feat(observability): ✨ add dashboards, scrape configs, and fix victoria-logs to template

Add new Grafana dashboard CRs to grafana-operator/manifests: - platform-overview, forgejo, argocd-operational, cronjob-monitoring Fix victoria-logs dashboard to use grafana.com marketplace (id: 22698) instead of raw GitHub URL Add hub-side scrape configs to victoria-k8s-stack/manifests: - argocd-scrape, garm-scrape, coredns-scrape, ci-sustainability-rules Add client-side forgejo VMServiceScrape to observability-client/vm-client-stack/manifests Enable ArgoCD metrics endpoints in core/argocd/values.yaml (required by argocd-scrape)
2026-06-19 12:58:06 +02:00 · 2026-06-19 12:58:06 +02:00 · 3bc8a7444b
commit 3bc8a7444b
parent 69e4d1b3dc
11 changed files with 587 additions and 1 deletions
--- a/template/stacks/core/argocd/values.yaml
+++ b/template/stacks/core/argocd/values.yaml
@ -40,3 +40,19 @@ notifications:

 dex:
  enabled: false
+
+controller:
+  metrics:
+    enabled: true
+
+server:
+  metrics:
+    enabled: true
+
+repoServer:
+  metrics:
+    enabled: true
+
+applicationSet:
+  metrics:
+    enabled: true
--- a/template/stacks/observability-client/vm-client-stack/manifests/forgejo-scrape.yaml
+++ b/template/stacks/observability-client/vm-client-stack/manifests/forgejo-scrape.yaml
@ -0,0 +1,15 @@
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMServiceScrape
+metadata:
+  name: forgejo
+  namespace: observability
+spec:
+  namespaceSelector:
+    matchNames:
+      - gitea
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: forgejo
+  endpoints:
+    - port: http
+      path: /metrics
--- a/template/stacks/observability/grafana-operator/manifests/argocd-operational.yaml
+++ b/template/stacks/observability/grafana-operator/manifests/argocd-operational.yaml
@ -0,0 +1,11 @@
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: argocd-operational
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  grafanaCom:
+    id: 19993
+    revision: 2
--- a/template/stacks/observability/grafana-operator/manifests/cronjob-monitoring.yaml
+++ b/template/stacks/observability/grafana-operator/manifests/cronjob-monitoring.yaml
@ -0,0 +1,11 @@
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: cronjob-monitoring
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  grafanaCom:
+    id: 14279
+    revision: 1
--- a/template/stacks/observability/grafana-operator/manifests/forgejo.yaml
+++ b/template/stacks/observability/grafana-operator/manifests/forgejo.yaml
@ -0,0 +1,184 @@
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: forgejo
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  json: |
+    {
+      "annotations": {"list": []},
+      "editable": true,
+      "graphTooltip": 1,
+      "panels": [
+        {
+          "collapsed": false,
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 0},
+          "title": "Forgejo Health",
+          "type": "row"
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"mappings": [{"options": {"0": {"text": "DOWN", "color": "red"}, "1": {"text": "UP", "color": "green"}}, "type": "value"}], "thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]}}},
+          "gridPos": {"h": 4, "w": 4, "x": 0, "y": 1},
+          "title": "Status",
+          "type": "stat",
+          "targets": [{"expr": "up{job=\"forgejo-server-http\", cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 4, "y": 1},
+          "title": "Version",
+          "type": "stat",
+          "targets": [{"expr": "gitea_build_info{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{version}}"}],
+          "options": {"reduceOptions": {"calcs": ["lastNotNull"]}, "textMode": "name"}
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 8, "y": 1},
+          "title": "Repositories",
+          "type": "stat",
+          "targets": [{"expr": "gitea_repositories{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 12, "y": 1},
+          "title": "Users",
+          "type": "stat",
+          "targets": [{"expr": "gitea_users{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 16, "y": 1},
+          "title": "Organizations",
+          "type": "stat",
+          "targets": [{"expr": "gitea_organizations{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 20, "y": 1},
+          "title": "Teams",
+          "type": "stat",
+          "targets": [{"expr": "gitea_teams{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "collapsed": false,
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 5},
+          "title": "Activity",
+          "type": "row"
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 6, "x": 0, "y": 6},
+          "title": "Open Issues",
+          "type": "stat",
+          "targets": [{"expr": "gitea_issues_open{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 6, "x": 6, "y": 6},
+          "title": "Closed Issues",
+          "type": "stat",
+          "targets": [{"expr": "gitea_issues_closed{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 6, "x": 12, "y": 6},
+          "title": "Webhooks",
+          "type": "stat",
+          "targets": [{"expr": "gitea_webhooks{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 6, "x": 18, "y": 6},
