Merge branch 'automated-tasks' into 'development'

chore(gitlab-ci): Automated update of git sub-module

See merge request nofusscomputing/projects/kubernetes_monitoring!28

.cz.yaml

@@ -4,4 +4,4 @@ commitizen:
   name: cz_conventional_commits
   tag_format: $major.$minor.$patch$prerelease
   update_changelog_on_bump: true
-  version: 0.1.0
+  version: 0.2.0

.nfc_automation.yaml

@@ -0,0 +1,10 @@
+---
+
+role_git_conf:
+  gitlab:
+    submodule_branch: "development"
+    default_branch: development
+    mr_labels: ~"type::automation" ~"impact::0" ~"priority::0"
+    auto_merge: true
+    merge_request:
+      patch_labels: '~"code review::not started"'

CHANGELOG.md

@@ -1,3 +1,39 @@
+## 0.2.0 (2023-11-19)
+
+### Bug Fixes
+
+- **ingress**: [11563741](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/11563741a90dc81ddf043cc529fa13916bee9082) - underscore removed from ingress name [ [!5](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/5) [!3](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/3) ]
+- **ingress**: [33883ec6](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/33883ec64025d8a2ab81fec50019d2605776ea07) - function bool not defined [ [!5](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/5) [!3](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/3) ]
+- **grafana**: [593d73e4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/593d73e4c6e5c029d592adc8af5173c92d6a6fb0) - PVC access mode default to ReadWriteOnce [ [!5](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/5) [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **prometheus**: [b6d0b18e](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/b6d0b18ece17dcd2733c6892cba7e8e83575fab0) - use correct variable for storage values [ [!5](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/5) [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+
+### Features
+
+- **prometheus**: [562bb7d6](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/562bb7d6f57f52b3cf4fcaf19a15a8eed492d15e) - added config for ingress [ [!5](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/5) [!3](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/3) ]
+- **grafana**: [26a78bdb](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/26a78bdb3373cbed1d78785ded47e3dfae28c853) - added config for ingress [ [!5](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/5) [!3](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/3) ]
+- **alert_manager**: [65534660](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/65534660dda9b10761bf6067abc3297bec75a182) - added config for ingress [ [!5](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/5) [!3](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/3) ]
+
+## 0.2.0rc0 (2023-11-06)
+
+### Code Refactor
+
+- **grafana_datasources**: [cf38a415](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/cf38a4156adcbdda150fe309f1f7dd97a5a3bf07) - default prom set to thanos [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+
+### Features
+
+- **Grafana**: [b047f33e](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/b047f33e275d2e908f7e8a220944573f2e367bf7) - Configure grafana from values.yaml [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **GrafanaAgent**: [0c296c17](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/0c296c173e786c77504fabba337b464bcde6c290) - Network Policy added [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **grafana**: [7164bb2e](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/7164bb2e0b5f2c5e7fb59bcb64321eabb651b08e) - Network Policy added [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **prometheus**: [ae35e704](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/ae35e704e33bee4d2fea3390a7965a087e30acce) - Network Policy added [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **NetworkPolicy**: [5c62055d](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/5c62055d2f2041b33a2ab5ff8023cf8bd6b08df1) - configure from values.yaml [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **labels**: [03affbee](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/03affbee809d9e36f0930ae49ab07191e2b645a2) - lables moved to values.yaml [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **graph**: [65b61ecf](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/65b61ecf545800bcbf4efc7e3175951b9c6d2965) - add ceph size/used to dashboard [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **prometheus**: [7afc6aa5](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/7afc6aa515db4a43ce8dc1a152f45f400fc68a39) - rule selector configurable from values.yaml [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **promtail**: [2371adcb](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/2371adcbc5d64a27ff72b0ac45f589ccef4eb400) - split node to seperate promtail service monitor [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **grafana_agent**: [f73a9e46](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/f73a9e462e16dffbc0e17eaed3c0c78aff95d52b) - add prom rules [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **prometheus**: [5bb71971](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/5bb71971292b8f760e9b348652dc9df3c0dfa921) - tsdb retention set [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+- **thanos**: [be016187](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/commit/be0161876d6b6868204af06255a01f08cc62c6ea) - prometheus rules added for sidecar [ [!4](https://gitlab.com/nofusscomputing/projects/kubernetes_monitoring/-/merge_requests/4) ]
+
 ## 0.1.0 (2023-09-27)
 
 ### Bug Fixes

docs/projects/kubernetes_monitoring/index.md

@@ -113,6 +113,8 @@ This helm chart started off with components from multiple open-source projects.
 
     - Prometheus-Adaptor
 
+    - Promtail
+
     - Thanos
 
 - kyverno policies _(optional, set in values.yaml)_

files/dashboard-summary.json

@@ -18,7 +18,7 @@
   "editable": true,
   "fiscalYearStartMonth": 0,
   "graphTooltip": 0,
-  "id": 66,
+  "id": 68,
   "links": [],
   "liveNow": false,
   "panels": [
@@ -630,13 +630,107 @@
       "transparent": true,
       "type": "stat"
     },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${PROMETHEUS}"
+      },
+      "description": "How much is used and Size",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [
+            {
+              "options": {
+                "Size": {
+                  "color": "green",
+                  "index": 0
+                }
+              },
+              "type": "value"
+            }
+          ],
+          "min": 0,
+          "thresholds": {
+            "mode": "percentage",
+            "steps": [
+              {
+                "color": "#007d35",
+                "value": null
+              }
+            ]
+          },
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 5,
+        "x": 3,
+        "y": 8
+      },
+      "id": 19,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "area",
+        "justifyMode": "center",
+        "orientation": "vertical",
+        "reduceOptions": {
+          "calcs": [
+            "last"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.1.2",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "exemplar": false,
+          "expr": "sum(ceph_osd_stat_bytes_used)",
+          "format": "time_series",
+          "hide": false,
+          "instant": true,
+          "legendFormat": "Used",
+          "range": false,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "exemplar": false,
+          "expr": "sum(ceph_osd_stat_bytes)",
+          "format": "time_series",
+          "hide": false,
+          "instant": true,
+          "legendFormat": "Size",
+          "range": false,
+          "refId": "B"
+        }
+      ],
+      "title": "Storage",
+      "transformations": [],
+      "type": "stat"
+    },
     {
       "collapsed": false,
       "gridPos": {
         "h": 1,
         "w": 24,
         "x": 0,
-        "y": 11
+        "y": 12
       },
       "id": 2,
       "panels": [],
@@ -672,7 +766,7 @@
         "h": 3,
         "w": 4,
         "x": 0,
-        "y": 12
+        "y": 13
       },
       "id": 12,
       "options": {
@@ -743,7 +837,7 @@
         "h": 3,
         "w": 4,
         "x": 4,
-        "y": 12
+        "y": 13
       },
       "id": 17,
       "options": {
@@ -814,7 +908,7 @@
         "h": 3,
         "w": 4,
         "x": 8,
-        "y": 12
+        "y": 13
       },
       "id": 16,
       "options": {
@@ -884,7 +978,7 @@
         "h": 3,
         "w": 4,
         "x": 12,
-        "y": 12
+        "y": 13
       },
       "id": 13,
       "options": {
@@ -955,7 +1049,7 @@
         "h": 3,
         "w": 4,
         "x": 16,
-        "y": 12
+        "y": 13
       },
       "id": 18,
       "options": {
@@ -1027,7 +1121,7 @@
         "h": 3,
         "w": 4,
         "x": 20,
-        "y": 12
+        "y": 13
       },
       "id": 15,
       "options": {
@@ -1131,7 +1225,7 @@
         "h": 9,
         "w": 12,
         "x": 0,
-        "y": 15
+        "y": 16
       },
       "id": 1,
       "options": {
@@ -1225,7 +1319,7 @@
         "h": 9,
         "w": 12,
         "x": 12,
-        "y": 15
+        "y": 16
       },
       "id": 14,
       "options": {
@@ -1257,7 +1351,7 @@
       "type": "timeseries"
     }
   ],
-  "refresh": "5s",
+  "refresh": "10s",
   "schemaVersion": 38,
   "style": "dark",
   "tags": [
@@ -1269,9 +1363,9 @@
     "list": [
       {
         "current": {
-          "selected": true,
+          "selected": false,
-          "text": "prometheus",
+          "text": "thanos",
-          "value": "77e897ec-8a32-4b71-9439-8f12ec42e920"
+          "value": "603ac67d-7d32-4fba-8ec3-35106f3c4cc9"
         },
         "hide": 0,
         "includeAll": false,
@@ -1296,6 +1390,6 @@
   "timezone": "",
   "title": "Cluster Overview",
   "uid": "no-fuss-computing-k8s-overview",
-  "version": 4,
+  "version": 5,
   "weekStart": ""
 }

templates/APIService-prometheus-adapter.yaml

@@ -1,11 +1,12 @@
+{{ if false }}
+# already on k3s
 ---
 apiVersion: apiregistration.k8s.io/v1
 kind: APIService
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -19,3 +20,4 @@ spec:
     namespace: monitoring
   version: v1beta1
   versionPriority: 100
+{{ end }}

templates/AlertManager-k8s.yaml

@@ -3,13 +3,12 @@ apiVersion: monitoring.coreos.com/v1
 kind: Alertmanager
 metadata:
   labels:
-    app.kubernetes.io/instance: main
+    {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 4 }}
-    app.kubernetes.io/component: alert-router
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: alertmanager
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: main
+  name: {{ $.Release.Name }}
   namespace: {{ .Values.nfc_monitoring.alert_manager.namespace | quote }}
 spec:
   image: "{{ .Values.nfc_monitoring.alert_manager.image.name }}:{{ .Values.nfc_monitoring.alert_manager.image.tag }}"
@@ -18,12 +17,12 @@ spec:
   podMetadata:
     labels:
       app.kubernetes.io/component: alert-router
-      app.kubernetes.io/instance: main
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: alertmanager
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
       app.kubernetes.io/managed-by: {{ $.Release.Service }}
       app.kubernetes.io/version: {{ $.Chart.Version }}
-  replicas: 3
+  replicas: {{ .Values.nfc_monitoring.alert_manager.replicas }}
   resources:
     limits:
       cpu: 100m

templates/ClusterPolicy-Prometheus-Role.yaml

@@ -14,8 +14,8 @@ metadata:
       monitoring instances is created to enable monitoring of  the namespace in
       question.
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -33,14 +33,13 @@ spec:
         synchronize: true
         apiVersion: rbac.authorization.k8s.io/v1
         kind: Role
-        name: prometheus-k8s
+        name: prometheus-{{ $.Release.Name }}
         namespace: "{{ `{{` }}request.object.metadata.name }}"
         data:
           metadata:
             labels:
-              app.kubernetes.io/component: prometheus
+              {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 14 }}
-              app.kubernetes.io/instance: k8s
+              app.kubernetes.io/instance: {{ $.Release.Name }}
-              app.kubernetes.io/name: prometheus
               app.kubernetes.io/part-of: {{ $.Chart.Name }}
               app.kubernetes.io/version: {{ $.Chart.Version }}
             

templates/ClusterPolicy-Prometheus-RoleBinding.yaml

@@ -14,8 +14,8 @@ metadata:
       monitoring instances is created to enable monitoring of  the namespace in
       question.
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -33,21 +33,21 @@ spec:
         synchronize: true
         apiVersion: rbac.authorization.k8s.io/v1
         kind: RoleBinding
-        name: prometheus-k8s
+        name: prometheus-{{ $.Release.Name }}
         namespace: "{{ `{{` }}request.object.metadata.name }}"
         data:
           metadata:
             labels:
-              app.kubernetes.io/component: prometheus
+              {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 14 }}
-              app.kubernetes.io/name: prometheus
+              app.kubernetes.io/instance: {{ $.Release.Name }}
               app.kubernetes.io/part-of: {{ $.Chart.Name }}
               app.kubernetes.io/version: {{ $.Chart.Version }}
           roleRef:
             apiGroup: rbac.authorization.k8s.io
             kind: Role
-            name: prometheus-k8s
+            name: prometheus-{{ $.Release.Name }}
           subjects:
           - kind: ServiceAccount
-            name: prometheus-k8s
+            name: prometheus-{{ $.Release.Name }}
             namespace: "{{ .Values.nfc_monitoring.prometheus.namespace }}"
 {{ end }}

templates/ClusterRole-GrafanaAgent.yaml

@@ -4,9 +4,8 @@ kind: ClusterRole
 metadata:
   name: grafana-agent
   labels:
-    app.kubernetes.io/instance: k8s
+    {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 4 }}
-    app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana-agent
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ClusterRole-aggregated-metrics-reader.yaml

@@ -1,11 +1,11 @@
+{{ if false }}
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -24,3 +24,6 @@ rules:
   - get
   - list
   - watch
+
+# Already exists on k3s
+{{ end }}

templates/ClusterRole-binding-delegator-prometheus-adaptor.yaml

@@ -3,8 +3,8 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus-adapter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ClusterRole-binding-hpa-custom-metrics-prometheus-adaptor.yaml

