From 90a9337f1ae0a5db9c1ae9652e517edf09573114 Mon Sep 17 00:00:00 2001 From: Eason Zhao Date: Mon, 20 Oct 2025 21:42:16 -0400 Subject: [PATCH] feat: update set-up --- .../helm-pkg/centralStorage/values.prod.yaml | 27 +++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/freeleaps/helm-pkg/centralStorage/values.prod.yaml b/freeleaps/helm-pkg/centralStorage/values.prod.yaml index e27dc287..aa1ccd09 100644 --- a/freeleaps/helm-pkg/centralStorage/values.prod.yaml +++ b/freeleaps/helm-pkg/centralStorage/values.prod.yaml @@ -109,3 +109,30 @@ centralStorage: controlledResources: - cpu - memory + prometheusRule: + name: freepeals-prod-central-storage + enabled: true + namespace: freeleaps-monitoring-system + labels: + release: kube-prometheus-stack + rules: + - alert: FreeleapsCentralStorageServiceDown + expr: up{job="central-storage-service"} == 0 + for: 1m + labels: + severity: critical + service: central-storage-service + annotations: + summary: Freeleaps Central Storage service is down (instance {{ $labels.instance }}) + description: Freeleaps Central Storage service has been down for more than 1 minutes. + runbook_url: https://netorgft10898514.sharepoint.com/:w:/s/FreeleapsEngineeringTeam/EUlvzumTsPxCpPAzI3gm9OIB0DCLTjQzzYVL6VsHYZFjxg?e=0dxVr7 + - alert: FreeleapsCentralStorageServiceHighErrorRate + expr: rate(http_requests_total{job="central-storage-service",status=~"5.."}[5m]) > 0.1 + for: 5m + labels: + severity: warning + service: central-storage-service + annotations: + summary: High error rate in freeleaps central storage service (instance {{ $labels.instance }}) + description: Freeleaps Central Storage service error rate is {{ $value }} errors per second. + runbook_url: https://netorgft10898514.sharepoint.com/:w:/s/FreeleapsEngineeringTeam/EUlvzumTsPxCpPAzI3gm9OIB0DCLTjQzzYVL6VsHYZFjxg?e=0dxVr7