Дмитрий Соловьев
39f108e496
Classify Ordinis classifier transport failures and empty responses as unavailable, keep stale platform cache when possible, and expose Prometheus metrics/alerting for the outage signal.
22 lines
935 B
YAML
22 lines
935 B
YAML
{{- if .Values.prometheusRule.enabled }}
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: {{ include "pcp-tgu-service.fullname" . }}-alerts
|
|
labels:
|
|
{{- include "pcp-tgu-service.labels" . | nindent 4 }}
|
|
spec:
|
|
groups:
|
|
- name: {{ include "pcp-tgu-service.name" . }}.ordinis
|
|
rules:
|
|
- alert: PcpTguOrdinisUnavailable
|
|
expr: pcp_tgu_ordinis_unavailable == 1
|
|
for: {{ index .Values.prometheusRule.ordinisUnavailable "for" | quote }}
|
|
labels:
|
|
severity: {{ .Values.prometheusRule.ordinisUnavailable.severity | quote }}
|
|
service: {{ include "pcp-tgu-service.name" . | quote }}
|
|
annotations:
|
|
summary: "Ordinis classifier is unavailable for pcp-tgu-service"
|
|
description: "The last pcp-tgu-service attempt to fetch platforms from Ordinis failed. Existing stale platform cache is kept when available."
|
|
{{- end }}
|