@@ -4,8 +4,8 @@ kind: ClusterRoleBinding
 metadata:
   name: hpa-controller-custom-metrics
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus-adapter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ClusterRole-binding-prometheus.yaml

@@ -3,8 +3,8 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus-adapter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ClusterRole-grafana-SideCar.yaml

@@ -1,12 +1,12 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 {{ if .Values.nfc_monitoring.additions.dashboard_sidecar.enabled -}}
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -16,3 +16,4 @@ rules:
     resources: ["configmaps"]
     verbs: ["get", "watch", "list"]
 {{- end }}
+{{- end }}

templates/ClusterRole-kube-monitor-proxy.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
@@ -5,7 +6,7 @@ metadata:
   name: kube-monitor-proxy
   labels:
     app.kubernetes.io/component: proxy
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-monitor-proxy
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -19,3 +20,5 @@ rules:
   resources:
   - subjectaccessreviews
   verbs: ["create"]
+
+{{ end }}

templates/ClusterRole-kubeStateMetrics-1.yaml

@@ -1,10 +1,11 @@
+{{ if .Values.nfc_monitoring.kube_state_metrics.enabled }}
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   labels:
     app.kubernetes.io/component: exporter
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -18,3 +19,5 @@ subjects:
 - kind: ServiceAccount
   name: kube-state-metrics
   namespace: monitoring
+
+{{ end }}

templates/ClusterRole-kubeStateMetrics.yaml

@@ -1,10 +1,11 @@
+{{ if .Values.nfc_monitoring.kube_state_metrics.enabled }}
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   labels:
     app.kubernetes.io/component: exporter
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -130,3 +131,5 @@ rules:
   verbs:
   - list
   - watch
+
+{{ end }}

templates/ClusterRole-metrics-server-resources-prometheus-adaptor.yaml

@@ -3,8 +3,8 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus-adapter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ClusterRole-prometheus-adapter.yaml

@@ -3,9 +3,8 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ClusterRole-prometheus.yaml

@@ -3,13 +3,12 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
 rules:
 - apiGroups:
   - ""

templates/ClusterRoleBinding-Grafana-Agent.yaml

@@ -3,9 +3,8 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   labels:
-    app.kubernetes.io/instance: k8s
+    {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 4 }}
-    app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana-agent
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ClusterRoleBinding-Grafana-SideCar.yaml

@@ -1,12 +1,12 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 {{ if .Values.nfc_monitoring.additions.dashboard_sidecar.enabled -}}
 ---
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1
 metadata:
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -20,3 +20,4 @@ subjects:
     name: grafana
     namespace: "{{ .Values.nfc_monitoring.grafana.namespace }}"
 {{- end }}
+{{- end }}

templates/ClusterRoleBinding-kube-monitor-proxy.yaml

@@ -5,7 +5,7 @@ metadata:
   name: kube-monitor-proxy
   labels:
     app.kubernetes.io/component: proxy
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-monitor-proxy
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}

templates/ClusterRoleBinding-prometheus.yaml

@@ -3,18 +3,17 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
 subjects:
 - kind: ServiceAccount
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}

templates/ConfigMap-Grafana.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 ---
 apiVersion: v1
 kind: ConfigMap
@@ -5,9 +6,8 @@ metadata:
   name: grafana-config
   namespace: "{{ .Values.nfc_monitoring.grafana.namespace }}"
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -50,9 +50,7 @@ apiVersion: v1
 kind: ConfigMap
 metadata:
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -127,4 +125,4 @@ data:
       }
     }
 
----
+{{- end }}

templates/ConfigMap-GrafanaAgent.yaml

@@ -3,9 +3,8 @@ apiVersion: v1
 kind: ConfigMap
 metadata:
   labels:
-    app.kubernetes.io/instance: k8s
+    {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 4 }}
-    app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana-agent
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -16,6 +15,8 @@ data:
     metrics:
       wal_directory: /tmp/wal
 
+
+{{ if .Values.nfc_monitoring.loki.config }}
     logs:
       positions_directory: "/tmp"
 
@@ -234,7 +235,7 @@ data:
               - target_label: node
                 source_labels:
                   - __meta_kubernetes_pod_node_name
-
+{{ end }}
 
     integrations:
 
@@ -254,7 +255,6 @@ data:
         netclass_ignored_devices: "^(veth.*|cali.*|[a-f0-9]{15})$"
         netdev_device_exclude: "^(veth.*|cali.*|[a-f0-9]{15})$"
 
-        scrape_integration: true
 
         include_exporter_metrics: true
         enable_collectors:
@@ -263,6 +263,8 @@ data:
 
   syslog_server.yaml: |
     # REF: https://grafana.com/docs/loki/latest/send-data/promtail/configuration/#example-syslog-config
+    
+{{ if .Values.nfc_monitoring.loki.config }}
     server:
       http_listen_port: 9080
       grpc_listen_port: 0
@@ -282,3 +284,5 @@ data:
         relabel_configs:
           - source_labels: ['__syslog_message_hostname']
             target_label: 'host'
+{{ end }}
+

templates/ConfigMap-GrafanaProvisioning.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 {{ if .Values.nfc_monitoring.additions.dashboard_sidecar.enabled -}}
 ---
 # Provisioning config
@@ -5,9 +6,8 @@ apiVersion: v1
 kind: ConfigMap
 metadata:
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -29,3 +29,4 @@ data:
           path: /var/lib/grafana/dashboards
           foldersFromFilesStructure: true
 {{- end }}
+{{- end }}

templates/ConfigMap-prometheus-adapter.yaml

@@ -3,9 +3,8 @@ apiVersion: v1
 kind: ConfigMap
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/Daemonset-GrafanaAgent.yaml

@@ -3,9 +3,8 @@ apiVersion: apps/v1
 kind: DaemonSet
 metadata:
   labels:
-    app.kubernetes.io/instance: k8s
+    {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 4 }}
-    app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana-agent
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -17,9 +16,8 @@ metadata:
 spec:
   selector:
     matchLabels:
-      app.kubernetes.io/instance: k8s
+      {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 6 }}
-      app.kubernetes.io/component: exporter
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: grafana-agent
       app.kubernetes.io/managed-by: {{ $.Release.Service }}
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
       app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -29,9 +27,8 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/instance: k8s
+        {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 8 }}
-        app.kubernetes.io/component: exporter
+        app.kubernetes.io/instance: {{ $.Release.Name }}
-        app.kubernetes.io/name: grafana-agent
         app.kubernetes.io/managed-by: {{ $.Release.Service }}
         app.kubernetes.io/part-of: {{ $.Chart.Name }}
         app.kubernetes.io/version: {{ $.Chart.Version }}

templates/Daemonset-kube-monitor-proxy.yaml

@@ -1,10 +1,11 @@
+{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
 ---
 apiVersion: apps/v1
 kind: DaemonSet
 metadata:
   labels:
     app.kubernetes.io/component: proxy
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-monitor-proxy
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -19,7 +20,7 @@ spec:
   selector:
     matchLabels:
       app.kubernetes.io/component: proxy
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: kube-monitor-proxy
       app.kubernetes.io/managed-by: {{ $.Release.Service }}
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -28,7 +29,7 @@ spec:
     metadata:
       labels:
         app.kubernetes.io/component: proxy
-        app.kubernetes.io/instance: k8s
+        app.kubernetes.io/instance: {{ $.Release.Name }}
         app.kubernetes.io/name: kube-monitor-proxy
         app.kubernetes.io/managed-by: {{ $.Release.Service }}
         app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -134,3 +135,5 @@ spec:
       serviceAccountName: kube-monitor-proxy
       tolerations:
       - operator: Exists
+
+{{ end }}

templates/Deployment-kubeStateMetrics.yaml

@@ -1,10 +1,11 @@
+{{ if .Values.nfc_monitoring.kube_state_metrics.enabled }}
 ---
 apiVersion: apps/v1
 kind: Deployment
 metadata:
   labels:
     app.kubernetes.io/component: exporter
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -16,7 +17,7 @@ spec:
   selector:
     matchLabels:
       app.kubernetes.io/component: exporter
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: kube-state-metrics
       app.kubernetes.io/managed-by: {{ $.Release.Service }}
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -26,7 +27,7 @@ spec:
         kubectl.kubernetes.io/default-container: kube-state-metrics
       labels:
         app.kubernetes.io/component: exporter
-        app.kubernetes.io/instance: k8s
+        app.kubernetes.io/instance: {{ $.Release.Name }}
         app.kubernetes.io/name: kube-state-metrics
         app.kubernetes.io/managed-by: {{ $.Release.Service }}
         app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -110,3 +111,5 @@ spec:
       nodeSelector:
         kubernetes.io/os: linux
       serviceAccountName: kube-state-metrics
+
+{{ end }}

templates/Deployment-prometheus-adapter.yaml

@@ -3,9 +3,8 @@ apiVersion: apps/v1
 kind: Deployment
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -15,9 +14,8 @@ spec:
   replicas: 2
   selector:
     matchLabels:
-      app.kubernetes.io/component: metrics-adapter
+      {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 6 }}
-      app.kubernetes.io/instance: main
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: prometheus-adapter
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
       app.kubernetes.io/managed-by: {{ $.Release.Service }}
       app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -28,9 +26,8 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/component: metrics-adapter
+        {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 8 }}
-        app.kubernetes.io/instance: main
+        app.kubernetes.io/instance: {{ $.Release.Name }}
-        app.kubernetes.io/name: prometheus-adapter
         app.kubernetes.io/part-of: {{ $.Chart.Name }}
         app.kubernetes.io/managed-by: {{ $.Release.Service }}
         app.kubernetes.io/version: {{ $.Chart.Version }}

templates/Grafana-Grafana.yaml

@@ -1,11 +1,11 @@
 ---
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 apiVersion: grafana.integreatly.org/v1beta1
 kind: Grafana
 metadata:
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -13,19 +13,12 @@ metadata:
   namespace: "{{ .Values.nfc_monitoring.grafana.namespace }}"
 spec:
   config:
-    log:
+    {{ toYaml $.Values.nfc_monitoring.grafana.config | nindent 4 }}
-      mode: "console"
-    auth:
-      disable_login_form: "false"
-    security:
-      admin_user: "{{ .Values.nfc_monitoring.grafana.admin_user }}"
-      admin_password: "{{ .Values.nfc_monitoring.grafana.admin_password }}"
   deployment:
     metadata:
       labels:
-        app.kubernetes.io/component: graphing
+        {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 8 }}
-        app.kubernetes.io/instance: k8s
+        app.kubernetes.io/instance: {{ $.Release.Name }}
-        app.kubernetes.io/name: grafana
         app.kubernetes.io/managed-by: {{ $.Release.Service }}
         app.kubernetes.io/part-of: {{ $.Chart.Name }}
         app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -33,9 +26,8 @@ spec:
       replicas: {{ .Values.nfc_monitoring.grafana.replicas | int }}
       selector:
         matchLabels:
-          app.kubernetes.io/component: graphing
+          {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 10 }}
-          app.kubernetes.io/instance: k8s
+          app.kubernetes.io/instance: {{ $.Release.Name }}
-          app.kubernetes.io/name: grafana
           app.kubernetes.io/managed-by: {{ $.Release.Service }}
           app.kubernetes.io/part-of: {{ $.Chart.Name }}
       strategy:
@@ -45,9 +37,8 @@ spec:
       template:
         metadata:
           labels:
-            app.kubernetes.io/component: graphing
+            {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 12 }}
-            app.kubernetes.io/instance: k8s
+            app.kubernetes.io/instance: {{ $.Release.Name }}
-            app.kubernetes.io/name: grafana
             app.kubernetes.io/managed-by: {{ $.Release.Service }}
             app.kubernetes.io/part-of: {{ $.Chart.Name }}
             app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -105,7 +96,7 @@ spec:
                 name: dashboards
           
           - image: "{{ .Values.nfc_monitoring.additions.dashboard_sidecar.image.name }}:{{ .Values.nfc_monitoring.additions.dashboard_sidecar.image.tag}}"
-            name: k8s-sidecar
+            name: sidecar
             env:
               - name: LABEL
                 value: "{{ .Values.nfc_monitoring.additions.dashboard_sidecar.label_name }}"
@@ -157,7 +148,9 @@ spec:
         app.kubernetes.io/part-of: {{ $.Chart.Name }}
     spec:
       accessModes:
-        - "ReadWriteMany"
+        - {{ .Values.nfc_monitoring.grafana.storage_accessModes | default "ReadWriteOnce" }}
       resources:
         requests:
           storage: "5Gi"
+
+{{- end }}

templates/GrafanaDashboard-AlertManager.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 ---
 apiVersion: grafana.integreatly.org/v1beta1
 kind: GrafanaDashboard
@@ -11,8 +12,10 @@ spec:
   instanceSelector:
     matchLabels:
       app.kubernetes.io/component: graphing
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: grafana
   grafanaCom:
     id: 9578
     revision: 4 # as @ 19-09-23
+
+{{- end }}

templates/GrafanaDashboard-Ceph.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 ---
 {{- if .Values.nfc_monitoring.additions.ceph.enabled | default false -}}
 apiVersion: grafana.integreatly.org/v1beta1
@@ -12,10 +13,11 @@ spec:
   instanceSelector:
     matchLabels:
       app.kubernetes.io/component: graphing
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: grafana
   grafanaCom:
     id: 2842
     revision: 17 # as @ 19-09-23
 
 {{- end -}}
+{{- end }}

templates/GrafanaDashboard-calico.yaml

@@ -0,0 +1,25 @@
+---
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
+{{- if eq .Values.nfc_monitoring.kubernetes.networking "calico" }}
+{{- if .Values.nfc_monitoring.prometheus.service_monitor.calico }}
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: calico-felix
+  namespace: {{ .Values.nfc_monitoring.grafana.namespace }}
+spec:
+  allowCrossNamespaceImport: true
+  folder: No Fuss Monitoring
+  resyncPeriod: 1d
+  instanceSelector:
+    matchLabels:
+      app.kubernetes.io/component: graphing
+      app.kubernetes.io/instance: {{ $.Release.Name }}
+      app.kubernetes.io/name: grafana
+  grafanaCom:
+    id: 12175
+    revision: 5 # as @ 2020-05-04T16:47:08
+
+{{- end }}
+{{ end }}
+{{ end }}

templates/GrafanaDashboard-cert-manager.yaml

@@ -0,0 +1,21 @@
+---
+{{ if .Values.nfc_monitoring.grafana.dashboards.cert_manager | default false -}}
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: node-exporter
+  namespace: {{ .Values.nfc_monitoring.grafana.namespace }}
+spec:
+  allowCrossNamespaceImport: true
+  folder: No Fuss Monitoring
+  resyncPeriod: 1d
+  instanceSelector:
+    matchLabels:
+      app.kubernetes.io/component: graphing
+      app.kubernetes.io/instance: {{ $.Release.Name }}
+      app.kubernetes.io/name: grafana
+  grafanaCom:
+    id: 11001
+    revision: 1 # as @ 2019-10-16T13:48:56
+
+{{- end }}

templates/GrafanaDashboard-cluster-summary.yaml

@@ -1,4 +1,5 @@
 ---
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 apiVersion: grafana.integreatly.org/v1beta1
 kind: GrafanaDashboard
 metadata:
@@ -11,9 +12,10 @@ spec:
   instanceSelector:
     matchLabels:
       app.kubernetes.io/component: graphing
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: grafana
    {{ $Dashboard := .Files.Get "files/dashboard-summary.json" | fromJson }}
   json: >-
     {{ $Dashboard | toRawJson }}
 
+{{- end }}

templates/GrafanaDashboard-node-exporter-full.yaml

@@ -1,4 +1,5 @@
 ---
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 apiVersion: grafana.integreatly.org/v1beta1
 kind: GrafanaDashboard
 metadata:
@@ -11,8 +12,10 @@ spec:
   instanceSelector:
     matchLabels:
       app.kubernetes.io/component: graphing
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: grafana
   grafanaCom:
     id: 1860
     revision: 32 # as @ 19-09-23
+
+{{- end }}

templates/GrafanaDatasources.yaml

@@ -1,4 +1,5 @@
 ---
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 apiVersion: grafana.integreatly.org/v1beta1
 kind: GrafanaDatasourceList
 items:
@@ -10,7 +11,7 @@ items:
       namespace: "{{ $.Values.nfc_monitoring.grafana.namespace }}"
       labels:
         app.kubernetes.io/component: dashboard
-        app.kubernetes.io/instance: k8s
+        app.kubernetes.io/instance: {{ $.Release.Name }}
         app.kubernetes.io/name: grafana
         app.kubernetes.io/managed-by: {{ $.Release.Service }}
         app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -18,11 +19,10 @@ items:
     spec:
       instanceSelector:
         matchLabels:
-          app.kubernetes.io/component: graphing
+          {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 10 }}
-          app.kubernetes.io/instance: k8s
-          app.kubernetes.io/name: grafana
       allowCrossNamespaceImport: true
       datasource:
         {{ toYaml . | nindent 8 }}
 
   {{ end }}
+{{- end }}

templates/Ingress-Multi.yaml

@@ -0,0 +1,85 @@
+{{ if .Values.nfc_monitoring.alert_manager.ingress.enabled -}}
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: alertmanager
+  namespace: "{{ .Values.nfc_monitoring.alert_manager.namespace }}"
+  annotations:
+    {{ toYaml $.Values.nfc_monitoring.alert_manager.ingress.annotations | nindent 4 }}
+spec:
+  tls:
+    - hosts:
+        - {{ .Values.nfc_monitoring.alert_manager.ingress.hostname }}
+      secretName: certificate-tls-alert-manager
+  rules:
+    - host:  {{ .Values.nfc_monitoring.alert_manager.ingress.hostname }}
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: alertmanager-{{ $.Release.Name }}
+                port:
+                  name: web
+
+{{ end }}
+
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
+{{ if .Values.nfc_monitoring.grafana.ingress.enabled -}}
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: grafana
+  namespace: "{{ .Values.nfc_monitoring.grafana.namespace }}"
+  annotations:
+    {{ toYaml $.Values.nfc_monitoring.grafana.ingress.annotations | nindent 4 }}
+spec:
+  tls:
+    - hosts:
+        - {{ .Values.nfc_monitoring.grafana.ingress.hostname }}
+      secretName: certificate-tls-grafana
+  rules:
+    - host:  {{ .Values.nfc_monitoring.grafana.ingress.hostname }}
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: grafana
+                port:
+                  name: grafana-http
+
+{{ end }}
+{{ end }}
+
+{{ if .Values.nfc_monitoring.prometheus.ingress.enabled | default "false" -}}
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: prometheus
+  namespace: "{{ .Values.nfc_monitoring.prometheus.namespace }}"
+  annotations:
+    {{ toYaml $.Values.nfc_monitoring.prometheus.ingress.annotations | nindent 4 }}
+spec:
+  tls:
+    - hosts:
+        - {{ .Values.nfc_monitoring.prometheus.ingress.hostname }}
+      secretName: certificate-tls-prometheus
+  rules:
+    - host:  {{ .Values.nfc_monitoring.prometheus.ingress.hostname }}
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: prometheus-{{ $.Release.Name }}
+                port:
+                  name: web
+
+{{ end }}

templates/NetworkPolicy-kubeStateMetrics.yaml

@@ -1,31 +1,37 @@
-# apiVersion: networking.k8s.io/v1
+{{ if .Values.nfc_monitoring.kube_state_metrics.enabled }}
-# kind: NetworkPolicy
+---
-# metadata:
+apiVersion: networking.k8s.io/v1
-#   labels:
+kind: NetworkPolicy
-#     app.kubernetes.io/component: exporter
+metadata:
-#     app.kubernetes.io/name: kube-state-metrics
+  labels:
-#     app.kubernetes.io/part-of: kube-prometheus
+    app.kubernetes.io/component: exporter
-#     app.kubernetes.io/version: 2.8.1
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-#   name: kube-state-metrics
+    app.kubernetes.io/name: kube-state-metrics
-#   namespace: monitoring
+    app.kubernetes.io/part-of: kube-prometheus
-# spec:
+    app.kubernetes.io/version: 2.8.1
-#   egress:
+  name: kube-state-metrics
-#   - {}
+  namespace: monitoring
-#   ingress:
+spec:
-#   - from:
+  egress:
-#     - podSelector:
+  - {}
-#         matchLabels:
+  ingress:
-#           app.kubernetes.io/name: prometheus
+  - from:
-#     ports:
+    - podSelector:
-#     - port: 8443
+        matchLabels:
-#       protocol: TCP
+          app.kubernetes.io/name: prometheus
-#     - port: 9443
+    ports:
-#       protocol: TCP
+    - port: 8443
-#   podSelector:
+      protocol: TCP
-#     matchLabels:
+    - port: 9443
-#       app.kubernetes.io/component: exporter
+      protocol: TCP
-#       app.kubernetes.io/name: kube-state-metrics
+  podSelector:
-#       app.kubernetes.io/part-of: kube-prometheus
+    matchLabels:
-#   policyTypes:
+      app.kubernetes.io/component: exporter
-#   - Egress
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-#   - Ingress
+      app.kubernetes.io/name: kube-state-metrics
+      app.kubernetes.io/part-of: kube-prometheus
+  policyTypes:
+  - Egress
+  - Ingress
+
+{{ end }}

