update cnl-quickstart with Prometheus and Grafana

charts/cnl-quickstart/Chart.yaml

@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.1.1
+version: 0.1.2
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
@@ -31,3 +31,10 @@ dependencies:
     repository: https://argoproj.github.io/argo-helm
     version: 7.6.12
     condition: argo-cd.enabled
+  - name: kube-prometheus-stack
+    repository: https://prometheus-community.github.io/helm-charts
+    version: 65.8.1
+  - name: monitoring
+    repository: file://subcharts/monitoring
+    condition: monitoring.enabled
+    version: 0.1.0

charts/cnl-quickstart/site.yaml

@@ -14,4 +14,5 @@ afterInstallationManual: |
 
 namespaces:
   - kafka
-  - argocd
+  - argocd
+  - prometheus

charts/cnl-quickstart/subcharts/monitoring/Chart.yaml

@@ -0,0 +1,24 @@
+apiVersion: v2
+name: cnl-quickstart-monitoring
+description: Deploys common used cloud native tools for Cloud Native Lab
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "0.1.0"

charts/cnl-quickstart/subcharts/monitoring/templates/_helpers.tpl

@@ -0,0 +1,10 @@
+{{/*
+Allow the release namespace to be overridden for multi-namespace deployments in combined charts.
+*/}}
+{{- define "monitoring.namespace" -}}
+  {{- if .Values.namespaceOverride -}}
+    {{- .Values.namespaceOverride -}}
+  {{- else -}}
+    {{- .Release.Namespace -}}
+  {{- end -}}
+{{- end -}}

charts/cnl-quickstart/subcharts/monitoring/templates/grafana-deployment.yaml

@@ -0,0 +1,46 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: grafana
+  labels:
+    app: strimzi
+  namespace: {{ template "monitoring.namespace" . }}
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      name: grafana
+  template:
+    metadata:
+      labels:
+        name: grafana
+    spec:
+      containers:
+      - name: grafana
+        image: grafana/grafana:9.5.18
+        ports:
+        - name: grafana
+          containerPort: 3000
+          protocol: TCP
+        volumeMounts:
+        - name: grafana-data
+          mountPath: /var/lib/grafana
+        - name: grafana-logs
+          mountPath: /var/log/grafana
+        readinessProbe:
+          httpGet:
+            path: /api/health
+            port: 3000
+          initialDelaySeconds: 5
+          periodSeconds: 10
+        livenessProbe:
+          httpGet:
+            path: /api/health
+            port: 3000
+          initialDelaySeconds: 15
+          periodSeconds: 20
+      volumes:
+      - name: grafana-data
+        emptyDir: {}
+      - name: grafana-logs
+        emptyDir: {}

charts/cnl-quickstart/subcharts/monitoring/templates/grafana-service.yaml

@@ -0,0 +1,17 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: grafana
+  labels:
+    app: strimzi
+  namespace: {{ template "monitoring.namespace" . }}
+spec:
+  ports:
+  - name: grafana
+    port: 3000
+    targetPort: 3000
+    protocol: TCP
+    nodePort: 32000  # Port for demo purposes
+  selector:
+    name: grafana
+  type: NodePort

charts/cnl-quickstart/subcharts/monitoring/templates/prometheus-additional.yaml

@@ -0,0 +1,94 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: additional-scrape-configs
+  namespace: {{ template "monitoring.namespace" . }}
+type: Opaque
+stringData:
+  prometheus-additional.yaml: |
+    - job_name: kubernetes-cadvisor
+      honor_labels: true
+      scrape_interval: 10s
+      scrape_timeout: 10s
+      metrics_path: /metrics/cadvisor
+      scheme: https
+      kubernetes_sd_configs:
+      - role: node
+        namespaces:
+          names: []
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        insecure_skip_verify: true
+      relabel_configs:
+      - separator: ;
+        regex: __meta_kubernetes_node_label_(.+)
+        replacement: $1
+        action: labelmap
+      - separator: ;
+        regex: (.*)
+        target_label: __address__
+        replacement: kubernetes.default.svc:443
+        action: replace
+      - source_labels: [__meta_kubernetes_node_name]
+        separator: ;
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+        action: replace
+      - source_labels: [__meta_kubernetes_node_name]
+        separator: ;
+        regex: (.*)
+        target_label: node_name
+        replacement: $1
+        action: replace
+      - source_labels: [__meta_kubernetes_node_address_InternalIP]
+        separator: ;
+        regex: (.*)
+        target_label: node_ip
+        replacement: $1
+        action: replace
+      metric_relabel_configs:
+      - source_labels: [container, __name__]
+        separator: ;
+        regex: POD;container_(network).*
+        target_label: container
+        replacement: $1
+        action: replace
+      - source_labels: [container]
+        separator: ;
+        regex: POD
+        replacement: $1
+        action: drop
+      - source_labels: [container]
+        separator: ;
+        regex: ^$
+        replacement: $1
+        action: drop
+      - source_labels: [__name__]
+        separator: ;
+        regex: container_(network_tcp_usage_total|tasks_state|memory_failures_total|network_udp_usage_total)
+        replacement: $1
+        action: drop
+
+    - job_name: kubernetes-nodes-kubelet
+      scrape_interval: 10s
+      scrape_timeout: 10s
+      scheme: https
+      kubernetes_sd_configs:
+      - role: node
+        namespaces:
+          names: []
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        insecure_skip_verify: true
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics