From 67c513d1a5451a4a72f889171720525769baae15 Mon Sep 17 00:00:00 2001
From: Daniel Sy <daniel.sy@noreply.edp.buildth.ing>
Date: Wed, 13 Aug 2025 13:38:31 +0200
Subject: [PATCH] =?UTF-8?q?feat(alerts):=20=F0=9F=8E=89=20Add=20disk=20con?=
 =?UTF-8?q?sumption=20high=20alert=20rule?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce a new alert rule for monitoring high disk consumption in Kubernetes. This enhances observability by providing alerts when disk usage exceeds 60%, helping to maintain storage health in the cluster environment.

Refs: DevFW/infra-deploy#109
---
 .../victoria-k8s-stack/manifests/alerts.yaml          | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/template/stacks/observability/victoria-k8s-stack/manifests/alerts.yaml b/template/stacks/observability/victoria-k8s-stack/manifests/alerts.yaml
index 9419609..110ee7e 100644
--- a/template/stacks/observability/victoria-k8s-stack/manifests/alerts.yaml
+++ b/template/stacks/observability/victoria-k8s-stack/manifests/alerts.yaml
@@ -27,3 +27,14 @@ spec:
           annotations:
             value: "{{ $value }}"
             description: 'forgejo s3 backup job failed in cluster environment {{ $labels.cluster_environment }}'
+    - name: disk-consumption-high
+      rules:
+        - alert: disk consumption high
+          expr: 1-(kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes) > 0.6
+          for: 30s
+          labels:
+            severity: major
+            job:  "{{ $labels.job }}"
+          annotations:
+            value: "{{ $value }}"
+            description: 'disk consumption of pvc {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is high in cluster environment {{ $labels.cluster_environment }}'