feat: Add Prometheus and Grafana monitoring

monitoring/grafana-values.yaml

@@ -0,0 +1,61 @@
+adminUser: admin
+adminPassword: admin1205
+
+persistence:
+  enabled: true
+  size: 10Gi
+
+service:
+  type: NodePort
+  nodePort: 30030
+
+resources:
+  limits:
+    cpu: 200m
+    memory: 256Mi
+  requests:
+    cpu: 100m
+    memory: 128Mi
+
+datasources:
+  datasources.yaml:
+    apiVersion: 1
+    datasources:
+    - name: Prometheus
+      type: prometheus
+      url: http://prometheus-server.monitoring.svc.cluster.local
+      access: proxy
+      isDefault: true
+      editable: true
+
+dashboardProviders:
+  dashboardproviders.yaml:
+    apiVersion: 1
+    providers:
+    - name: 'default'
+      orgId: 1
+      folder: ''
+      type: file
+      disableDeletion: false
+      editable: true
+      options:
+        path: /var/lib/grafana/dashboards/default
+
+dashboards:
+  default:
+    kubernetes-cluster:
+      gnetId: 7249
+      revision: 1
+      datasource: Prometheus
+    kubernetes-pods:
+      gnetId: 6417
+      revision: 1
+      datasource: Prometheus
+    node-exporter:
+      gnetId: 1860
+      revision: 27
+      datasource: Prometheus
+
+plugins:
+  - grafana-piechart-panel
+  - grafana-clock-panel

monitoring/prometheus-values.yaml

@@ -0,0 +1,69 @@
+server:
+  persistentVolume:
+    enabled: true
+    size: 8Gi
+
+  resources:
+    limits:
+      cpu: 500m
+      memory: 512Mi
+    requests:
+      cpu: 250m
+      memory: 256Mi
+
+  retention: "15d"
+
+  service:
+    type: NodePort
+    nodePort: 30090
+
+  global:
+    scrape_interval: 15s
+    scrape_timeout: 10s
+    evaluation_interval: 15s
+
+alertmanager:
+  enabled: true
+  persistentVolume:
+    enabled: true
+    size: 2Gi
+
+  service:
+    type: NodePort
+    nodePort: 30093
+
+pushgateway:
+  enabled: false
+
+nodeExporter:
+  enabled: true
+
+kubeStateMetrics:
+  enabled: true
+
+serviceMonitors:
+  enabled: true
+
+serverFiles:
+  prometheus.yml:
+    scrape_configs:
+      - job_name: 'quote-app'
+        kubernetes_sd_configs:
+          - role: endpoints
+            namespaces:
+              names:
+                - quote-app
+                - quote-app-terraform
+        relabel_configs:
+          - source_labels: [__meta_kubernetes_service_label_app]
+            action: keep
+            regex: quote-app
+          - source_labels: [__meta_kubernetes_endpoint_port_name]
+            action: keep
+            regex: http
+          - source_labels: [__meta_kubernetes_namespace]
+            target_label: namespace
+          - source_labels: [__meta_kubernetes_pod_name]
+            target_label: pod
+          - source_labels: [__meta_kubernetes_service_name]
+            target_label: service

monitoring/quote-app-dashboard.json

@@ -0,0 +1,120 @@
+{
+  "dashboard": {
+    "title": "Quote App Metrics",
+    "tags": ["quote-app", "nodejs"],
+    "timezone": "browser",
+    "panels": [
+      {
+        "id": 1,
+        "title": "Total Quotes Served",
+        "type": "stat",
+        "targets": [
+          {
+            "expr": "sum(quotes_served_total)",
+            "refId": "A"
+          }
+        ],
+        "gridPos": {
+          "h": 8,
+          "w": 6,
+          "x": 0,
+          "y": 0
+        }
+      },
+      {
+        "id": 2,
+        "title": "HTTP Request Rate",
+        "type": "graph",
+        "targets": [
+          {
+            "expr": "rate(http_requests_total[5m])",
+            "legendFormat": "{{method}} {{route}}",
+            "refId": "A"
+          }
+        ],
+        "gridPos": {
+          "h": 8,
+          "w": 18,
+          "x": 6,
+          "y": 0
+        }
+      },
+      {
+        "id": 3,
+        "title": "Request Duration (p95)",
+        "type": "graph",
+        "targets": [
+          {
+            "expr": "histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))",
+            "legendFormat": "{{route}}",
+            "refId": "A"
+          }
+        ],
+        "gridPos": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 8
+        }
+      },
+      {
+        "id": 4,
+        "title": "Active Pods",
+        "type": "stat",
+        "targets": [
+          {
+            "expr": "count(kube_pod_info{namespace=\"quote-app\"})",
+            "refId": "A"
+          }
+        ],
+        "gridPos": {
+          "h": 8,
+          "w": 6,
+          "x": 12,
+          "y": 8
+        }
+      },
+      {
+        "id": 5,
+        "title": "CPU Usage",
+        "type": "graph",
+        "targets": [
+          {
+            "expr": "rate(container_cpu_usage_seconds_total{namespace=\"quote-app\"}[5m])",
+            "legendFormat": "{{pod}}",
+            "refId": "A"
+          }
+        ],
+        "gridPos": {
+          "h": 8,
+          "w": 12,
+          "x": 0,
+          "y": 16
+        }
+      },
+      {
+        "id": 6,
+        "title": "Memory Usage",
+        "type": "graph",
+        "targets": [
+          {
+            "expr": "container_memory_usage_bytes{namespace=\"quote-app\"}",
+            "legendFormat": "{{pod}}",
+            "refId": "A"
+          }
+        ],
+        "gridPos": {
+          "h": 8,
+          "w": 12,
+          "x": 12,
+          "y": 16
+        }
+      }
+    ],
+    "time": {
+      "from": "now-1h",
+      "to": "now"
+    },
+    "refresh": "10s"
+  }
+}

monitoring/quote-app-servicemonitor.yaml

@@ -0,0 +1,16 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: quote-app-monitor
+  namespace: quote-app
+  labels:
+    app: quote-app
+    release: prometheus
+spec:
+  selector:
+    matchLabels:
+      app: quote-app
+  endpoints:
+  - port: http
+    path: /metrics
+    interval: 30s

package.json

@@ -9,17 +9,23 @@
     "test": "jest --coverage",
     "test:watch": "jest --watch"
   },
-  "keywords": ["quotes", "api", "devops", "cicd"],
+  "keywords": [
+    "quotes",
+    "api",
+    "devops",
+    "cicd"
+  ],
   "author": "Aditya Singh",
   "license": "MIT",
   "dependencies": {
-    "express": "^4.18.2",
     "cors": "^2.8.5",
-    "dotenv": "^16.3.1"
+    "dotenv": "^16.3.1",
+    "express": "^4.18.2",
+    "prom-client": "^15.1.3"
   },
   "devDependencies": {
-    "nodemon": "^3.0.1",
     "jest": "^29.7.0",
+    "nodemon": "^3.0.1",
     "supertest": "^6.3.3"
   }
 }