feat: split Grafana dashboards into per-folder ConfigMaps

Replace monolithic dashboards-configmap.yaml with 10 dedicated files, one per Grafana folder: Ingress, Observability, Infrastructure, Storage, Identity, DevTools, Search, Media, La Suite, Communications. New dashboards for Longhorn, PostgreSQL/CNPG, Cert-Manager, SeaweedFS, Hydra, Kratos, Gitea, OpenSearch, LiveKit, La Suite golden signals (Linkerd metrics), Matrix, and Email Pipeline.
2026-03-24 12:20:42 +00:00
parent 234fe72707
commit 74bb59cfdc
11 changed files with 1418 additions and 247 deletions
--- a/base/monitoring/dashboards-ingress.yaml
+++ b/base/monitoring/dashboards-ingress.yaml
@@ -0,0 +1,135 @@
+# Grafana dashboard ConfigMaps — Ingress
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-dashboard-pingora
+  namespace: monitoring
+  labels:
+    grafana_dashboard: "1"
+  annotations:
+    grafana_folder: "Ingress"
+data:
+  pingora.json: |
+    {
+      "annotations": { "list": [] },
+      "editable": true,
+      "fiscalYearStartMonth": 0,
+      "graphTooltip": 1,
+      "links": [],
+      "panels": [
+        {
+          "title": "Requests / sec",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
+          "datasource": { "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "sum(rate(pingora_http_requests_total[5m]))",
+              "legendFormat": "total"
+            },
+            {
+              "expr": "sum(rate(pingora_http_requests_total[5m])) by (status_code)",
+              "legendFormat": "{{status_code}}"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": { "unit": "reqps" }
+          }
+        },
+        {
+          "title": "Error Rate (5xx)",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
+          "datasource": { "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "sum(rate(pingora_http_requests_total{status_code=~\"5..\"}[5m])) / sum(rate(pingora_http_requests_total[5m]))",
+              "legendFormat": "5xx ratio"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": { "unit": "percentunit", "max": 1, "thresholds": { "steps": [{"color":"green","value":null},{"color":"yellow","value":0.01},{"color":"red","value":0.05}] } }
+          }
+        },
+        {
+          "title": "Request Latency (p50 / p95 / p99)",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
+          "datasource": { "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "histogram_quantile(0.50, sum(rate(pingora_http_request_duration_seconds_bucket[5m])) by (le))",
+              "legendFormat": "p50"
+            },
+            {
+              "expr": "histogram_quantile(0.95, sum(rate(pingora_http_request_duration_seconds_bucket[5m])) by (le))",
+              "legendFormat": "p95"
+            },
+            {
+              "expr": "histogram_quantile(0.99, sum(rate(pingora_http_request_duration_seconds_bucket[5m])) by (le))",
+              "legendFormat": "p99"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": { "unit": "s" }
+          }
+        },
+        {
+          "title": "Active Connections",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
+          "datasource": { "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "pingora_active_connections",
+              "legendFormat": "active"
+            }
+          ]
+        },
+        {
+          "title": "Upstream Latency by Backend",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 0, "y": 16 },
+          "datasource": { "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "histogram_quantile(0.95, sum(rate(pingora_upstream_duration_seconds_bucket[5m])) by (le, backend))",
+              "legendFormat": "{{backend}} p95"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": { "unit": "s" }
+          }
+        },
+        {
+          "title": "DDoS / Scanner Detections",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 16 },
+          "datasource": { "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "sum(rate(pingora_ddos_detections_total[5m]))",
+              "legendFormat": "DDoS"
+            },
+            {
+              "expr": "sum(rate(pingora_scanner_detections_total[5m]))",
+              "legendFormat": "Scanner"
+            },
+            {
+              "expr": "sum(rate(pingora_rate_limit_rejected_total[5m]))",
+              "legendFormat": "Rate-limited"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": { "unit": "reqps" }
+          }
+        }
+      ],
+      "schemaVersion": 39,
+      "tags": ["ingress", "pingora"],
+      "templating": { "list": [] },
+      "time": { "from": "now-1h", "to": "now" },
+      "title": "Pingora Proxy",
+      "uid": "pingora-proxy"
+    }