Add Kubernetes manifests for Grafana dashboard and Prometheus scraping

ConfigMap with grafana_dashboard label for sidecar auto-discovery,
and ServiceMonitor for kube-prometheus-stack scrape target.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

k8s/grafana-dashboard-configmap.yaml

@@ -0,0 +1,232 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: pokerface-dashboard
+  namespace: monitoring
+  labels:
+    grafana_dashboard: "1"
+data:
+  pokerface.json: |
+    {
+      "annotations": { "list": [] },
+      "editable": true,
+      "fiscalYearStartMonth": 0,
+      "graphTooltip": 1,
+      "links": [],
+      "panels": [
+        {
+          "collapsed": false,
+          "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
+          "id": 100,
+          "title": "Overview",
+          "type": "row"
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": {
+            "defaults": {
+              "thresholds": { "steps": [{ "color": "green", "value": null }] },
+              "color": { "mode": "thresholds" }
+            }
+          },
+          "gridPos": { "h": 4, "w": 6, "x": 0, "y": 1 },
+          "id": 1,
+          "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": ["lastNotNull"] } },
+          "title": "Unique Users",
+          "type": "stat",
+          "targets": [{ "expr": "pokerface_unique_users", "legendFormat": "", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": {
+            "defaults": {
+              "thresholds": { "steps": [{ "color": "green", "value": null }] },
+              "color": { "mode": "thresholds" }
+            }
+          },
+          "gridPos": { "h": 4, "w": 6, "x": 6, "y": 1 },
+          "id": 2,
+          "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": ["lastNotNull"] } },
+          "title": "Unique Tenants",
+          "type": "stat",
+          "targets": [{ "expr": "pokerface_unique_tenants", "legendFormat": "", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": {
+            "defaults": {
+              "thresholds": { "steps": [{ "color": "blue", "value": null }] },
+              "color": { "mode": "thresholds" }
+            }
+          },
+          "gridPos": { "h": 4, "w": 6, "x": 12, "y": 1 },
+          "id": 3,
+          "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": ["lastNotNull"] } },
+          "title": "Active Connections",
+          "type": "stat",
+          "targets": [{ "expr": "pokerface_websocket_connections", "legendFormat": "", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": {
+            "defaults": {
+              "thresholds": { "steps": [{ "color": "purple", "value": null }] },
+              "color": { "mode": "thresholds" }
+            }
+          },
+          "gridPos": { "h": 4, "w": 6, "x": 18, "y": 1 },
+          "id": 4,
+          "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": ["lastNotNull"] } },
+          "title": "Active Rooms",
+          "type": "stat",
+          "targets": [{ "expr": "sum(pokerface_rooms_active)", "legendFormat": "", "refId": "A" }]
+        },
+        {
+          "collapsed": false,
+          "gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
+          "id": 101,
+          "title": "Activity",
+          "type": "row"
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 8, "x": 0, "y": 6 },
+          "id": 5,
+          "options": { "tooltip": { "mode": "single" } },
+          "title": "Sessions Created / hr",
+          "type": "timeseries",
+          "targets": [{ "expr": "rate(pokerface_sessions_created_total[1h]) * 3600", "legendFormat": "sessions/hr", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 8, "x": 8, "y": 6 },
+          "id": 6,
+          "options": { "tooltip": { "mode": "single" } },
+          "title": "Votes / hr",
+          "type": "timeseries",
+          "targets": [{ "expr": "rate(pokerface_votes_total[1h]) * 3600", "legendFormat": "votes/hr", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 8, "x": 16, "y": 6 },
+          "id": 7,
+          "options": { "tooltip": { "mode": "multi" } },
+          "title": "OAuth Logins / hr",
+          "type": "timeseries",
+          "targets": [
+            { "expr": "rate(pokerface_oauth_logins_total{status=\"success\"}[1h]) * 3600", "legendFormat": "success", "refId": "A" },
+            { "expr": "rate(pokerface_oauth_logins_total{status=\"failure\"}[1h]) * 3600", "legendFormat": "failure", "refId": "B" }
