From e4a39d5fafe06935c81dc1999f12b067887364c3 Mon Sep 17 00:00:00 2001 From: Jahir <124062934+juddin927@users.noreply.github.com> Date: Thu, 31 Aug 2023 17:41:26 +0100 Subject: [PATCH] added alerting for Unhealthy container count in DNS ECS cluster (#188) Co-authored-by: Jahir --- .../templates/dns-dhcp-alert-rules.yaml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/k8s-helm-charts/cns-team-monitoring/templates/dns-dhcp-alert-rules.yaml b/k8s-helm-charts/cns-team-monitoring/templates/dns-dhcp-alert-rules.yaml index a648b0d..ce3f746 100644 --- a/k8s-helm-charts/cns-team-monitoring/templates/dns-dhcp-alert-rules.yaml +++ b/k8s-helm-charts/cns-team-monitoring/templates/dns-dhcp-alert-rules.yaml @@ -120,16 +120,16 @@ spec: summary: DNS ECS CPU or MemoryUtilization is above 60 percent description: The Memory or CPU is currently {{ "{{ $value }}" }} grafana_dashboard_url: https://monitoring-alerting.staff.service.justice.gov.uk/d/tm5gLH1Gz/bind-dns-metrics - - alert: DNS ECS Unhealthy container Alert - expr: aws_networkelb_un_healthy_host_count_sum{dimension_LoadBalancer=~\".+dns.+\",account_id="{{ .Values.production_account_id }}"} > 0 + - alert: DNS ECS Unhealthy Container Alert + expr: aws_networkelb_un_healthy_host_count_sum{dimension_LoadBalancer=~".+dns.+",account_id="{{ .Values.production_account_id }}"} > 0 for: 5m labels: severity: critical service: DNS DHCP namespace: {{ .Release.Namespace }} annotations: - summary: DNS ECS Unhealthy container is above 0 - description: Unhealthy container count is currently {{ "{{ $value }}" }} + summary: DNS ECS Unhealthy Container is above 0 + description: Unhealthy Container count is currently {{ "{{ $value }}" }} grafana_dashboard_url: https://monitoring-alerting.staff.service.justice.gov.uk/d/tm5gLH1Gz/bind-dns-metrics - alert: DNS ECS Task Count expr: aws_ecs_containerinsights_running_task_count_average{dimension_ClusterName="staff-device-production-dns-cluster"} < 1