feat(monitoring): add Prometheus metrics endpoint and Grafana dashboards

Add observability stack with @willsoto/nestjs-prometheus for /metrics endpoint, Prometheus scraping config, and 4 auto-provisioned Grafana dashboards (API overview, database, search, business metrics). Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-04-08 03:08:54 +07:00
parent b392bc3570
commit d99dfbafbc
13 changed files with 770 additions and 2 deletions
--- a/monitoring/grafana/dashboards/database.json
+++ b/monitoring/grafana/dashboards/database.json
@@ -0,0 +1,108 @@
+{
+  "annotations": { "list": [] },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "links": [],
+  "panels": [
+    {
+      "title": "Query Latency (p50 / p95 / p99)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
+      "targets": [
+        {
+          "expr": "histogram_quantile(0.50, sum(rate(db_query_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "p50",
+          "refId": "A"
+        },
+        {
+          "expr": "histogram_quantile(0.95, sum(rate(db_query_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "p95",
+          "refId": "B"
+        },
+        {
+          "expr": "histogram_quantile(0.99, sum(rate(db_query_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "p99",
+          "refId": "C"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s",
+          "custom": { "drawStyle": "line", "fillOpacity": 10 }
+        }
+      }
+    },
+    {
+      "title": "Query Rate by Operation",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
+      "targets": [
+        {
+          "expr": "sum(rate(db_query_duration_seconds_count[5m])) by (operation)",
+          "legendFormat": "{{operation}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": { "drawStyle": "bars", "fillOpacity": 50 }
+        }
+      }
+    },
+    {
+      "title": "Active DB Connections",
+      "type": "gauge",
+      "gridPos": { "h": 8, "w": 8, "x": 0, "y": 8 },
+      "targets": [
+        {
+          "expr": "db_pool_active_connections",
+          "legendFormat": "Active",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 15 },
+              { "color": "red", "value": 25 }
+            ]
+          },
+          "max": 30
+        }
+      }
+    },
+    {
+      "title": "Slow Queries (> 100ms)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 16, "x": 8, "y": 8 },
+      "targets": [
+        {
+          "expr": "sum(rate(db_query_duration_seconds_bucket{le=\"0.1\"}[5m])) / sum(rate(db_query_duration_seconds_count[5m]))",
+          "legendFormat": "% queries < 100ms",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percentunit",
+          "min": 0,
+          "max": 1,
+          "custom": { "drawStyle": "line", "fillOpacity": 10 }
+        }
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["goodgo", "database"],
+  "templating": { "list": [] },
+  "time": { "from": "now-1h", "to": "now" },
+  "timepicker": {},
+  "timezone": "browser",
+  "title": "GoodGo Database",
+  "uid": "goodgo-database",
+  "version": 1
+}