refactor(k8s): consolidate to infra/+apps/ single-source tree, dedicated per-app CNPG (authentik-db/temporal-db), wire monitoring-config, forgejo→cicd ns, drop orphan/stale (data-schemas, ollama, story-crater, sqs/argocd, key-rotation)

2026-08-18 15:08:03 -07:00
parent 54fa540b33
commit 41f5b05395
241 changed files with 467 additions and 10416 deletions
@@ -0,0 +1,141 @@
+# k8s/monitoring/dashboards/service-golden-signals.yaml
+# RED metrics (rate/errors/duration) for every service fronted by ingress-nginx.
+# Picked up automatically by Grafana's sidecar (grafana_dashboard=1 label) — see
+# sidecar.dashboards in k8s/logging/grafana-values.yaml.
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: service-golden-signals-dashboard
+  namespace: logging
+  labels:
+    grafana_dashboard: "1"
+data:
+  service-golden-signals.json: |
+    {
+      "title": "Latency & Golden Signals (Ingress RED)",
+      "uid": "svc-golden-signals",
+      "schemaVersion": 39,
+      "timezone": "browser",
+      "time": { "from": "now-6h", "to": "now" },
+      "refresh": "30s",
+      "templating": {
+        "list": [
+          {
+            "name": "ingress",
+            "type": "query",
+            "datasource": { "type": "prometheus", "uid": "prometheus" },
+            "query": "label_values(nginx_ingress_controller_requests, ingress)",
+            "refresh": 2,
+            "includeAll": false
+          }
+        ]
+      },
+      "panels": [
+        {
+          "id": 1,
+          "title": "Request rate by status — $ingress",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\"}[5m])) by (status)",
+              "legendFormat": "{{status}}"
+            }
+          ]
+        },
+        {
+          "id": 2,
+          "title": "Error rate % (4xx / 5xx) — $ingress",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "fieldConfig": { "defaults": { "unit": "percent" } },
+          "targets": [
+            {
+              "expr": "sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\", status=~\"5..\"}[5m])) / sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\"}[5m])) * 100",
+              "legendFormat": "5xx"
+            },
+            {
+              "expr": "sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\", status=~\"4..\"}[5m])) / sum(rate(nginx_ingress_controller_requests{ingress=\"$ingress\"}[5m])) * 100",
+              "legendFormat": "4xx"
+            }
+          ]
+        },
+        {
+          "id": 3,
+          "title": "Latency p50 / p95 / p99 — $ingress",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "fieldConfig": { "defaults": { "unit": "s" } },
+          "targets": [
+            {
+              "expr": "histogram_quantile(0.50, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress=\"$ingress\"}[5m])) by (le))",
+              "legendFormat": "p50"
+            },
+            {
+              "expr": "histogram_quantile(0.95, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress=\"$ingress\"}[5m])) by (le))",
+              "legendFormat": "p95"
+            },
+            {
+              "expr": "histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{ingress=\"$ingress\"}[5m])) by (le))",
+              "legendFormat": "p99"
+            }
+          ]
+        },
+        {
+          "id": 4,
+          "title": "All services — traffic overview",
+          "type": "table",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "topk(11, sum(rate(nginx_ingress_controller_requests[5m])) by (ingress))",
+              "format": "table",
+              "instant": true
+            }
+          ]
+        },
+        {
+          "id": 5,
+          "title": "Customer-facing failures (5xx count, window total)",
+          "type": "stat",
+          "gridPos": { "h": 5, "w": 12, "x": 0, "y": 16 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "fieldConfig": {
+            "defaults": {
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  { "value": 0, "color": "green" },
+                  { "value": 1, "color": "yellow" },
+                  { "value": 50, "color": "red" }
+                ]
+              }
+            }
+          },
+          "targets": [
+            {
+              "expr": "sum(increase(nginx_ingress_controller_requests{status=~\"5..\"}[$__range])) OR on() vector(0)",
+              "legendFormat": "5xx total"
+            }
+          ]
+        },
+        {
+          "id": 6,
+          "title": "Top 5 error-contributing services",
+          "type": "table",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 16 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "targets": [
+            {
+              "expr": "topk(5, sum(rate(nginx_ingress_controller_requests{status=~\"5..\"}[5m])) by (ingress))",
+              "format": "table",
+              "instant": true
+            }
+          ]
+        }
+      ]
+    }