added minimal monitoring setup for the plugin enabled basic alert/dashboards

Author: christophrichtersap

.github/workflows/validate-prometheus-alerts.yaml

@@ -0,0 +1,51 @@
+# SPDX-FileCopyrightText: 2026 SAP SE or an SAP affiliate company and cobaltcore-dev contributors
+# SPDX-License-Identifier: Apache-2.0
+
+name: Validate Prometheus Alerts
+
+on:
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - 'charts/openstack-hypervisor-operator/alerts/*.yaml'
+      - 'charts/openstack-hypervisor-operator/alerts/*.yml'
+
+permissions:
+  contents: read
+
+env:
+  PROMTOOL_VERSION: 3.8.0
+
+defaults:
+  run:
+    shell: bash
+
+concurrency:
+  group: validate-prometheus-alerts-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  validate-alerts:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Install promtool
+        run: |
+          set -euo pipefail
+          curl -sSfL "https://github.com/prometheus/prometheus/releases/download/v${PROMTOOL_VERSION}/prometheus-${PROMTOOL_VERSION}.linux-amd64.tar.gz" \
+            | tar xz --strip-components=1 "prometheus-${PROMTOOL_VERSION}.linux-amd64/promtool"
+          sudo install -m 0755 promtool /usr/local/bin/promtool
+          promtool --version
+
+      - name: Validate Prometheus alert rules
+        run: |
+          set -euo pipefail
+          shopt -s nullglob
+          files=(charts/openstack-hypervisor-operator/alerts/*.{yaml,yml})
+          if [ ${#files[@]} -eq 0 ]; then
+            echo "No Prometheus rule files found."
+            exit 1
+          fi
+          promtool check rules "${files[@]}"

charts/openstack-hypervisor-operator/alerts/operator.yaml

@@ -0,0 +1,60 @@
+# SPDX-FileCopyrightText: 2025 SAP SE or an SAP affiliate company and cobaltcore-dev contributors
+# SPDX-License-Identifier: Apache-2.0
+
+groups:
+- name: hypervisorOperator
+  rules:
+  - alert: HypervisorNotReady
+    expr: |
+      kube_customresource_hypervisor_condition{condition="Ready"} == 0
+    for: 10m
+    labels:
+      severity: critical
+      type: hypervisor_operator
+    annotations:
+      summary: "Hypervisor {{`{{ $labels.name }}`}} is not ready"
+      description: "The hypervisor {{`{{ $labels.name }}`}} in zone {{`{{ $labels.zone }}`}} has been in a non-ready state for more than 10 minutes."
+
+  - alert: HypervisorConditionDegraded
+    expr: |
+      kube_customresource_hypervisor_condition{condition!="Ready"} == 0
+    for: 10m
+    labels:
+      severity: warning
+      type: hypervisor_operator
+    annotations:
+      summary: "Hypervisor {{`{{ $labels.name }}`}} condition {{`{{ $labels.condition }}`}} is degraded"
+      description: "The hypervisor {{`{{ $labels.name }}`}} in zone {{`{{ $labels.zone }}`}} has condition {{`{{ $labels.condition }}`}} in a False state for more than 10 minutes. Reason: {{`{{ $labels.reason }}`}}."
+
+  - alert: HypervisorEvicted
+    expr: |
+      kube_customresource_hypervisor_evicted == 1
+    for: 2d
+    labels:
+      severity: warning
+      type: hypervisor_operator
+    annotations:
+      summary: "Hypervisor {{`{{ $labels.name }}`}} has been evicted"
+      description: "The hypervisor {{`{{ $labels.name }}`}} in zone {{`{{ $labels.zone }}`}} has been in an evicted state for more than 2 days."
+
+  - alert: HypervisorOperatorReconcileErrors
+    expr: |
+      rate(controller_runtime_reconcile_errors_total[5m]) > 0
+    for: 15m
+    labels:
+      severity: warning
+      type: hypervisor_operator
+    annotations:
+      summary: "Hypervisor operator controller {{`{{ $labels.controller }}`}} has persistent reconcile errors"
+      description: "The controller {{`{{ $labels.controller }}`}} has been producing reconciliation errors for more than 15 minutes."
+
+  - alert: HypervisorOperatorDown
+    expr: |
+      up{job=~".*hypervisor-operator.*"} == 0
+    for: 5m
+    labels:
+      severity: critical
+      type: hypervisor_operator
+    annotations:
+      summary: "Hypervisor operator is down"
+      description: "The hypervisor operator metrics endpoint has been unreachable for more than 5 minutes."