+          "title": "Hook Tasks",
+          "type": "stat",
+          "targets": [{"expr": "gitea_hooktasks{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "collapsed": false,
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 10},
+          "title": "Content & Auth",
+          "type": "row"
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 0, "y": 11},
+          "title": "Stars",
+          "type": "stat",
+          "targets": [{"expr": "gitea_stars{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 4, "y": 11},
+          "title": "Watches",
+          "type": "stat",
+          "targets": [{"expr": "gitea_watches{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 8, "y": 11},
+          "title": "Releases",
+          "type": "stat",
+          "targets": [{"expr": "gitea_releases{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 12, "y": 11},
+          "title": "Mirrors",
+          "type": "stat",
+          "targets": [{"expr": "gitea_mirrors{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 16, "y": 11},
+          "title": "Public Keys",
+          "type": "stat",
+          "targets": [{"expr": "gitea_publickeys{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 20, "y": 11},
+          "title": "OAuth Apps",
+          "type": "stat",
+          "targets": [{"expr": "gitea_oauths{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        }
+      ],
+      "schemaVersion": 39,
+      "tags": ["edp", "forgejo", "gitea"],
+      "templating": {
+        "list": [
+          {
+            "current": {"selected": true, "text": "All", "value": "$__all"},
+            "datasource": {"type": "prometheus"},
+            "definition": "label_values(gitea_repositories, cluster_environment)",
+            "includeAll": true,
+            "multi": true,
+            "name": "cluster_environment",
+            "label": "Environment",
+            "query": "label_values(gitea_repositories, cluster_environment)",
+            "refresh": 2,
+            "type": "query"
+          }
+        ]
+      },
+      "time": {"from": "now-6h", "to": "now"},
+      "title": "Forgejo",
+      "uid": "edp-forgejo"
+    }
--- a/template/stacks/observability/grafana-operator/manifests/platform-overview.yaml
+++ b/template/stacks/observability/grafana-operator/manifests/platform-overview.yaml
@ -0,0 +1,230 @@
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: platform-overview
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  json: |
+    {
+      "annotations": {"list": []},
+      "editable": true,
+      "fiscalYearStartMonth": 0,
+      "graphTooltip": 1,
+      "links": [],
+      "panels": [
+        {
+          "collapsed": false,
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 0},
+          "title": "Platform Health",
+          "type": "row"
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {
+            "defaults": {
+              "mappings": [{"options": {"0": {"text": "DOWN", "color": "red"}, "1": {"text": "UP", "color": "green"}}, "type": "value"}],
+              "thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]}
+            }
+          },
+          "gridPos": {"h": 4, "w": 4, "x": 0, "y": 1},
+          "title": "Forgejo",
+          "type": "stat",
+          "targets": [{"expr": "sum(up{job=\"forgejo-server-http\", cluster_environment=~\"$cluster_environment\"})", "legendFormat": ""}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {
+            "defaults": {
+              "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 1}, {"color": "red", "value": 3}]}
+            }
+          },
+          "gridPos": {"h": 4, "w": 4, "x": 4, "y": 1},
+          "title": "Ingress 5xx (5m)",
+          "type": "stat",
+          "targets": [{"expr": "sum(rate(nginx_ingress_controller_requests{status=~\"5..\", cluster_environment=~\"$cluster_environment\"}[5m]))", "legendFormat": ""}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "short",
+              "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "red", "value": 1}]}
+            }
+          },
+          "gridPos": {"h": 4, "w": 4, "x": 8, "y": 1},
+          "title": "Failed Jobs (24h)",
+          "type": "stat",
+          "targets": [{"expr": "sum(kube_job_status_failed{namespace=\"gitea\", cluster_environment=~\"$cluster_environment\"}) or vector(0)", "legendFormat": ""}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percentunit",
+              "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 0.7}, {"color": "red", "value": 0.85}]}
+            }
+          },
+          "gridPos": {"h": 4, "w": 4, "x": 12, "y": 1},
+          "title": "Cluster CPU Usage",
+          "type": "stat",
+          "targets": [{"expr": "1 - avg(rate(node_cpu_seconds_total{mode=\"idle\", cluster_environment=~\"$cluster_environment\"}[5m]))", "legendFormat": ""}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percentunit",
+              "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 0.7}, {"color": "red", "value": 0.85}]}
+            }