templates/NetworkPolicy.yaml

@@ -0,0 +1,313 @@
+
+{{- if .Values.nfc_monitoring.network_policy.enabled -}}
+---
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  labels:
+    {{ toYaml (get $.Values.nfc_monitoring .name ).labels | nindent 4 }}
+    app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/managed-by: {{ $.Release.Service }}
+    app.kubernetes.io/part-of: {{ $.Chart.Name }}
+    app.kubernetes.io/version: {{ $.Chart.Version }}
+  name: {{ .name  | replace "_" "-" }}
+  namespace: {{ (get $.Values.nfc_monitoring .name ).namespace }}
+spec:
+  - name: prometheus
+    policy:
+      egress: # ToDo: add further restrictions to egress. is variable lookup possible to obtain values????
+          # - {}
+        - to: # Alert Manager
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: alerting
+              podSelector:
+                matchLabels:
+                  app.kubernetes.io/instance: {{ $.Release.Name }}
+                  app.kubernetes.io/component: alert-router
+                  app.kubernetes.io/name: alertmanager
+          ports:
+            - port: 9093
+              protocol: TCP
+
+        - to: # Ceph
+            - ipBlock:
+                cidr: 172.16.10.0/24
+          ports:
+            - port: 9283
+              protocol: TCP
+
+        - to: # Grafana
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: grafana
+              podSelector:
+                matchLabels:
+                  app.kubernetes.io/component: graphing
+                  app.kubernetes.io/instance: {{ $.Release.Name }}
+                  app.kubernetes.io/name: grafana
+          ports:
+            - port: 3000
+              protocol: TCP
+
+        - to: # Grafana Agent
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: monitoring
+              podSelector:
+                matchLabels:
+                  app.kubernetes.io/instance: {{ $.Release.Name }}
+                  app.kubernetes.io/component: exporter
+                  app.kubernetes.io/name: grafana-agent
+          ports:
+            - port: 12345
+              protocol: TCP
+
+        - to: # Kube DNS
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: kube-system
+              podSelector:
+                matchLabels:
+                  k8s-app: kube-dns
+          ports:
+            - port: 53
+              protocol: TCP
+            - port: 53
+              protocol: UDP
+
+        - to:
+            - podSelector:
+                matchLabels:
+                  app.kubernetes.io/name: prometheus
+              # namespaceSelector:
+              #   matchLabels:
+              #     kubernetes.io/metadata.name: monitoiring
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: metrics
+          ports: []
+
+        - {} # ToDo: Temp rule: Allow All. this rule MUST be removed when egress has been refactored
+
+      ingress: 
+
+        - from:
+            - podSelector:
+                matchLabels:
+                  app.kubernetes.io/name: prometheus
+              # namespaceSelector:
+              #   matchLabels:
+              #     kubernetes.io/metadata.name: monitoiring
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: metrics
+          ports: []
+            # - port: 8080
+            #   protocol: TCP
+            # - port: 9090
+            #   protocol: TCP
+            # - port: 10901
+            #   protocol: TCP
+
+        - from:
+            - podSelector:
+                matchLabels:
+                  app.kubernetes.io/name: grafana
+              namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: grafana
+            - podSelector:
+                matchLabels:
+                  app.kubernetes.io/name: prometheus-adapter
+              namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: monitoring
+          ports:
+            - port: 9090
+              protocol: TCP
+
+        - from: []
+          ports: []
+
+      policyTypes:
+      - Egress
+      - Ingress
+
+  podSelector:
+    matchLabels:
+      {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 6 }}
+      app.kubernetes.io/instance: {{ $.Release.Name }}
+      app.kubernetes.io/part-of: {{ $.Chart.Name }}
+      app.kubernetes.io/managed-by: {{ $.Release.Service }}
+
+---
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  labels:
+    {{ toYaml (get $.Values.nfc_monitoring .name ).labels | nindent 4 }}
+    app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/managed-by: {{ $.Release.Service }}
+    app.kubernetes.io/part-of: {{ $.Chart.Name }}
+    app.kubernetes.io/version: {{ $.Chart.Version }}
+  name: {{ .name  | replace "_" "-" }}
+  namespace: {{ (get $.Values.nfc_monitoring .name ).namespace }}
+spec:
+  - name: grafana
+    policy:
+        egress:
+
+          - to:
+              - namespaceSelector:
+                  matchLabels:
+                    kubernetes.io/metadata.name: alerting
+                podSelector:
+                  matchLabels:
+                    app.kubernetes.io/instance: {{ $.Release.Name }}
+                    app.kubernetes.io/component: alert-router
+                    app.kubernetes.io/name: alertmanager
+            ports:
+              - port: 9093
+                protocol: TCP
+
+          - to:
+              - namespaceSelector:
+                  matchLabels:
+                    kubernetes.io/metadata.name: logging
+                podSelector:
+                  matchLabels:
+                    app.kubernetes.io/component: gateway
+                    app.kubernetes.io/instance: loki
+                    app.kubernetes.io/name: loki
+            ports:
+              - port: 80       # Service Port
+                protocol: TCP
+              - port: 8080     # Pod Port
+                protocol: TCP
+
+          - to:
+              - namespaceSelector:
+                  matchLabels:
+                    kubernetes.io/metadata.name: monitoring
+                podSelector:
+                  matchLabels:
+                    app.kubernetes.io/component: prometheus
+                    app.kubernetes.io/instance: {{ $.Release.Name }}
+                    app.kubernetes.io/name: prometheus
+              - namespaceSelector:
+                  matchLabels:
+                    kubernetes.io/metadata.name: metrics
+                podSelector:
+                  matchLabels:
+                    app.kubernetes.io/component: query-layer
+                    app.kubernetes.io/instance: thanos-query
+                    app.kubernetes.io/name: thanos-query
+            ports:
+              - port: 9090
+                protocol: TCP
+
+          - to: [] # Requires internet access for plugins and dashboard downloading
+            ports:
+              - port: 443
+                protocol: TCP
+
+          - to: # Kube DNS
+              - namespaceSelector:
+                  matchLabels:
+                    kubernetes.io/metadata.name: kube-system
+                podSelector:
+                  matchLabels:
+                    k8s-app: kube-dns
+            ports:
+              - port: 53
+                protocol: TCP
+              - port: 53
+                protocol: UDP
+
+        ingress:
+
+          - from: []
+            ports:
+              - port: 3000
+                protocol: TCP
+        policyTypes:
+          - Egress
+          - Ingress
+
+  podSelector:
+    matchLabels:
+      {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 8 }}
+      app.kubernetes.io/instance: {{ $.Release.Name }}
+      app.kubernetes.io/managed-by: {{ $.Release.Service }}
+      app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+---
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  labels:
+    {{ toYaml (get $.Values.nfc_monitoring .name ).labels | nindent 4 }}
+    app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/managed-by: {{ $.Release.Service }}
+    app.kubernetes.io/part-of: {{ $.Chart.Name }}
+    app.kubernetes.io/version: {{ $.Chart.Version }}
+  name: {{ .name  | replace "_" "-" }}
+  namespace: {{ (get $.Values.nfc_monitoring .name ).namespace }}
+spec:
+  - name: grafana_agent
+    policy:
+      egress:
+
+        - to: # Logging
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: logging
+              podSelector:
+                matchLabels:
+                  app.kubernetes.io/component: gateway
+                  app.kubernetes.io/instance: loki
+                  app.kubernetes.io/name: loki
+          ports:
+            - port: 80
+              protocol: TCP
+
+        - to: # Kube DNS
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: kube-system
+              podSelector:
+                matchLabels:
+                  k8s-app: kube-dns
+          ports:
+            - port: 53
+              protocol: TCP
+            - port: 53
+              protocol: UDP
+
+      ingress:
+
+        - from: 
+            - namespaceSelector:
+                matchLabels:
+                  kubernetes.io/metadata.name: monitoring
+              podSelector:
+                matchLabels:
+                  app.kubernetes.io/component: prometheus
+                  app.kubernetes.io/name: prometheus
+          ports:
+            - port: 12345
+              protocol: TCP
+
+      policyTypes:
+      - Egress
+      - Ingress
+
+  podSelector:
+    matchLabels:
+      {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 8 }}
+      app.kubernetes.io/instance: {{ $.Release.Name }}
+      app.kubernetes.io/managed-by: {{ $.Release.Service }}
+      app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+{{ end }}

templates/PodDisruptionBudget-alertmanager.yaml

@@ -3,9 +3,8 @@ apiVersion: policy/v1
 kind: PodDisruptionBudget
 metadata:
   labels:
-    app.kubernetes.io/component: alert-router
+    {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: alertmanager
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -15,7 +14,6 @@ spec:
   maxUnavailable: 1
   selector:
     matchLabels:
-      app.kubernetes.io/component: alert-router
+      {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 6 }}
-      app.kubernetes.io/instance: main
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: alertmanager
       app.kubernetes.io/part-of: {{ $.Chart.Name }}

templates/PodDisruptionBudget-prometheus-adapter.yaml

@@ -3,9 +3,8 @@ apiVersion: policy/v1
 kind: PodDisruptionBudget
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -15,7 +14,6 @@ spec:
   minAvailable: 1
   selector:
     matchLabels:
-      app.kubernetes.io/component: metrics-adapter
+      {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 6 }}
-      app.kubernetes.io/instance: main
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: prometheus-adapter
       app.kubernetes.io/part-of: {{ $.Chart.Name }}

templates/PodDisruptionBudget-prometheus.yaml

@@ -3,18 +3,16 @@ apiVersion: policy/v1
 kind: PodDisruptionBudget
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
-    app.kubernetes.io/name: prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
 spec:
   minAvailable: 1
   selector:
     matchLabels:
-      app.kubernetes.io/component: prometheus
+      {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 6 }}
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/part-of: {{ $.Chart.Name }}

templates/Prometheus-prometheus.yaml

@@ -3,12 +3,12 @@ apiVersion: monitoring.coreos.com/v1
 kind: Prometheus
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: k8s
+  name: {{ $.Release.Name }}
   namespace: "{{ .Values.nfc_monitoring.prometheus.namespace }}"
 spec:
   affinity:
@@ -16,19 +16,18 @@ spec:
   alerting:
     alertmanagers:
     - apiVersion: v2
-      name: alertmanager-main
+      name: alertmanager-{{ $.Release.Name }}
       namespace: "{{ .Values.nfc_monitoring.alert_manager.namespace }}"
       port: web
   enableFeatures: []
   externalLabels: {}
-  image: quay.io/prometheus/prometheus:v2.42.0
+  image: {{ .Values.nfc_monitoring.prometheus.image.name }}:{{ .Values.nfc_monitoring.prometheus.image.tag}}
   nodeSelector:
     kubernetes.io/os: linux
   podMetadata:
     labels:
-      app.kubernetes.io/component: prometheus
+      {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 6 }}
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: prometheus
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
       app.kubernetes.io/managed-by: {{ $.Release.Service }}
       app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -36,28 +35,33 @@ spec:
   podMonitorSelector: {}
   probeNamespaceSelector: {}
   probeSelector: {}
-  replicas: 3
+  {{ if .Values.nfc_monitoring.prometheus.remotewrite }}
+  remoteWrite: {{ .Values.nfc_monitoring.prometheus.remotewrite | toYaml | nindent 4 }}
+
+  {{- end }}
+  replicas: {{ $.Values.nfc_monitoring.prometheus.replicas }}
   resources:
     requests:
       memory: 400Mi
   ruleNamespaceSelector: {}
-  ruleSelector: {}
   securityContext:
     fsGroup: 2000
     runAsNonRoot: true
     runAsUser: 1000
-  serviceAccountName: prometheus-k8s
+  serviceAccountName: prometheus-{{ $.Release.Name }}
   serviceMonitorNamespaceSelector: {}
   serviceMonitorSelector: {}
   storage:
-    {{- toYaml .Values.nfc_monitoring.prometheus.affinity | nindent 4 }}
+    {{- toYaml .Values.nfc_monitoring.prometheus.storage | nindent 4 }}
   {{ if .Values.nfc_monitoring.thanos.sidecar.enabled }}
+  {{ if .Values.nfc_monitoring.thanos.sidecar.config }}
   thanos:
     image: "{{ .Values.nfc_monitoring.thanos.image.name }}:{{ .Values.nfc_monitoring.thanos.image.tag }}"
     objectStorageConfig:
       key: thanos.yaml
       name: thanos-sidecar-config
   {{ end }}
+  {{ end }}
   version: 2.42.0
   {{ if .Values.nfc_monitoring.prometheus.additional }}
   {{ toYaml .Values.nfc_monitoring.prometheus.additional | nindent 2 }}

templates/PrometheusRule-alertmanager.yaml

@@ -3,13 +3,12 @@ apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
-    app.kubernetes.io/component: alert-router
+    {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: alertmanager
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
   name: alertmanager-main-rules
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
@@ -25,7 +24,7 @@ spec:
       expr: |
         # Without max_over_time, failed scrapes could create false negatives, see
         # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
-        max_over_time(alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"}[5m]) == 0
+        max_over_time(alertmanager_config_last_reload_successful{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}[5m]) == 0
       for: 10m
       labels:
         severity: critical
@@ -37,9 +36,9 @@ spec:
       expr: |
         # Without max_over_time, failed scrapes could create false negatives, see
         # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
-          max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}[5m])
+          max_over_time(alertmanager_cluster_members{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}[5m])
         < on (namespace,service) group_left
-          count by (namespace,service) (max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}[5m]))
+          count by (namespace,service) (max_over_time(alertmanager_cluster_members{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}[5m]))
       for: 15m
       labels:
         severity: critical
@@ -50,9 +49,9 @@ spec:
         summary: An Alertmanager instance failed to send notifications.
       expr: |
         (
-          rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring"}[5m])
+          rate(alertmanager_notifications_failed_total{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}[5m])
         /
-          rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring"}[5m])
+          rate(alertmanager_notifications_total{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}[5m])
         )
         > 0.01
       for: 5m
@@ -65,9 +64,9 @@ spec:
         summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration.
       expr: |
         min by (namespace,service, integration) (
-          rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring", integration=~`.*`}[5m])
+          rate(alertmanager_notifications_failed_total{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring", integration=~`.*`}[5m])
         /
-          rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring", integration=~`.*`}[5m])
+          rate(alertmanager_notifications_total{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring", integration=~`.*`}[5m])
         )
         > 0.01
       for: 5m
@@ -80,9 +79,9 @@ spec:
         summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration.
       expr: |
         min by (namespace,service, integration) (
-          rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring", integration!~`.*`}[5m])
+          rate(alertmanager_notifications_failed_total{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring", integration!~`.*`}[5m])
         /
-          rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring", integration!~`.*`}[5m])
+          rate(alertmanager_notifications_total{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring", integration!~`.*`}[5m])
         )
         > 0.01
       for: 5m
@@ -95,7 +94,7 @@ spec:
         summary: Alertmanager instances within the same cluster have different configurations.
       expr: |
         count by (namespace,service) (
-          count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring"})
+          count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"})
         )
         != 1
       for: 20m
@@ -109,11 +108,11 @@ spec:
       expr: |
         (
           count by (namespace,service) (
-            avg_over_time(up{job="alertmanager-main",namespace="monitoring"}[5m]) < 0.5
+            avg_over_time(up{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}[5m]) < 0.5
           )
         /
           count by (namespace,service) (
-            up{job="alertmanager-main",namespace="monitoring"}
+            up{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}
           )
         )
         >= 0.5
@@ -128,11 +127,11 @@ spec:
       expr: |
         (
           count by (namespace,service) (
-            changes(process_start_time_seconds{job="alertmanager-main",namespace="monitoring"}[10m]) > 4
+            changes(process_start_time_seconds{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}[10m]) > 4
           )
         /
           count by (namespace,service) (
-            up{job="alertmanager-main",namespace="monitoring"}
+            up{job="alertmanager-{{ $.Release.Name }}",namespace="monitoring"}
           )
         )
         >= 0.5

templates/PrometheusRule-common.yaml

@@ -0,0 +1,48 @@
+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  labels:
+    app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/name: kube-prometheus
+    app.kubernetes.io/part-of: {{ $.Chart.Name }}
+    app.kubernetes.io/version: {{ $.Chart.Version }}
+    app.kubernetes.io/managed-by: {{ $.Release.Service }}
+    prometheus: {{ $.Release.Name }}
+    role: alert-rules
+  name: common
+  namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
+spec:
+  groups:
+  - name: common.rules
+    rules:
+
+    - alert: Watchdog
+      annotations:
+        description: |
+          This is an alert is meant to ensure that the entire alerting pipeline is functional.
+          This alert is always firing, therefore it should always be firing in Alertmanager
+          and always fire against a receiver. There are integrations with various notification
+          mechanisms that send a notification when this alert is not firing. For example the
+          "DeadMansSnitch" integration in PagerDuty.
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
+        summary: An alert that should always be firing to certify that Alertmanager is working properly.
+      expr: vector(1)
+      labels:
+        severity: none
+
+    - alert: InfoInhibitor
+      annotations:
+        description: |
+          This is an alert that is used to inhibit info alerts.
+          By themselves, the info-level alerts are sometimes very noisy, but they are relevant when combined with
+          other alerts.
+          This alert fires whenever there's a severity="info" alert, and stops firing when another alert with a
+          severity of 'warning' or 'critical' starts firing on the same namespace.
+          This alert should be routed to a null receiver and configured to inhibit alerts with severity="info".
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor
+        summary: Info-level alert inhibition.
+      expr: ALERTS{severity = "info"} == 1 unless on(namespace) ALERTS{alertname != "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1
+      labels:
+        severity: none

