Merge pull request #384 from jottofar/ota-189-alert-upgradeable-false

Add an alert to CVO that fires when cluster is not upgradeable

Author: openshift-merge-robot

install/0000_90_cluster-version-operator_02_servicemonitor.yaml

@@ -53,6 +53,14 @@ spec:
         severity: critical
   - name: cluster-operators
     rules:
+    - alert: ClusterNotUpgradeable
+      annotations:
+        message: One or more cluster operators have been blocking minor version cluster upgrades for at least an hour for reason {{ "{{ with $cluster_operator_conditions := \"cluster_operator_conditions\" | query}}{{range $value := .}}{{if and (eq (label \"name\" $value) \"version\") (eq (label \"condition\" $value) \"Upgradeable\") (eq (label \"endpoint\" $value) \"metrics\") (eq (value $value) 0.0) (ne (len (label \"reason\" $value)) 0) }}{{label \"reason\" $value}}.{{end}}{{end}}{{end}}"}} {{ "{{ with $console_url := \"console_url\" | query }}{{ if ne (len (label \"url\" (first $console_url ) ) ) 0}} For more information refer to {{ label \"url\" (first $console_url ) }}/settings/cluster/.{{ end }}{{ end }}" }}
+      expr: |
+        max by (name, condition, endpoint) (cluster_operator_conditions{name="version", condition="Upgradeable", endpoint="metrics"} == 0)
+      for: 60m
+      labels:
+        severity: warning
     - alert: ClusterOperatorDown
       annotations:
         message: Cluster operator {{ "{{ $labels.name }}" }} has not been available for 10 minutes. Operator may be down or disabled, cluster will not be kept up to date and upgrades will not be possible.