diff --git a/altermanager/alertmanager-config.yaml b/altermanager/alertmanager-config.yaml index 3d712acb..8064fc95 100644 --- a/altermanager/alertmanager-config.yaml +++ b/altermanager/alertmanager-config.yaml @@ -3,7 +3,7 @@ kind: Secret type: Opaque metadata: name: altermanager-email-credentials - namespace: freeleaps-monitoring-system + namespace: freeleaps-prod data: password: cHducGNya3d0aXp5Z2RoZQ== --- @@ -11,7 +11,7 @@ apiVersion: monitoring.coreos.com/v1alpha1 kind: AlertmanagerConfig metadata: name: alertmanager-config - namespace: freeleaps-monitoring-system + namespace: freeleaps-prod spec: receivers: # - msteamsConfigs: @@ -37,16 +37,21 @@ spec: sendResolved: true headers: - key: Subject - value: 'π¨Freeleaps Alert: {{ .CommonAnnotations.summary }}' + value: '{{ if eq .Status "firing" }}π¨ Freeleaps Alert: {{ .CommonAnnotations.summary }}{{ else }}β Freeleaps Resolved: {{ .CommonAnnotations.summary }}{{ end }}' html: |- +
π AlertName: {{ .CommonLabels.alertname }}
+π§ Service: {{ .CommonLabels.service }}
+π§ Pod: {{ .CommonLabels.pod }}({{ .CommonLabels.instance }})
+π·οΈ Severity: {{ .CommonLabels.severity }}
+{{ if eq .Status "firing" }}π΄ Status:{{ else }}π’ Status:{{ end }} {{ .Status | toUpper }}
π Description: {{ .CommonAnnotations.description }}
-{{ if eq .Status "firing" }}π΄ Status: {{ .Status | toUpper }}{{ else }}π’ Status: {{ .Status | toUpper }}{{ end }}
π Runbook: {{ .CommonAnnotations.runbook_url }}
name: email route: groupBy: - severity - groupInterval: 30s + groupInterval: 5m receiver: email - groupWait: 30s - repeatInterval: 1m + groupWait: 5m + repeatInterval: 6h diff --git a/freeleaps/helm-pkg/metrics/values.prod.yaml b/freeleaps/helm-pkg/metrics/values.prod.yaml index 7327084e..b1f6f443 100644 --- a/freeleaps/helm-pkg/metrics/values.prod.yaml +++ b/freeleaps/helm-pkg/metrics/values.prod.yaml @@ -94,7 +94,7 @@ metrics: labels: severity: critical service: metrics-service - namespace: freeleaps-monitoring-system + namespace: freeleaps-prod annotations: summary: Freeleaps Metrics service is down (instance {{ $labels.instance }}) description: Freeleaps Metrics service has been down for more than 1 minutes. @@ -105,7 +105,7 @@ metrics: labels: severity: warning service: metrics-service - namespace: freeleaps-monitoring-system + namespace: freeleaps-prod annotations: summary: High error rate in freeleaps metrics service (instance {{ $labels.instance }}) description: Freeleaps Metrics service error rate is {{ $value }} errors per second.