templates/PrometheusRule-grafana-agent.yaml

@@ -3,13 +3,13 @@ apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
-    app.kubernetes.io/component: exporter
+    {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 4 }}
-    app.kubernetes.io/name: grafana-agent
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
-    role: grafana-agent-promtail
+    role: alert-rules
   name: grafana-agent
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
 spec:
@@ -21,3 +21,87 @@ spec:
     - expr: |
         agent_build_info
       record: promtail_build_info
+  - name: promtail_rules
+    rules:
+    - expr: histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[1m]))
+        by (le, job))
+      record: job:promtail_request_duration_seconds:99quantile
+    - expr: histogram_quantile(0.50, sum(rate(promtail_request_duration_seconds_bucket[1m]))
+        by (le, job))
+      record: job:promtail_request_duration_seconds:50quantile
+    - expr: sum(rate(promtail_request_duration_seconds_sum[1m])) by (job) / sum(rate(promtail_request_duration_seconds_count[1m]))
+        by (job)
+      record: job:promtail_request_duration_seconds:avg
+    - expr: sum(rate(promtail_request_duration_seconds_bucket[1m])) by (le, job)
+      record: job:promtail_request_duration_seconds_bucket:sum_rate
+    - expr: sum(rate(promtail_request_duration_seconds_sum[1m])) by (job)
+      record: job:promtail_request_duration_seconds_sum:sum_rate
+    - expr: sum(rate(promtail_request_duration_seconds_count[1m])) by (job)
+      record: job:promtail_request_duration_seconds_count:sum_rate
+    - expr: histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[1m]))
+        by (le, job, namespace))
+      record: job_namespace:promtail_request_duration_seconds:99quantile
+    - expr: histogram_quantile(0.50, sum(rate(promtail_request_duration_seconds_bucket[1m]))
+        by (le, job, namespace))
+      record: job_namespace:promtail_request_duration_seconds:50quantile
+    - expr: sum(rate(promtail_request_duration_seconds_sum[1m])) by (job, namespace)
+        / sum(rate(promtail_request_duration_seconds_count[1m])) by (job, namespace)
+      record: job_namespace:promtail_request_duration_seconds:avg
+    - expr: sum(rate(promtail_request_duration_seconds_bucket[1m])) by (le, job, namespace)
+      record: job_namespace:promtail_request_duration_seconds_bucket:sum_rate
+    - expr: sum(rate(promtail_request_duration_seconds_sum[1m])) by (job, namespace)
+      record: job_namespace:promtail_request_duration_seconds_sum:sum_rate
+    - expr: sum(rate(promtail_request_duration_seconds_count[1m])) by (job, namespace)
+      record: job_namespace:promtail_request_duration_seconds_count:sum_rate
+    - expr: histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[1m]))
+        by (le, job, status_code, namespace))
+      record: job_status_code_namespace:promtail_request_duration_seconds:99quantile
+    - expr: histogram_quantile(0.50, sum(rate(promtail_request_duration_seconds_bucket[1m]))
+        by (le, job, status_code, namespace))
+      record: job_status_code_namespace:promtail_request_duration_seconds:50quantile
+    - expr: sum(rate(promtail_request_duration_seconds_sum[1m])) by (job, status_code,
+        namespace) / sum(rate(promtail_request_duration_seconds_count[1m])) by (job,
+        status_code, namespace)
+      record: job_status_code_namespace:promtail_request_duration_seconds:avg
+    - expr: sum(rate(promtail_request_duration_seconds_bucket[1m])) by (le, job, status_code,
+        namespace)
+      record: job_status_code_namespace:promtail_request_duration_seconds_bucket:sum_rate
+    - expr: sum(rate(promtail_request_duration_seconds_sum[1m])) by (job, status_code,
+        namespace)
+      record: job_status_code_namespace:promtail_request_duration_seconds_sum:sum_rate
+    - expr: sum(rate(promtail_request_duration_seconds_count[1m])) by (job, status_code,
+        namespace)
+      record: job_status_code_namespace:promtail_request_duration_seconds_count:sum_rate
+
+  - name: promtail_alerts
+    rules:
+    - alert: PromtailRequestsErrors
+      annotations:
+        message: |
+          {{ `{{` }} $labels.job }} {{ `{{` }} $labels.route }} is experiencing {{ `{{` }} printf "%.2f" $value }}% errors.
+      expr: |
+        100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[1m])) by (namespace, job, route, instance)
+          /
+        sum(rate(promtail_request_duration_seconds_count[1m])) by (namespace, job, route, instance)
+          > 10
+      for: 15m
+      labels:
+        severity: critical
+    - alert: PromtailRequestLatency
+      annotations:
+        message: |
+          {{ `{{` }} $labels.job }} {{ `{{` }} $labels.route }} is experiencing {{ `{{` }} printf "%.2f" $value }}s 99th percentile latency.
+      expr: |
+        job_status_code_namespace:promtail_request_duration_seconds:99quantile > 1
+      for: 15m
+      labels:
+        severity: critical
+    - alert: PromtailFileMissing
+      annotations:
+        message: |
+          {{ `{{` }} $labels.instance }} {{ `{{` }} $labels.job }} {{ `{{` }} $labels.path }} matches the glob but is not being tailed.
+      expr: |
+        promtail_file_bytes_total unless promtail_read_bytes_total
+      for: 15m
+      labels:
+        severity: warning

templates/PrometheusRule-grafana.yaml

@@ -1,14 +1,15 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
-    app.kubernetes.io/component: grafana
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/name: grafana
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
   name: grafana-rules
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
@@ -33,3 +34,5 @@ spec:
     - expr: |
         sum by (namespace, job, handler, status_code) (rate(grafana_http_request_duration_seconds_count[5m]))
       record: namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m
+
+{{- end }}

templates/PrometheusRule-kubePrometheus.yaml

@@ -1,14 +1,16 @@
+{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
     app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
   name: kube-prometheus-rules
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
@@ -25,33 +27,6 @@ spec:
       for: 10m
       labels:
         severity: warning
-    - alert: Watchdog
-      annotations:
-        description: |
-          This is an alert meant to ensure that the entire alerting pipeline is functional.
-          This alert is always firing, therefore it should always be firing in Alertmanager
-          and always fire against a receiver. There are integrations with various notification
-          mechanisms that send a notification when this alert is not firing. For example the
-          "DeadMansSnitch" integration in PagerDuty.
-        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
-        summary: An alert that should always be firing to certify that Alertmanager is working properly.
-      expr: vector(1)
-      labels:
-        severity: none
-    - alert: InfoInhibitor
-      annotations:
-        description: |
-          This is an alert that is used to inhibit info alerts.
-          By themselves, the info-level alerts are sometimes very noisy, but they are relevant when combined with
-          other alerts.
-          This alert fires whenever there's a severity="info" alert, and stops firing when another alert with a
-          severity of 'warning' or 'critical' starts firing on the same namespace.
-          This alert should be routed to a null receiver and configured to inhibit alerts with severity="info".
-        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor
-        summary: Info-level alert inhibition.
-      expr: ALERTS{severity = "info"} == 1 unless on(namespace) ALERTS{alertname != "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1
-      labels:
-        severity: none
   - name: node-network
     rules:
     - alert: NodeNetworkInterfaceFlapping
@@ -84,3 +59,5 @@ spec:
       record: count:up1
     - expr: count without(instance, pod, node) (up == 0)
       record: count:up0
+
+{{ end }}

templates/PrometheusRule-kubeStateMetrics.yaml

@@ -1,14 +1,16 @@
+{{ if .Values.nfc_monitoring.kube_state_metrics.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
     app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
   name: kube-state-metrics-rules
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
@@ -65,3 +67,5 @@ spec:
       for: 15m
       labels:
         severity: critical
+
+{{ end }}

templates/PrometheusRule-kubernetesControlPlane.yaml

@@ -1,13 +1,15 @@
+{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
   name: kubernetes-monitoring-rules
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
@@ -1439,3 +1441,5 @@ spec:
       labels:
         quantile: "0.5"
       record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
+
+{{ end }}

templates/PrometheusRule-loki.yaml

@@ -1,15 +1,17 @@
 ---
 {{- if .Values.nfc_monitoring.loki.enabled | default false -}}
+{{ if .Values.nfc_monitoring.loki.config }}
 apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
     app.kubernetes.io/component: logging
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: loki
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
   name: loki
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
@@ -109,4 +111,5 @@ spec:
       labels:
         severity: warning
 
+{{ end }}
 {{- end -}}

templates/PrometheusRule-nodeExporter.yaml

@@ -4,11 +4,12 @@ kind: PrometheusRule
 metadata:
   labels:
     app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: node-exporter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
   name: node-exporter-rules
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
@@ -16,6 +17,16 @@ spec:
   groups:
   - name: node-exporter
     rules:
+{{ range $index, $node := (lookup "v1" "Node" "" "").items }}
+    - alert: NodeExporterJobMissing-{{ $node.metadata.name }}
+      annotations:
+        summary: Node Exporter job missing for node {{ $node.metadata.name }}. (instance {{ `{{` }} $labels.instance }})
+        description: "Node Exporter job has disappeared\n  Node = {{ $node.metadata.name }}\n  Value = {{ `{{` }} $value }}\n  LABELS = {{ `{{` }} $labels }}"
+      expr: absent(up{job="node-exporter", node="{{ $node.metadata.name }}"})
+      for: 0m
+      labels:
+        severity: critical
+{{ end }}
     - alert: NodeFilesystemSpaceFillingUp
       annotations:
         description: Filesystem on {{ `{{` }} $labels.device }} at {{ `{{` }} $labels.instance }} has only {{ `{{` }} printf "%.2f" $value }}% available space left and is filling up.

