{ $labels.fqdn }}/{{ $labels.backend }} backend\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyBackendDown
      expr: 'haproxy_backend_up == 0'
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: HAProxy backend down (instance {{ $labels.instance }})
        description: "HAProxy backend is down\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyServerDown
      expr: 'haproxy_server_up == 0'
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: HAProxy server down (instance {{ $labels.instance }})
        description: "HAProxy server is down\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyFrontendSecurityBlockedRequests
      expr: 'sum by (frontend) (rate(haproxy_frontend_requests_denied_total[2m])) > 10'
      for: 2m
      labels:
        severity: warning
      annotations:
        summary: HAProxy frontend security blocked requests (instance {{ $labels.instance }})
        description: "HAProxy is blocking requests for security reason\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HaproxyServerHealthcheckFailure
      expr: 'increase(haproxy_server_check_failures_total[1m]) > 0'
      for: 1m
      labels:
        severity: warning
      annotations:
        summary: HAProxy server healthcheck failure (instance {{ $labels.instance }})
        description: "Some server healthcheck are failing on {{ $labels.server }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"