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 +1,121 @@
+# k8s/monitoring/dashboards/hardware-overview.yaml
+# Trimmed operator at-a-glance view across all nodes — node-exporter already
+# powers the deep-dive "Node Exporter Full" (#1860, see grafana-values.yaml),
+# this is the quick health-check version, not a replacement for it.
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: hardware-overview-dashboard
+  namespace: logging
+  labels:
+    grafana_dashboard: "1"
+data:
+  hardware-overview.json: |
+    {
+      "title": "Hardware Statistics (Operator Overview)",
+      "uid": "hardware-overview",
+      "schemaVersion": 39,
+      "timezone": "browser",
+      "time": { "from": "now-6h", "to": "now" },
+      "refresh": "30s",
+      "panels": [
+        {
+          "id": 1,
+          "title": "Nodes up / down",
+          "type": "stat",
+          "gridPos": { "h": 5, "w": 24, "x": 0, "y": 0 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "fieldConfig": {
+            "defaults": {
+              "mappings": [
+                { "type": "value", "options": { "0": { "text": "DOWN", "color": "red" } } },
+                { "type": "value", "options": { "1": { "text": "UP", "color": "green" } } }
+              ]
+            }
+          },
+          "targets": [
+            { "expr": "up{job=~\".*node-exporter.*\"}", "legendFormat": "{{instance}}" }
+          ]
+        },
+        {
+          "id": 2,
+          "title": "CPU usage % by node",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 0, "y": 5 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "fieldConfig": { "defaults": { "unit": "percent", "max": 100, "min": 0 } },
+          "targets": [
+            {
+              "expr": "(1 - avg(rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) by (instance)) * 100",
+              "legendFormat": "{{instance}}"
+            }
+          ]
+        },
+        {
+          "id": 3,
+          "title": "Memory usage % by node",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 5 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "fieldConfig": { "defaults": { "unit": "percent", "max": 100, "min": 0 } },
+          "targets": [
+            {
+              "expr": "(1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100",
+              "legendFormat": "{{instance}}"
+            }
+          ]
+        },
+        {
+          "id": 4,
+          "title": "Root filesystem usage % by node",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 0, "y": 13 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "fieldConfig": { "defaults": { "unit": "percent", "max": 100, "min": 0 } },
+          "targets": [
+            {
+              "expr": "(1 - node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"}) * 100",
+              "legendFormat": "{{instance}}"
+            }
+          ]
+        },
+        {
+          "id": 5,
+          "title": "Root filesystem space remaining",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 13 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "fieldConfig": { "defaults": { "unit": "bytes" } },
+          "targets": [
+            {
+              "expr": "node_filesystem_avail_bytes{mountpoint=\"/\"}",
+              "legendFormat": "{{instance}}"
+            }
+          ]
+        },
+        {
+          "id": 6,
+          "title": "Network errors/drops by node",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 0, "y": 21 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "targets": [
+            { "expr": "rate(node_network_receive_errs_total[5m])", "legendFormat": "{{instance}} rx errs" },
+            { "expr": "rate(node_network_transmit_errs_total[5m])", "legendFormat": "{{instance}} tx errs" },
+            { "expr": "rate(node_network_receive_drop_total[5m])", "legendFormat": "{{instance}} rx drops" },
+            { "expr": "rate(node_network_transmit_drop_total[5m])", "legendFormat": "{{instance}} tx drops" }
+          ]
+        },
+        {
+          "id": 7,
+          "title": "Load average (1m / 5m) by node",
+          "type": "timeseries",
+          "gridPos": { "h": 8, "w": 12, "x": 12, "y": 21 },
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "targets": [
+            { "expr": "node_load1", "legendFormat": "{{instance}} load1" },
+            { "expr": "node_load5", "legendFormat": "{{instance}} load5" }
+          ]
+        }
+      ]
+    }