templates/PrometheusRule-prometheus.yaml

@@ -3,14 +3,14 @@ apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
-  name: prometheus-k8s-prometheus-rules
+  name: prometheus-{{ $.Release.Name }}-prometheus-rules
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
 spec:
   groups:
@@ -24,7 +24,7 @@ spec:
       expr: |
         # Without max_over_time, failed scrapes could create false negatives, see
         # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
-        max_over_time(prometheus_config_last_reload_successful{job="prometheus-k8s",namespace="monitoring"}[5m]) == 0
+        max_over_time(prometheus_config_last_reload_successful{job="prometheus",namespace="monitoring"}[5m]) == 0
       for: 10m
       labels:
         severity: critical
@@ -37,9 +37,9 @@ spec:
         # Without min_over_time, failed scrapes could create false negatives, see
         # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
         (
-          predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s",namespace="monitoring"}[5m], 60 * 30)
+          predict_linear(prometheus_notifications_queue_length{job="prometheus",namespace="monitoring"}[5m], 60 * 30)
         >
-          min_over_time(prometheus_notifications_queue_capacity{job="prometheus-k8s",namespace="monitoring"}[5m])
+          min_over_time(prometheus_notifications_queue_capacity{job="prometheus",namespace="monitoring"}[5m])
         )
       for: 15m
       labels:
@@ -51,9 +51,9 @@ spec:
         summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager.
       expr: |
         (
-          rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
+          rate(prometheus_notifications_errors_total{job="prometheus",namespace="monitoring"}[5m])
         /
-          rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
+          rate(prometheus_notifications_sent_total{job="prometheus",namespace="monitoring"}[5m])
         )
         * 100
         > 1
@@ -68,7 +68,7 @@ spec:
       expr: |
         # Without max_over_time, failed scrapes could create false negatives, see
         # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
-        max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s",namespace="monitoring"}[5m]) < 1
+        max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus",namespace="monitoring"}[5m]) < 1
       for: 10m
       labels:
         severity: warning
@@ -78,7 +78,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbreloadsfailing
         summary: Prometheus has issues reloading blocks from disk.
       expr: |
-        increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
+        increase(prometheus_tsdb_reloads_failures_total{job="prometheus",namespace="monitoring"}[3h]) > 0
       for: 4h
       labels:
         severity: warning
@@ -88,7 +88,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbcompactionsfailing
         summary: Prometheus has issues compacting blocks.
       expr: |
-        increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
+        increase(prometheus_tsdb_compactions_failed_total{job="prometheus",namespace="monitoring"}[3h]) > 0
       for: 4h
       labels:
         severity: warning
@@ -99,12 +99,12 @@ spec:
         summary: Prometheus is not ingesting samples.
       expr: |
         (
-          rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
+          rate(prometheus_tsdb_head_samples_appended_total{job="prometheus",namespace="monitoring"}[5m]) <= 0
         and
           (
-            sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus-k8s",namespace="monitoring"}) > 0
+            sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus",namespace="monitoring"}) > 0
           or
-            sum without(rule_group) (prometheus_rule_group_rules{job="prometheus-k8s",namespace="monitoring"}) > 0
+            sum without(rule_group) (prometheus_rule_group_rules{job="prometheus",namespace="monitoring"}) > 0
           )
         )
       for: 10m
@@ -116,7 +116,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusduplicatetimestamps
         summary: Prometheus is dropping samples with duplicate timestamps.
       expr: |
-        rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+        rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus",namespace="monitoring"}[5m]) > 0
       for: 10m
       labels:
         severity: warning
@@ -126,7 +126,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusoutofordertimestamps
         summary: Prometheus drops samples with out-of-order timestamps.
       expr: |
-        rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+        rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus",namespace="monitoring"}[5m]) > 0
       for: 10m
       labels:
         severity: warning
@@ -137,12 +137,12 @@ spec:
         summary: Prometheus fails to send samples to remote storage.
       expr: |
         (
-          (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-k8s",namespace="monitoring"}[5m]))
+          (rate(prometheus_remote_storage_failed_samples_total{job="prometheus",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus",namespace="monitoring"}[5m]))
         /
           (
-            (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-k8s",namespace="monitoring"}[5m]))
+            (rate(prometheus_remote_storage_failed_samples_total{job="prometheus",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus",namespace="monitoring"}[5m]))
           +
-            (rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]))
+            (rate(prometheus_remote_storage_succeeded_samples_total{job="job="prometheus",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus",namespace="monitoring"}[5m]))
           )
         )
         * 100
@@ -159,9 +159,9 @@ spec:
         # Without max_over_time, failed scrapes could create false negatives, see
         # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
         (
-          max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
+          max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus",namespace="monitoring"}[5m])
         - ignoring(remote_name, url) group_right
-          max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
+          max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus",namespace="monitoring"}[5m])
         )
         > 120
       for: 15m
@@ -169,16 +169,16 @@ spec:
         severity: critical
     - alert: PrometheusRemoteWriteDesiredShards
       annotations:
-        description: Prometheus {{ `{{` }}$labels.namespace}}/{{ `{{` }}$labels.pod}} remote write desired shards calculation wants to run {{ `{{` }} $value }} shards for queue {{ `{{` }} $labels.remote_name}}:{{ `{{` }} $labels.url }}, which is more than the max of {{ `{{` }} printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}` $labels.instance | query | first | value }}.
+        description: Prometheus {{ `{{` }}$labels.namespace}}/{{ `{{` }}$labels.pod}} remote write desired shards calculation wants to run {{ `{{` }} $value }} shards for queue {{ `{{` }} $labels.remote_name}}:{{ `{{` }} $labels.url }}, which is more than the max of {{ `{{` }} printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus",namespace="monitoring"}` $labels.instance | query | first | value }}.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards
         summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
       expr: |
         # Without max_over_time, failed scrapes could create false negatives, see
         # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
         (
-          max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="monitoring"}[5m])
+          max_over_time(prometheus_remote_storage_shards_desired{job="prometheus",namespace="monitoring"}[5m])
         >
-          max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="monitoring"}[5m])
+          max_over_time(prometheus_remote_storage_shards_max{job="prometheus",namespace="monitoring"}[5m])
         )
       for: 15m
       labels:
@@ -189,7 +189,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusrulefailures
         summary: Prometheus is failing rule evaluations.
       expr: |
-        increase(prometheus_rule_evaluation_failures_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+        increase(prometheus_rule_evaluation_failures_total{job="prometheus",namespace="monitoring"}[5m]) > 0
       for: 15m
       labels:
         severity: critical
@@ -199,7 +199,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusmissingruleevaluations
         summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
       expr: |
-        increase(prometheus_rule_group_iterations_missed_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+        increase(prometheus_rule_group_iterations_missed_total{job="prometheus",namespace="monitoring"}[5m]) > 0
       for: 15m
       labels:
         severity: warning
@@ -209,7 +209,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetlimithit
         summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit.
       expr: |
-        increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+        increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus",namespace="monitoring"}[5m]) > 0
       for: 15m
       labels:
         severity: warning
@@ -219,7 +219,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuslabellimithit
         summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit.
       expr: |
-        increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+        increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="prometheus",namespace="monitoring"}[5m]) > 0
       for: 15m
       labels:
         severity: warning
@@ -229,7 +229,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapebodysizelimithit
         summary: Prometheus has dropped some targets that exceeded body size limit.
       expr: |
-        increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+        increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="prometheus",namespace="monitoring"}[5m]) > 0
       for: 15m
       labels:
         severity: warning
@@ -239,7 +239,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapesamplelimithit
         summary: Prometheus has failed scrapes that have exceeded the configured sample limit.
       expr: |
-        increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
+        increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="prometheus",namespace="monitoring"}[5m]) > 0
       for: 15m
       labels:
         severity: warning
@@ -249,7 +249,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetsyncfailure
         summary: Prometheus has failed to sync targets.
       expr: |
-        increase(prometheus_target_sync_failed_total{job="prometheus-k8s",namespace="monitoring"}[30m]) > 0
+        increase(prometheus_target_sync_failed_total{job="prometheus",namespace="monitoring"}[30m]) > 0
       for: 5m
       labels:
         severity: critical
@@ -259,7 +259,7 @@ spec:
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheushighqueryload
         summary: Prometheus is reaching its maximum capacity serving concurrent requests.
       expr: |
-        avg_over_time(prometheus_engine_queries{job="prometheus-k8s",namespace="monitoring"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0.8
+        avg_over_time(prometheus_engine_queries{job="prometheus",namespace="monitoring"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="prometheus",namespace="monitoring"}[5m]) > 0.8
       for: 15m
       labels:
         severity: warning
@@ -270,9 +270,9 @@ spec:
         summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
       expr: |
         min without (alertmanager) (
-          rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring",alertmanager!~``}[5m])
+          rate(prometheus_notifications_errors_total{job="prometheus",namespace="monitoring",alertmanager!~``}[5m])
         /
-          rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring",alertmanager!~``}[5m])
+          rate(prometheus_notifications_sent_total{job="prometheus",namespace="monitoring",alertmanager!~``}[5m])
         )
         * 100
         > 3

templates/PrometheusRule-thanos.yaml

@@ -0,0 +1,58 @@
+{{ if .Values.nfc_monitoring.thanos.sidecar.enabled }}
+{{ if .Values.nfc_monitoring.thanos.sidecar.config }}
+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  labels:
+    app.kubernetes.io/component: metrics
+    app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/name: thanos
+    app.kubernetes.io/part-of: {{  $.Chart.Name }}
+    app.kubernetes.io/managed-by: {{  $.Release.Service }}
+    app.kubernetes.io/version: {{  $.Chart.Version }}
+    prometheus: {{ $.Release.Name }}
+    role: alert-rules
+  name: thanos-sidecar-rules
+  namespace: {{  .Values.nfc_monitoring.prometheus.namespace }}
+spec:
+  groups:
+    - name: thanos-sidecar
+      rules:
+      - alert: ThanosSidecarBucketOperationsFailed
+        annotations:
+          description: Thanos Sidecar {{ `{{` }}$labels.instance}} bucket operations are failing
+          runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanossidecarbucketoperationsfailed
+          summary: Thanos Sidecar bucket operations are failing
+        expr: |
+          sum by (job, instance) (rate(thanos_objstore_bucket_operation_failures_total{job=~".*thanos-sidecar.*"}[5m])) > 0
+        for: 5m
+        labels:
+          severity: critical
+      - alert: ThanosSidecarNoConnectionToStartedPrometheus
+        annotations:
+          description: Thanos Sidecar {{ `{{` }}$labels.instance}} is unhealthy.
+          runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanossidecarnoconnectiontostartedprometheus
+          summary: Thanos Sidecar cannot access Prometheus, even though Prometheus seems
+            healthy and has reloaded WAL.
+        expr: |
+          thanos_sidecar_prometheus_up{job=~".*thanos-sidecar.*"} == 0
+          AND on (namespace, pod)
+          prometheus_tsdb_data_replay_duration_seconds != 0
+        for: 5m
+        labels:
+          severity: critical
+      - alert: ThanosSidecarIsDown
+        annotations:
+          description: ThanosSidecar has disappeared. Prometheus target for the component
+            cannot be discovered.
+          runbook_url: https://github.com/thanos-io/thanos/tree/main/mixin/runbook.md#alert-name-thanossidecarisdown
+          summary: Thanos component has disappeared.
+        expr: |
+          absent(up{job=~".*thanos-sidecar.*"} == 1)
+        for: 5m
+        labels:
+          severity: critical
+
+{{ end }}
+{{ end }}

templates/Role-SpecificNamespaces-prometheus.yaml

@@ -2,19 +2,18 @@
 apiVersion: rbac.authorization.k8s.io/v1
 items:
 
-{{ range .Values.nfc_monitoring.prometheus.monitor_namespaces }}
+{{ range $index, $namespace := (lookup "v1" "Namespace" "" "").items }}
 - apiVersion: rbac.authorization.k8s.io/v1
   kind: Role
   metadata:
     labels:
-      app.kubernetes.io/component: prometheus
+      {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 6 }}
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: prometheus
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
       app.kubernetes.io/managed-by: {{ $.Release.Service }}
       app.kubernetes.io/version: {{ $.Chart.Version }}
-    name: prometheus-k8s
+    name: prometheus-{{ $.Release.Name }}
-    namespace: {{ . | quote }}
+    namespace: {{ $namespace.metadata.name | quote }}
   rules:
   - apiGroups:
     - ""

templates/RoleBinding-Config-prometheus.yaml

@@ -3,9 +3,8 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: RoleBinding
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -14,8 +13,8 @@ metadata:
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
-  name: prometheus-k8s-config
+  name: prometheus-{{ $.Release.Name }}-config
 subjects:
 - kind: ServiceAccount
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}

templates/RoleBinding-SpecificNamespaces-prometheus.yaml

@@ -1,26 +1,25 @@
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 items:
-{{ range .Values.nfc_monitoring.prometheus.monitor_namespaces }}
+{{ range $index, $namespace := (lookup "v1" "Namespace" "" "").items }}
 - apiVersion: rbac.authorization.k8s.io/v1
   kind: RoleBinding
   metadata:
     labels:
-      app.kubernetes.io/component: prometheus
+      {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 6 }}
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: prometheus
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
       app.kubernetes.io/managed-by: {{ $.Release.Service }}
       app.kubernetes.io/version: {{ $.Chart.Version }}
-    name: prometheus-k8s
+    name: prometheus-{{ $.Release.Name }}
-    namespace: {{ . | quote }}
+    namespace: {{ $namespace.metadata.name | quote }}
   roleRef:
     apiGroup: rbac.authorization.k8s.io
     kind: Role
-    name: prometheus-k8s
+    name: prometheus-{{ $.Release.Name }}
   subjects:
   - kind: ServiceAccount
-    name: prometheus-k8s
+    name: prometheus-{{ $.Release.Name }}
     namespace: {{ $.Values.nfc_monitoring.prometheus.namespace }}
 {{ end }}
 

templates/RoleBinding-prometheus-adapter-auth-reader.yaml

@@ -3,8 +3,8 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: RoleBinding
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus-adapter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/version: 0.11.1
   name: resource-metrics-auth-reader
   namespace: kube-system

templates/RoleConfig-prometheus.yaml

@@ -3,13 +3,12 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: Role
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: prometheus-k8s-config
+  name: prometheus-{{ $.Release.Name }}-config
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
 rules:
 - apiGroups:

templates/Secret-alertmanager.yaml

@@ -3,9 +3,8 @@ apiVersion: v1
 kind: Secret
 metadata:
   labels:
-    app.kubernetes.io/component: alert-router
+    {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: alertmanager
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/Secret-prometheus-sidecar-thanos.yaml

@@ -1,8 +1,15 @@
 {{ if .Values.nfc_monitoring.thanos.sidecar.enabled }}
+{{ if .Values.nfc_monitoring.thanos.sidecar.config }}
 ---
 apiVersion: v1
 kind: Secret
 metadata:
+  labels:
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
+    app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/part-of: {{ $.Chart.Name }}
+    app.kubernetes.io/managed-by: {{ $.Release.Service }}
+    app.kubernetes.io/version: {{ $.Chart.Version }}
   name: thanos-sidecar-config
   namespace: monitoring
 type: Opaque
@@ -11,3 +18,4 @@ stringData:
     {{ toYaml .Values.nfc_monitoring.thanos.sidecar.config | nindent 4 }}
 