+          },
+          "gridPos": {"h": 4, "w": 4, "x": 16, "y": 1},
+          "title": "Cluster Memory Usage",
+          "type": "stat",
+          "targets": [{"expr": "1 - sum(node_memory_MemAvailable_bytes{cluster_environment=~\"$cluster_environment\"}) / sum(node_memory_MemTotal_bytes{cluster_environment=~\"$cluster_environment\"})", "legendFormat": ""}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percentunit",
+              "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 0.6}, {"color": "red", "value": 0.8}]}
+            }
+          },
+          "gridPos": {"h": 4, "w": 4, "x": 20, "y": 1},
+          "title": "Max PVC Usage",
+          "type": "stat",
+          "targets": [{"expr": "max(1 - kubelet_volume_stats_available_bytes{cluster_environment=~\"$cluster_environment\"} / kubelet_volume_stats_capacity_bytes{cluster_environment=~\"$cluster_environment\"})", "legendFormat": ""}]
+        },
+        {
+          "collapsed": false,
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 5},
+          "title": "Forgejo",
+          "type": "row"
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 0, "y": 6},
+          "title": "Repositories",
+          "type": "stat",
+          "targets": [{"expr": "gitea_repositories{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 4, "y": 6},
+          "title": "Users",
+          "type": "stat",
+          "targets": [{"expr": "gitea_users{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 8, "y": 6},
+          "title": "Organizations",
+          "type": "stat",
+          "targets": [{"expr": "gitea_organizations{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 12, "y": 6},
+          "title": "Open Issues",
+          "type": "stat",
+          "targets": [{"expr": "gitea_issues_open{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 16, "y": 6},
+          "title": "Webhooks",
+          "type": "stat",
+          "targets": [{"expr": "gitea_webhooks{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "short"}},
+          "gridPos": {"h": 4, "w": 4, "x": 20, "y": 6},
+          "title": "Mirrors",
+          "type": "stat",
+          "targets": [{"expr": "gitea_mirrors{cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cluster_environment}}"}]
+        },
+        {
+          "collapsed": false,
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 10},
+          "title": "Resources",
+          "type": "row"
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "percentunit", "min": 0, "max": 1}},
+          "gridPos": {"h": 8, "w": 12, "x": 0, "y": 11},
+          "title": "Node CPU Usage",
+          "type": "timeseries",
+          "targets": [{"expr": "1 - rate(node_cpu_seconds_total{mode=\"idle\", cluster_environment=~\"$cluster_environment\"}[5m])", "legendFormat": "{{instance}}"}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "percentunit", "min": 0, "max": 1}},
+          "gridPos": {"h": 8, "w": 12, "x": 12, "y": 11},
+          "title": "PVC Usage by Claim",
+          "type": "timeseries",
+          "targets": [{"expr": "1 - (kubelet_volume_stats_available_bytes{cluster_environment=~\"$cluster_environment\"} / kubelet_volume_stats_capacity_bytes{cluster_environment=~\"$cluster_environment\"})", "legendFormat": "{{namespace}}/{{persistentvolumeclaim}}"}]
+        },
+        {
+          "collapsed": false,
+          "gridPos": {"h": 1, "w": 24, "x": 0, "y": 19},
+          "title": "Backups",
+          "type": "row"
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "s", "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "yellow", "value": 86400}, {"color": "red", "value": 172800}]}}},
+          "gridPos": {"h": 4, "w": 8, "x": 0, "y": 20},
+          "title": "Time Since Last Backup Schedule",
+          "type": "stat",
+          "targets": [{"expr": "time() - kube_cronjob_status_last_schedule_time{cronjob=~\"forgejo-s3-backup|secrets-backup\", cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{cronjob}} ({{cluster_environment}})"}]
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "s"}},
+          "gridPos": {"h": 4, "w": 8, "x": 8, "y": 20},
+          "title": "Backup Job Duration (Last 7d)",
+          "type": "timeseries",
+          "targets": [{"expr": "kube_job_status_completion_time{job_name=~\"forgejo-s3-backup.*|secrets-backup.*\", cluster_environment=~\"$cluster_environment\"} - kube_job_status_start_time{job_name=~\"forgejo-s3-backup.*|secrets-backup.*\", cluster_environment=~\"$cluster_environment\"}", "legendFormat": "{{job_name}}"}],
+          "options": {"legend": {"displayMode": "table"}}
+        },
+        {
+          "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+          "fieldConfig": {"defaults": {"unit": "short", "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}, {"color": "red", "value": 1}]}}},
+          "gridPos": {"h": 4, "w": 8, "x": 16, "y": 20},
+          "title": "Failed Backup Jobs (Active)",
+          "type": "stat",
+          "targets": [{"expr": "sum by(cluster_environment, job_name) (kube_job_status_failed{job_name=~\"forgejo-s3-backup.*|secrets-backup.*\", cluster_environment=~\"$cluster_environment\"})", "legendFormat": "{{job_name}} ({{cluster_environment}})"}]
