From 8c1fa4b11cf513d1ee0810ef8d739e0c3d624082 Mon Sep 17 00:00:00 2001 From: Herve Nicol <12008875+hervenicol@users.noreply.github.com> Date: Tue, 15 Oct 2024 15:30:35 +0200 Subject: [PATCH] Inhibit prometheas-agent alerts when a cluster has no worker nodes --- CHANGELOG.md | 4 ++++ .../platform/atlas/alerting-rules/prometheus-agent.rules.yml | 1 + 2 files changed, 5 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 7136d39c..fb0ee314 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ## [Unreleased] +### Changed + +- Inhibit prometheas-agent alerts when a cluster has no worker nodes (AWS vintage only for now) + ## [4.19.0] - 2024-10-15 ### Added diff --git a/helm/prometheus-rules/templates/platform/atlas/alerting-rules/prometheus-agent.rules.yml b/helm/prometheus-rules/templates/platform/atlas/alerting-rules/prometheus-agent.rules.yml index 16772172..0dfbc0c9 100644 --- a/helm/prometheus-rules/templates/platform/atlas/alerting-rules/prometheus-agent.rules.yml +++ b/helm/prometheus-rules/templates/platform/atlas/alerting-rules/prometheus-agent.rules.yml @@ -51,6 +51,7 @@ spec: cancel_if_cluster_is_not_running_prometheus_agent: "true" cancel_if_cluster_status_creating: "true" cancel_if_cluster_status_deleting: "true" + cancel_if_cluster_has_no_workers: "true" ## Same as PrometheusAgentFailing, but triggers inhibition earlier and does not page. - alert: PrometheusAgentFailingInhibition annotations: