fix(common-services): fix 2.0.1 deployment failures

.github/workflows/lint-test-common-services.yaml

@@ -109,10 +109,20 @@ jobs:
           kubectl cluster-info --context kind-chart-testing
           kubectl get nodes --context kind-chart-testing
 
+      - name: Install Prometheus Operator CRDs
+        run: |
+          curl -sSL -o /tmp/prom-crds.yaml https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/main/example/prometheus-operator-crd/monitoring.coreos.com_servicemonitors.yaml
+          curl -sSL -o /tmp/prom-podmonitor-crd.yaml https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/main/example/prometheus-operator-crd/monitoring.coreos.com_podmonitors.yaml
+          curl -sSL -o /tmp/prom-rule-crd.yaml https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/main/example/prometheus-operator-crd/monitoring.coreos.com_prometheusrules.yaml
+          kubectl apply -f /tmp/prom-crds.yaml
+          kubectl apply -f /tmp/prom-podmonitor-crd.yaml
+          kubectl apply -f /tmp/prom-rule-crd.yaml
+        shell: bash
+
       - name: Run chart-testing (install)
         run: |
           ct install --charts=charts/common-services \
-            --helm-extra-args="--timeout=15m0s" \
+            --helm-extra-args="--timeout=20m0s" \
             --helm-extra-set-args="--set=velero-ui.enabled=false \
             --set=elasticsearch.replicas=1 \
             --set=elasticsearch.clusterHealthCheckParams=wait_for_status=yellow&timeout=60s \
@@ -132,7 +142,7 @@ jobs:
       contents: read
       packages: write
     runs-on: ubuntu-latest
-    needs: test
+    needs: lint
     steps:
       - name: Checkout
         uses: actions/checkout@v3

charts/common-services/Chart.yaml

@@ -10,7 +10,7 @@ type: application
 # Chart Version
 # -------------
 # This version should be incremented following Semantic Versioning (https://semver.org/) whenever the chart's structure or templates change.
-version: 2.0.0
+version: 2.0.1
 
 # Application Version (Informational)
 # -----------------------------------
@@ -98,7 +98,7 @@ dependencies:
   condition: velero.enabled
 - name: cloudnative-pg
   repository: https://cloudnative-pg.github.io/charts
-  version: 0.26.0
+  version: 0.27.1
   condition: cloudnative-pg.enabled
 - name: velero-ui
   version: 0.x.x
@@ -109,8 +109,8 @@ dependencies:
   repository: https://vesoft-inc.github.io/nebula-operator/charts
   condition: nebula-operator.enabled
 - name: flink-kubernetes-operator
-  version: 1.12.1
-  repository: https://downloads.apache.org/flink/flink-kubernetes-operator-1.12.1
+  version: 1.13.0
+  repository: https://downloads.apache.org/flink/flink-kubernetes-operator-1.13.0
   condition: flink-kubernetes-operator.enabled
 - name: loki
   repository: https://grafana.github.io/helm-charts
@@ -120,3 +120,7 @@ dependencies:
   repository: https://grafana.github.io/helm-charts
   version: 1.2.1
   condition: alloy.enabled
+- name: prometheus-elasticsearch-exporter
+  version: 6.6.0
+  repository: https://prometheus-community.github.io/helm-charts
+  condition: prometheus-elasticsearch-exporter.enabled

charts/common-services/README.md

@@ -1,9 +1,50 @@
 # common-services
 
-![Version: 1.0.9](https://img.shields.io/badge/Version-1.0.9-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.3](https://img.shields.io/badge/AppVersion-1.3-informational?style=flat-square)
+![Version: 2.0.1](https://img.shields.io/badge/Version-2.0.1-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.0](https://img.shields.io/badge/AppVersion-2.0-informational?style=flat-square)
 
 A Helm chart for deploying RadiantOne Common Services on Kubernetes
 
+## What's New in 2.0.1
+
+### Automatic Metrics & Dashboards
+
+Every enabled service now automatically:
+- Exposes a Prometheus-compatible metrics endpoint
+- Is scraped by Prometheus via service annotations
+- Has a pre-configured Grafana dashboard
+
+| Service | Metrics Port | Dashboard |
+|---------|-------------|-----------|
+| ArgoCD | 8082, 8083, 8084 | ✅ |
+| Elasticsearch (exporter) | 9108 | ✅ |
+| Fluent-bit | 2020 | ✅ |
+| Grafana | 3000 | ✅ |
+| HAProxy | 8404 | ✅ |
+| Kibana | 9684 | ✅ |
+| Loki | 3100 | ✅ |
+| OpenSearch | 9200 | ✅ |
+| PostgreSQL | 9187 | ✅ |
+| Velero | 8085 | ✅ |
+| Zookeeper | 9141 | ✅ |
+| CloudNative-PG | 8080 | ✅ |
+| Alloy | 12345 | ✅ |
+| Flink Operator | 9999 | ✅ |
+
+### Prometheus Scraping
+
+Services are configured with standard annotations for Prometheus discovery:
+
+```yaml
+annotations:
+  prometheus.io/scrape: "true"
+  prometheus.io/port: "<port>"
+  prometheus.io/path: "/metrics"
+```
+
+### Dashboard Auto-Import
+
+Grafana dashboards are automatically provisioned via ConfigMaps with the `grafana_dashboard: "1"` label. The Grafana sidecar discovers and imports them on startup.
+
 ## Maintainers
 
 | Name | Email | Url |

charts/common-services/dashboards/alloy/README.md

@@ -0,0 +1,30 @@
+# Grafana Alloy Dashboards
+
+## Included Dashboard
+
+- `alloy-cluster-dashboard.json` - Cluster overview dashboard (Grafana Dashboard ID: 19624)
+
+This dashboard is automatically provisioned when:
+- `grafana.enabled: true`
+- `alloy.enabled: true`
+
+## Metrics
+
+Alloy exposes metrics on port 12345 at `/metrics`. The service is configured with Prometheus annotations for automatic scraping:
+
+```yaml
+alloy:
+  service:
+    annotations:
+      prometheus.io/scrape: "true"
+      prometheus.io/port: "12345"
+      prometheus.io/path: "/metrics"
+```
+
+## Key Metrics
+
+| Metric | Description |
+|--------|-------------|
+| `alloy_build_info` | Build information |
+| `alloy_component_*` | Component-level metrics |
+| `alloy_resources_*` | Resource usage metrics |