+          ]
+        },
+        {
+          "collapsed": false,
+          "gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
+          "id": 102,
+          "title": "Performance",
+          "type": "row"
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 6, "x": 0, "y": 15 },
+          "id": 8,
+          "options": { "tooltip": { "mode": "multi" } },
+          "title": "HTTP Request Rate by Route",
+          "type": "timeseries",
+          "targets": [{ "expr": "sum by (route) (rate(pokerface_http_requests_total[5m]))", "legendFormat": "{{route}}", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "unit": "s", "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 6, "x": 6, "y": 15 },
+          "id": 9,
+          "options": { "tooltip": { "mode": "multi" } },
+          "title": "HTTP Latency p95",
+          "type": "timeseries",
+          "targets": [{ "expr": "histogram_quantile(0.95, sum by (le, route) (rate(pokerface_http_request_duration_seconds_bucket[5m])))", "legendFormat": "{{route}}", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "unit": "s", "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 6, "x": 12, "y": 15 },
+          "id": 10,
+          "options": { "tooltip": { "mode": "single" } },
+          "title": "Jira API Latency p95",
+          "type": "timeseries",
+          "targets": [{ "expr": "histogram_quantile(0.95, sum by (le) (rate(pokerface_jira_request_duration_seconds_bucket[5m])))", "legendFormat": "p95", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 6, "x": 18, "y": 15 },
+          "id": 11,
+          "options": { "tooltip": { "mode": "single" } },
+          "title": "Jira Error Rate",
+          "type": "timeseries",
+          "targets": [{ "expr": "rate(pokerface_jira_errors_total[5m])", "legendFormat": "errors/s", "refId": "A" }]
+        },
+        {
+          "collapsed": false,
+          "gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
+          "id": 103,
+          "title": "System",
+          "type": "row"
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "unit": "bytes", "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 8, "x": 0, "y": 24 },
+          "id": 12,
+          "options": { "tooltip": { "mode": "multi" } },
+          "title": "Node.js Memory Usage",
+          "type": "timeseries",
+          "targets": [
+            { "expr": "process_resident_memory_bytes", "legendFormat": "RSS", "refId": "A" },
+            { "expr": "nodejs_heap_size_used_bytes", "legendFormat": "Heap Used", "refId": "B" }
+          ]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "unit": "s", "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 8, "x": 8, "y": 24 },
+          "id": 13,
+          "options": { "tooltip": { "mode": "single" } },
+          "title": "Event Loop Lag",
+          "type": "timeseries",
+          "targets": [{ "expr": "nodejs_eventloop_lag_seconds", "legendFormat": "lag", "refId": "A" }]
+        },
+        {
+          "datasource": { "type": "prometheus", "uid": "${datasource}" },
+          "fieldConfig": { "defaults": { "unit": "percentunit", "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
+          "gridPos": { "h": 8, "w": 8, "x": 16, "y": 24 },
+          "id": 14,
+          "options": { "tooltip": { "mode": "single" } },
+          "title": "CPU Usage",
+          "type": "timeseries",
+          "targets": [{ "expr": "rate(process_cpu_seconds_total[5m])", "legendFormat": "CPU", "refId": "A" }]
+        }
+      ],
+      "refresh": "30s",
+      "schemaVersion": 39,
+      "tags": ["pokerface"],
+      "templating": {
+        "list": [
+          {
+            "current": {},
+            "hide": 0,
+            "includeAll": false,
+            "name": "datasource",
+            "options": [],
+            "query": "prometheus",
+            "refresh": 1,
+            "type": "datasource"
+          }
+        ]
+      },
+      "time": { "from": "now-3h", "to": "now" },
+      "title": "Pokerface",
+      "uid": "pokerface-overview"
+    }

k8s/servicemonitor.yaml

@@ -0,0 +1,18 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: pokerface
+  namespace: monitoring
+  labels:
+    release: kube-prometheus-stack
+spec:
+  namespaceSelector:
+    matchNames:
+      - pokerface
+  selector:
+    matchLabels:
+      app: pokerface
+  endpoints:
+    - port: http
+      path: /metrics
+      interval: 15s