+        }
+      ],
+      "schemaVersion": 39,
+      "tags": ["edp", "platform", "overview"],
+      "templating": {
+        "list": [
+          {
+            "current": {"selected": true, "text": "All", "value": "$__all"},
+            "datasource": {"type": "prometheus", "uid": "${DS_VICTORIAMETRICS}"},
+            "definition": "label_values(up, cluster_environment)",
+            "includeAll": true,
+            "multi": true,
+            "name": "cluster_environment",
+            "label": "Environment",
+            "query": "label_values(up, cluster_environment)",
+            "refresh": 2,
+            "sort": 1,
+            "type": "query"
+          }
+        ]
+      },
+      "time": {"from": "now-6h", "to": "now"},
+      "title": "EDP Platform Overview",
+      "uid": "edp-platform-overview"
+    }
--- a/template/stacks/observability/grafana-operator/manifests/victoria-logs.yaml
+++ b/template/stacks/observability/grafana-operator/manifests/victoria-logs.yaml
@ -6,4 +6,6 @@ spec:
  instanceSelector:
    matchLabels:
      dashboards: "grafana"
-  url: "https://raw.githubusercontent.com/VictoriaMetrics/VictoriaMetrics/refs/heads/master/dashboards/vm/victorialogs.json"
+  grafanaCom:
+    id: 22698
+    revision: 1
--- a/template/stacks/observability/victoria-k8s-stack/manifests/argocd-scrape.yaml
+++ b/template/stacks/observability/victoria-k8s-stack/manifests/argocd-scrape.yaml
@ -0,0 +1,13 @@
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMServiceScrape
+metadata:
+  name: argocd
+spec:
+  namespaceSelector:
+    matchNames:
+      - argocd
+  selector:
+    matchLabels:
+      app.kubernetes.io/part-of: argocd
+  endpoints:
+    - port: http-metrics
--- a/template/stacks/observability/victoria-k8s-stack/manifests/ci-sustainability-rules.yaml
+++ b/template/stacks/observability/victoria-k8s-stack/manifests/ci-sustainability-rules.yaml
@ -0,0 +1,61 @@
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMRule
+metadata:
+  name: ci-sustainability
+spec:
+  groups:
+    - name: ci.sustainability.daily
+      interval: 5m
+      rules:
+        - record: ci:cpu_seconds:increase1d
+          expr: |
+            sum by(namespace, cluster) (
+              increase(container_cpu_usage_seconds_total{
+                namespace=~"gitea|garm",
+                pod=~"forgejo-runner.*|garm-.*",
+                container!=""
+              }[1d])
+            )
+        - record: ci:memory_bytes_seconds:avg1d
+          expr: |
+            avg_over_time(
+              sum by(namespace, cluster) (
+                container_memory_working_set_bytes{
+                  namespace=~"gitea|garm",
+                  pod=~"forgejo-runner.*|garm-.*",
+                  container!=""
+                }
+              )[1d:5m]
+            )
+        - record: ci:pod_count:avg1d
+          expr: |
+            avg_over_time(
+              count by(namespace, cluster) (
+                kube_pod_info{
+                  namespace=~"gitea|garm",
+                  pod=~"forgejo-runner.*|garm-.*"
+                }
+              )[1d:5m]
+            )
+        - record: ci:pod_creations:increase1d
+          expr: |
+            sum by(namespace, cluster) (
+              changes(kube_pod_start_time{
+                namespace=~"gitea|garm",
+                pod=~"forgejo-runner.*|garm-.*"
+              }[1d])
+            )
+    - name: ci.sustainability.cluster
+      interval: 5m
+      rules:
+        - record: cluster:cpu_seconds:rate5m
+          expr: |
+            sum by(cluster) (
+              rate(node_cpu_seconds_total{mode!="idle"}[5m])
+            )
+        - record: cluster:memory_used_bytes:sum
+          expr: |
+            sum by(cluster) (
+              node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes
+            )
+
--- a/template/stacks/observability/victoria-k8s-stack/manifests/coredns-scrape.yaml
+++ b/template/stacks/observability/victoria-k8s-stack/manifests/coredns-scrape.yaml
@ -0,0 +1,30 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: coredns-metrics
+  namespace: kube-system
+  labels:
+    k8s-app: coredns-metrics
+spec:
+  clusterIP: None
+  selector:
+    k8s-app: coredns
+  ports:
+    - name: metrics
+      port: 9153
+      targetPort: 9153
+      protocol: TCP
+---
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMServiceScrape
+metadata:
+  name: coredns
+spec:
+  namespaceSelector:
+    matchNames:
+      - kube-system
+  selector:
+    matchLabels:
+      k8s-app: coredns-metrics
+  endpoints:
+    - port: metrics
--- a/template/stacks/observability/victoria-k8s-stack/manifests/garm-scrape.yaml
+++ b/template/stacks/observability/victoria-k8s-stack/manifests/garm-scrape.yaml
@ -0,0 +1,13 @@
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMServiceScrape
+metadata:
+  name: garm
+spec:
+  namespaceSelector:
+    matchNames:
+      - garm
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: garm
+  endpoints:
+    - port: http