 {{ end }}
+{{ end }}

templates/Service-CalicoMetrics.yaml

@@ -5,7 +5,7 @@ apiVersion: v1
 kind: Service
 metadata:
   name: calico-metrics
-  namespace: kube-system
+  namespace: calico-system
   labels:
     k8s-app: calico-node
 spec:

templates/Service-Grafana.yaml

@@ -1,22 +1,20 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 ---
-
 apiVersion: v1
 kind: Service
 metadata:
   name: grafana
   namespace: {{ .Values.nfc_monitoring.grafana.namespace }}
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
 spec:
   selector:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
   #type: NodePort
   #type: LoadBalancer
@@ -28,3 +26,5 @@ spec:
       #nodePort: 3000
   #type: LoadBalancer
   sessionAffinity: ClientIP
+
+{{- end }}

templates/Service-GrafanaAgent.yaml

@@ -5,17 +5,15 @@ metadata:
   name: grafana-agent
   namespace: monitoring
   labels:
-    app.kubernetes.io/instance: k8s
+    {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 4 }}
-    app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana-agent
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
 spec:
   selector:
-    app.kubernetes.io/instance: k8s
+    {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 4 }}
-    app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana-agent
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
   ports:
     - name: grafana-metrics

templates/Service-alertmanager.yaml

@@ -3,13 +3,12 @@ apiVersion: v1
 kind: Service
 metadata:
   labels:
-    app.kubernetes.io/component: alert-router
+    {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: alertmanager
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: alertmanager-main
+  name: alertmanager-{{ $.Release.Name }}
   namespace: {{ .Values.nfc_monitoring.alert_manager.namespace | quote }}
 spec:
   ports:
@@ -21,7 +20,7 @@ spec:
     targetPort: reloader-web
   selector:
     app.kubernetes.io/component: alert-router
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: alertmanager
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
   sessionAffinity: ClientIP

templates/Service-kube-monitor-proxy.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
 ---
 apiVersion: v1
 kind: Service
@@ -6,7 +7,7 @@ metadata:
   namespace: monitoring
   labels:
     app.kubernetes.io/component: proxy
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-monitor-proxy
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -16,7 +17,7 @@ metadata:
 spec:
   selector:
     app.kubernetes.io/component: proxy
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-monitor-proxy
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     
@@ -28,3 +29,5 @@ spec:
       port: 10259
       targetPort: kube-scheduler
   sessionAffinity: ClientIP
+
+{{ end }}

templates/Service-kubeStateMetrics.yaml

@@ -1,10 +1,11 @@
+{{ if .Values.nfc_monitoring.kube_state_metrics.enabled }}
 ---
 apiVersion: v1
 kind: Service
 metadata:
   labels:
     app.kubernetes.io/component: exporter
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -22,7 +23,8 @@ spec:
     targetPort: https-self
   selector:
     app.kubernetes.io/component: exporter
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
 
+{{ end }}

templates/Service-prometheus-adapter.yaml

@@ -3,9 +3,8 @@ apiVersion: v1
 kind: Service
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -17,7 +16,6 @@ spec:
     port: 443
     targetPort: 6443
   selector:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}

templates/Service-prometheus.yaml

@@ -3,13 +3,12 @@ apiVersion: v1
 kind: Service
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
 spec:
   ports:
@@ -20,9 +19,8 @@ spec:
     port: 8080
     targetPort: reloader-web
   selector:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
   sessionAffinity: ClientIP
 
@@ -34,7 +32,7 @@ kind: Service
 metadata:
   labels:
     app.kubernetes.io/component: prometheus-sidecar
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: thanos-sidecar
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
@@ -51,9 +49,7 @@ spec:
     port: 10902
     targetPort: 10902
   selector:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus
-    app.kubernetes.io/part-of: {{ $.Chart.Name }}
 
 {{ end }}

templates/ServiceAccount-Grafana.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 ---
 apiVersion: v1
 automountServiceAccountToken: false
@@ -6,9 +7,10 @@ metadata:
   name: grafana
   namespace: {{ .Values.nfc_monitoring.grafana.namespace }}
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
+
+{{- end }}

templates/ServiceAccount-GrafanaAgent.yaml

@@ -6,9 +6,8 @@ metadata:
   name: grafana-agent
   namespace: monitoring
   labels:
-    app.kubernetes.io/instance: k8s
+    {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 4 }}
-    app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana-agent
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ServiceAccount-alertmanager.yaml

@@ -4,9 +4,8 @@ automountServiceAccountToken: false
 kind: ServiceAccount
 metadata:
   labels:
-    app.kubernetes.io/component: alert-router
+    {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: alertmanager
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ServiceAccount-kube-monitor-proxy.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
 ---
 apiVersion: v1
 kind: ServiceAccount
@@ -6,8 +7,10 @@ metadata:
   namespace: monitoring
   labels:
     app.kubernetes.io/component: proxy
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-monitor-proxy
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
+
+{{ end }}

templates/ServiceAccount-kubeStateMetrics.yaml

@@ -1,3 +1,4 @@
+{{ if .Values.nfc_monitoring.kube_state_metrics.enabled }}
 ---
 apiVersion: v1
 automountServiceAccountToken: false
@@ -5,10 +6,12 @@ kind: ServiceAccount
 metadata:
   labels:
     app.kubernetes.io/component: exporter
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
   name: kube-state-metrics
   namespace: monitoring
+
+{{ end }}

templates/ServiceAccount-prometheus-adapter.yaml

@@ -4,9 +4,8 @@ automountServiceAccountToken: false
 kind: ServiceAccount
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}

templates/ServiceAccount-prometheus.yaml

@@ -4,11 +4,10 @@ automountServiceAccountToken: true
 kind: ServiceAccount
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}

templates/ServiceMonitor-APIServer.yaml

@@ -1,8 +1,10 @@
+{{ if .Values.nfc_monitoring.prometheus.service_monitor.apiserver }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: apiserver
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -76,3 +78,5 @@ spec:
     matchLabels:
       component: apiserver
       provider: kubernetes
+
+{{ end }}

templates/ServiceMonitor-Cadvisor.yaml

@@ -1,8 +1,10 @@
+{{ if .Values.nfc_monitoring.prometheus.service_monitor.cadvisor }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: cadvisor
     app.kubernetes.io/component: exporter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -50,3 +52,5 @@ spec:
   selector:
     matchLabels:
       app.kubernetes.io/name: kubelet
+
+{{ end }}

templates/ServiceMonitor-Calico.yaml

@@ -1,10 +1,12 @@
 ---
 {{- if eq .Values.nfc_monitoring.kubernetes.networking "calico" -}}
+{{ if .Values.nfc_monitoring.prometheus.service_monitor.calico }}
 
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: calico
     app.kubernetes.io/component: networking
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -12,7 +14,7 @@ metadata:
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     k8s-app: calico-node
   name: calico
-  namespace: kube-system
+  namespace: calico-system
 spec:
   endpoints:
   - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
@@ -34,3 +36,4 @@ spec:
       k8s-app: calico-node
 
 {{- end -}}
+{{ end }}

templates/ServiceMonitor-CoreDNS.yaml

@@ -1,8 +1,10 @@
+{{ if .Values.nfc_monitoring.prometheus.service_monitor.coredns }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: coredns
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -26,3 +28,5 @@ spec:
   selector:
     matchLabels:
       k8s-app: kube-dns
+
+{{ end }}

templates/ServiceMonitor-Grafana.yaml

@@ -1,11 +1,11 @@
+{{ if .Values.nfc_monitoring.grafana.enabled -}}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
-    app.kubernetes.io/component: graphing
+    {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 4 }}
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: grafana
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -31,7 +31,9 @@ spec:
   jobLabel: app.kubernetes.io/name
   selector:
     matchLabels:
-      app.kubernetes.io/component: graphing
+      {{ toYaml $.Values.nfc_monitoring.grafana.labels | nindent 6 }}
-      app.kubernetes.io/instance: k8s
-      app.kubernetes.io/name: grafana
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
+      app.kubernetes.io/instance: {{ $.Release.Name }}
+
+{{- end }}
+

templates/ServiceMonitor-Kubelet.yaml

@@ -1,8 +1,10 @@
+{{ if .Values.nfc_monitoring.prometheus.service_monitor.kubelet }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kubelet
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -85,3 +87,6 @@ spec:
   selector:
     matchLabels:
       app.kubernetes.io/name: kubelet
+      app.kubernetes.io/instance: {{ $.Release.Name }}
+
+{{ end }}

templates/ServiceMonitor-Node.yaml

@@ -1,9 +1,11 @@
+{{ if .Values.nfc_monitoring.grafana_agent.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
     app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: node
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -35,9 +37,46 @@ spec:
       sourceLabels:
       - __meta_kubernetes_pod_node_name
       targetLabel: node
+    metricRelabelings:
+      - action: drop
+        sourceLabels: [__name__]
+        regex: '(promtail_).*'
+
+  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
+    interval: 5s
+    honorLabels: true
+    path: /metrics
+    port: grafana-metrics
+    scheme: http
+    relabelings:
+    - action: replace
+      regex: (.*)
+      replacement: $1
+      sourceLabels:
+      - __meta_kubernetes_pod_node_name
+      targetLabel: instance
+    - targetLabel: "job"
+      replacement: "promtail"
+    - action: replace
+      regex: (.*)
+      replacement: $1
+      sourceLabels:
+      - __meta_kubernetes_pod_node_name
+      targetLabel: node
+    - action: replace
+      separator: /
+      sourceLabels:
+      - namespace
+      - job
+      targetLabel: job
+    metricRelabelings:
+      - action: keep
+        sourceLabels: [__name__]
+        regex: '(promtail_).*'
   selector:
     matchLabels:
-      app.kubernetes.io/instance: k8s
+      {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 6 }}
-      app.kubernetes.io/component: exporter
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: grafana-agent
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+{{ end }}

templates/ServiceMonitor-ceph.yaml

@@ -7,6 +7,7 @@ metadata:
   labels:
     app.kubernetes.io/name: ceph
     app.kubernetes.io/component: storage
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}

templates/ServiceMonitor-kube-controller-manager.yaml

@@ -1,10 +1,12 @@
+{{ if .Values.nfc_monitoring.prometheus.service_monitor.kube_controller_manager }}
+{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
     app.kubernetes.io/component: proxy
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-controller-manager
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -77,6 +79,9 @@ spec:
       insecureSkipVerify: true
   selector:
     matchLabels:
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: kube-monitor-proxy
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+{{ end }}
+{{ end }}

templates/ServiceMonitor-kube-scheduler.yaml

@@ -1,10 +1,12 @@
+{{ if .Values.nfc_monitoring.prometheus.service_monitor.kube_scheduler }}
+{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
     app.kubernetes.io/component: proxy
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-scheduler
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -31,6 +33,9 @@ spec:
       insecureSkipVerify: true
   selector:
     matchLabels:
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: kube-monitor-proxy
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+{{ end }}
+{{ end }}

templates/ServiceMonitor-kubeStateMetrics.yaml

@@ -1,10 +1,11 @@
+{{ if .Values.nfc_monitoring.kube_state_metrics.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
     app.kubernetes.io/component: exporter
-    app.kubernetes.io/instance: k8s
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
@@ -41,6 +42,8 @@ spec:
   selector:
     matchLabels:
       app.kubernetes.io/component: exporter
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: kube-state-metrics
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+{{ end }}

templates/ServiceMonitor-node-exporter.yaml

@@ -1,9 +1,11 @@
+{{ if .Values.nfc_monitoring.grafana_agent.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
     app.kubernetes.io/component: exporter
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: node-exporter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -38,7 +40,8 @@ spec:
       insecureSkipVerify: true
   selector:
     matchLabels:
-      app.kubernetes.io/instance: k8s
+      {{ toYaml $.Values.nfc_monitoring.grafana_agent.labels | nindent 6 }}
-      app.kubernetes.io/component: exporter
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: grafana-agent
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+{{ end }}

templates/ServiceMonitor-prometheus-adapter.yaml

@@ -1,11 +1,11 @@
+{{ if .Values.nfc_monitoring.prometheus_adaptor.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
-    app.kubernetes.io/component: metrics-adapter
+    {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: prometheus-adapter
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -33,7 +33,8 @@ spec:
       insecureSkipVerify: true
   selector:
     matchLabels:
-      app.kubernetes.io/component: metrics-adapter
+      {{ toYaml $.Values.nfc_monitoring.prometheus_adaptor.labels | nindent 6 }}
-      app.kubernetes.io/instance: main
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: prometheus-adapter
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+{{ end }}

templates/ServiceMonitor-prometheus.yaml

@@ -1,14 +1,15 @@
+{{ if .Values.nfc_monitoring.prometheus.enabled }}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
-    app.kubernetes.io/component: prometheus
+    {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 4 }}
-    app.kubernetes.io/name: prometheus
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-  name: prometheus-k8s
+  name: prometheus-{{ $.Release.Name }}
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
 spec:
   endpoints:
@@ -21,23 +22,26 @@ spec:
       sourceLabels:
       - __meta_kubernetes_pod_name
       targetLabel: instance
+    - targetLabel: "job"
+      replacement: "prometheus"
   - interval: 30s
     port: reloader-web
   selector:
     matchLabels:
-      app.kubernetes.io/component: prometheus
+      {{ toYaml $.Values.nfc_monitoring.prometheus.labels | nindent 6 }}
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: prometheus
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
 
