feat: Add Redpanda Console, Pulsar Distribution Service, and Grafana Dashboards

- Add Redpanda Console service (port 28080, Traefik integration)
- Add Pulsar Distribution Service (Pulsar -> Brokers)
- Create Grafana dashboards for Redpanda, Pulsar, and Smart City Ingestion
- Configure Prometheus targets for Pulsar and Redpanda metrics
- Fix FROST URL in distribution service
- Create session resume for 2026-05-05

grafana/provisioning/dashboards/redpanda-metrics.json

@@ -0,0 +1,102 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Redpanda Overview",
+      "type": "row",
+      "gridPos": {"h": 1, "w": 24, "x": 0, "y": 0}
+    },
+    {
+      "title": "Kafka API Requests",
+      "type": "timeseries",
+      "datasource": {"type": "prometheus", "uid": "prometheus"},
+      "targets": [
+        {
+          "expr": "rate(redpanda_kafka_requests_total[1m])",
+          "legendFormat": "{{method}} - {{topic}}"
+        }
+      ],
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 1}
+    },
+    {
+      "title": "Under-Replicated Partitions",
+      "type": "stat",
+      "datasource": {"type": "prometheus", "uid": "prometheus"},
+      "targets": [
+        {
+          "expr": "redpanda_cluster_under_replicated_partitions",
+          "legendFormat": "Under-Replicated"
+        }
+      ],
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 1}
+    },
+    {
+      "title": "Producer Latency (p99)",
+      "type": "timeseries",
+      "datasource": {"type": "prometheus", "uid": "prometheus"},
+      "targets": [
+        {
+          "expr": "histogram_quantile(0.99, rate(redpanda_kafka_produce_latency_seconds_bucket[5m]))",
+          "legendFormat": "p99 Latency"
+        }
+      ],
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 9}
+    },
+    {
+      "title": "Consumer Fetch Latency (p99)",
+      "type": "timeseries",
+      "datasource": {"type": "prometheus", "uid": "prometheus"},
+      "targets": [
+        {
+          "expr": "histogram_quantile(0.99, rate(redpanda_kafka_fetch_latency_seconds_bucket[5m]))",
+          "legendFormat": "p99 Latency"
+        }
+      ],
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 9}
+    },
+    {
+      "title": "Redpanda Resource Usage",
+      "type": "row",
+      "gridPos": {"h": 1, "w": 24, "x": 0, "y": 17}
+    },
+    {
+      "title": "Memory Usage",
+      "type": "timeseries",
+      "datasource": {"type": "prometheus", "uid": "prometheus"},
+      "targets": [
+        {
+          "expr": "redpanda_memory_allocated_bytes",
+          "legendFormat": "Allocated (bytes)"
+        }
+      ],
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 18}
+    },
+    {
+      "title": "CPU Usage",
+      "type": "timeseries",
+      "datasource": {"type": "prometheus", "uid": "prometheus"},
+      "targets": [
+        {
+          "expr": "rate(redpanda_cpu_busy_seconds_total[1m])",
+          "legendFormat": "CPU Busy Rate"
+        }
+      ],
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 18}
+    }
+  ],
+  "schemaVersion": 38,
+  "style": "dark",
+  "tags": ["redpanda", "kafka", "smart-city"],
+  "templating": {"list": []},
+  "time": {"from": "now-1h", "to": "now"},
+  "title": "Redpanda Metrics",
+  "uid": "redpanda-metrics",
+  "version": 1
+}