 {{ if .Values.nfc_monitoring.thanos.sidecar.enabled }}
+{{ if .Values.nfc_monitoring.thanos.sidecar.config }}
+
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
     app.kubernetes.io/component: prometheus-sidecar
-    app.kubernetes.io/instance: thanos-sidecar
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: thanos-sidecar
     app.kubernetes.io/version: v0.30.2
   name: thanos-sidecar
@@ -55,8 +59,10 @@ spec:
   selector:
     matchLabels:
       app.kubernetes.io/component: prometheus-sidecar
-      app.kubernetes.io/instance: k8s
+      app.kubernetes.io/instance: {{ $.Release.Name }}
       app.kubernetes.io/name: thanos-sidecar
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
 
 {{ end }}
+{{ end }}
+{{ end }}

templates/prometheusRule-ceph.yaml

@@ -6,11 +6,12 @@ kind: PrometheusRule
 metadata:
   labels:
     app.kubernetes.io/component: storage
+    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/name: ceph
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
-    prometheus: k8s
+    prometheus: {{ $.Release.Name }}
     role: alert-rules
   name: ceph-rules
   namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}

templates/serviceMonitor-alertmanager.yaml

@@ -1,11 +1,11 @@
+{{ if .Values.nfc_monitoring.alert_manager.enabled -}}
 ---
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
-    app.kubernetes.io/component: alert-router
+    {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 4 }}
-    app.kubernetes.io/instance: main
+    app.kubernetes.io/instance: {{ $.Release.Name }}
-    app.kubernetes.io/name: alertmanager
     app.kubernetes.io/part-of: {{ $.Chart.Name }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/version: {{ $.Chart.Version }}
@@ -16,14 +16,30 @@ spec:
   endpoints:
   - interval: 30s
     port: web
+    relabelings:
+    - action: replace
+      regex: (.*)
+      replacement: $1
+      sourceLabels:
+      - __meta_kubernetes_pod_name
+      targetLabel: instance
   - interval: 30s
     port: reloader-web
+    relabelings:
+    - action: replace
+      regex: (.*)
+      replacement: $1
+      sourceLabels:
+      - __meta_kubernetes_pod_name
+      targetLabel: instance
+    
   namespaceSelector:
     matchNames:
     - "{{ .Values.nfc_monitoring.alert_manager.namespace }}"
   selector:
     matchLabels:
-      app.kubernetes.io/component: alert-router
+      {{ toYaml $.Values.nfc_monitoring.alert_manager.labels | nindent 6 }}
-      app.kubernetes.io/instance: main
+      app.kubernetes.io/instance: {{ $.Release.Name }}
-      app.kubernetes.io/name: alertmanager
       app.kubernetes.io/part-of: {{ $.Chart.Name }}
+
+{{ end }}

values.yaml

@@ -12,25 +12,85 @@ nfc_monitoring:
 
 
   alert_manager:
+
+    enabled: true 
     image: 
       name: quay.io/prometheus/alertmanager
       tag: 'v0.26.0'
+
+    # How many replicas to deploy
+    replicas: 1
+
+
+    ingress:
+      annotations:
+        cert-manager.io/cluster-issuer: "selfsigned-issuer"
+        nginx.ingress.kubernetes.io/ssl-redirect: "true"
+      
+      enabled: false
+
+      hostname: alert-manager.local
+
+    
+    labels:
+      app.kubernetes.io/component: alert-router
+      app.kubernetes.io/name: alertmanager
+
     namespace: alerting
 
 
   grafana:
 
+    dashboards:
+      cert_manager: false
+
+    enabled: false
+
+    # Grafana Configuration
+    # Type: Dict
+    # See: https://grafana.com/docs/grafana/latest/setup-grafana/configure-grafana
+    config:
+      analytics:
+        enabled: 'false'
+      # database:
+      #   type: mysql
+      #   host: mariadb-galera.mariadb.svc:3306
+      #   name: grafana
+      #   user: root
+      #   password: admin
+
+      log:
+        mode: "console"
+      auth:
+        disable_login_form: "false"
+      security:
         admin_user: admin
         admin_password: admin
 
     image: 
       name: grafana/grafana
-      tag: '10.1.2' # '10.0.5'
+      tag: '10.3.1' # '10.0.5'
+
+    ingress:
+      annotations:
+        cert-manager.io/cluster-issuer: "selfsigned-issuer"
+        nginx.ingress.kubernetes.io/ssl-redirect: "true"
+      
+      enabled: true
+      
+      hostname:  grafana.local
+
+
+    labels:
+      app.kubernetes.io/component: graphing
+      app.kubernetes.io/name: grafana
 
     namespace: grafana
 
     replicas: 1
 
+    # storage_accessModes: ReadWriteMany
+
     affinity: 
       nodeAffinity:
         preferredDuringSchedulingIgnoredDuringExecution:
@@ -93,23 +153,23 @@ nfc_monitoring:
       #     prometheusType: Mimir
       #   editable: true
 
-      - name: prometheus
+      # - name: prometheus
-        type: prometheus
+      #   type: prometheus
-        access: proxy
+      #   access: proxy
-        url: "http://prometheus-k8s.{{ .Values.nfc_monitoring.prometheus.namespace }}.svc:9090"
+      #   url: "http://prometheus-k8s.{{ .Values.nfc_monitoring.prometheus.namespace }}.svc:9090"
-        isDefault: true
+      #   isDefault: true
-        jsonData:
+      #   jsonData:
-          manageAlerts: true
+      #     manageAlerts: true
-          orgId: 1
+      #     orgId: 1
-          prometheusType: Prometheus
+      #     prometheusType: Prometheus
-          prometheusVersion: 2.42.0
+      #     prometheusVersion: 2.42.0
-        editable: true
+      #   editable: true
 
       - name: thanos
         type: prometheus
         access: proxy
         url: "http://thanos-query.metrics.svc:9090"
-        isDefault: false
+        isDefault: true
         jsonData:
           manageAlerts: true
           orgId: 1
@@ -119,9 +179,17 @@ nfc_monitoring:
 
 
   grafana_agent:
+
+    enabled: true 
+
     image: 
       name: grafana/agent
-      tag: 'v0.36.1'
+      tag: 'v0.39.2'
+
+    labels:
+      app.kubernetes.io/component: exporter
+      app.kubernetes.io/name: grafana-agent
+
     namespace: monitoring
 
 
@@ -135,9 +203,11 @@ nfc_monitoring:
 
     namespace: logging
 
+    # If no config is setup, logging will not be enabled.
+    config: {}
     # service name and port are used for the connection to your loki instance
-    service_name: loki-gateway
+    # service_name: loki-gateway
-    service_port: 80
+    # service_port: 80
 
     ServiceMonitor:
       selector:
@@ -147,10 +217,12 @@ nfc_monitoring:
 
 
   kube_monitor_proxy:
+    enabled: false
     namespace: monitoring
 
 
   kube_rbac_proxy:
+
     # This image is used as part of kube-monitor-proxy.
     image: 
       name: quay.io/brancz/kube-rbac-proxy
@@ -158,6 +230,8 @@ nfc_monitoring:
 
 
   kube_state_metrics:
+
+    enabled: false
     image: 
       name: registry.k8s.io/kube-state-metrics/kube-state-metrics
       tag: 'v2.8.1'
@@ -168,7 +242,43 @@ nfc_monitoring:
 
     image:
       name: prom/prometheus
-      tag: 'v2.47.0'
+      tag: 'v2.49.0'
+
+    # How many replicas to deploy
+    replicas: 1
+
+    # alertmanagers:
+    #   - name: 
+
+    # Configure prometheus to write metrics to remote host
+    # below example config uses a secret named "prometheus-remote-write" with two keys username and password.
+    # Documentation: https://prometheus-operator.dev/docs/operator/api/#monitoring.coreos.com/v1.RemoteWriteSpec
+    remotewrite: {}
+      # url:
+      # name:
+      # remoteTimeout: 30
+      # writeRelabelConfigs:
+      # basicAuth:
+      #   username:
+      #     name: prometheus-remote-write
+      #     key: username
+      #   password:
+      #     name: prometheus-remote-write
+      #     key: password
+
+
+    ingress:
+      annotations:
+        cert-manager.io/cluster-issuer: "selfsigned-issuer"
+        nginx.ingress.kubernetes.io/ssl-redirect: "true"
+      enabled: true
+      hostname:  prometheus.local
+
+    
+    # These labels are appended to all Prometheus items and are also the selector labels
+    labels:
+      app.kubernetes.io/component: prometheus
+      app.kubernetes.io/name: prometheus
 
     namespace: monitoring
 
@@ -197,28 +307,11 @@ nfc_monitoring:
             topologyKey: kubernetes.io/hostname
           weight: 10
 
-    # List of namespaces that prometheus is to monitor
-    # used to create Roles and RoleBindings
-    # type: list
-    monitor_namespaces:
-      - alerting
-      - default
-      # - ceph
-      - grafana
-      - monitoring
-      # - kube-dashboard
-      # - kube-metrics
-      - kube-policy
-      - kube-system
-      - logging
-      # - mariadb
-      # - olm
-      # - operators
 
     # Deploy a generate policy for kyverno to create Role and RoleBindings
     # for the prometheus service account so it can monitor
     # new/existing namespaces
-    kyverno_role_policy: true
+    kyverno_role_policy: false
 
     storage:
       volumeClaimTemplate:
@@ -232,19 +325,40 @@ nfc_monitoring:
     # Additional settings for Prometheus.
     # See: https://prometheus-operator.dev/docs/operator/api/#monitoring.coreos.com/v1.PrometheusSpec
     # Type: dict
-    additional: {}
+    additional:
 
+      # Don't declare remoteWrite Here, as it's don at path .prometheus.remote_write
       # remoteWrite: 
-      #   - name: mimir
+
-      #     url: http://mimir-gateway.metrics.svc.cluster.local/api/v1/push
+      retention: 24h
+      retentionSize: 2GB
+      ruleSelector:
+        matchLabels:
+          role: alert-rules
+
+    service_monitor:
+      apiserver: false
+      cadvisor: false
+      calico: false
+      ceph: false
+      coredns: false
+      kube_controller_manager: false
+      kubelet: false
+      kube_scheduler: false
 
 
   prometheus_adaptor:
 
+    enalbed: false
+
     image:
       name: registry.k8s.io/prometheus-adapter/prometheus-adapter
       tag: 'v0.11.1'
 
+    labels:
+      app.kubernetes.io/component: metrics-adapter
+      app.kubernetes.io/name: prometheus-adapter
+
     namespace: monitoring
 
     affinity: 
@@ -284,20 +398,22 @@ nfc_monitoring:
 
       enabled: true
       
-      config:
+      # Config must be specified for the sidecar to deploy
-        type: S3
+      config: {}
-        config:
+      #   type: S3
-          bucket: "thanos-metrics"
+      #   config:
-          endpoint: "rook-ceph-rgw-earth.ceph.svc:80"
+      #     bucket: "thanos-metrics"
-          access_key: "7J5NM2MNCDB4T4Y9OKJ5"
+      #     endpoint: "rook-ceph-rgw-earth.ceph.svc:80"
-          secret_key: "t9r69RzZdWEBL3NCKiUIpDk6j5625xc6HucusiGG"
+      #     access_key: "7J5NM2MNCDB4T4Y9OKJ5"
+      #     secret_key: "t9r69RzZdWEBL3NCKiUIpDk6j5625xc6HucusiGG"
+      #     insecure: true
 
 
   additions:
 
     ceph:
 
-      enabled: true
+      enabled: false
 
       namespace: ceph
 
@@ -312,7 +428,7 @@ nfc_monitoring:
     # Add sidecar to grafana pod to load dashboards from configMap
     dashboard_sidecar: 
       
-      enabled: true
+      enabled: false
 
       image:
         name: ghcr.io/kiwigrid/k8s-sidecar
@@ -322,6 +438,11 @@ nfc_monitoring:
       label_value: "1"
 
 
+  network_policy:
+    
+    enabled: false
+
+
 loki_instance:
   image: 
     name: grafana/loki