feat(monitoring): Move to Prometheus operator

Changes the implementation of Prometheus to use its Operator instead of the regular configmap implementation.
This allows the deployment of metrics through independent ServiceMonitors instead of a centralized ConfigMap.
This update is reflated in Grfana's datasources.

README.md

@@ -2,22 +2,22 @@
 
 | Name                    | Usage                                | Accessibility    | Host                    | DB type    | Additional data      | Backup configuration | Loki integration | Prometheus integration | Secret management      | Status                            | Standalone migration |
 |-------------------------|--------------------------------------|------------------|-------------------------|------------|----------------------|----------------------|------------------|------------------------|------------------------|-----------------------------------|----------------------|
-| Traefik                 | Reverse proxy and load balancer      | Public & Private | Socrates & Pythagoras-b | -          | -                    | -                    | Configured       | Configured             | -                      | Completed<sup>5</sup>             | Backbone             |
+| Traefik                 | Reverse proxy and load balancer      | Public & Private | Socrates & Pythagoras-b | -          | -                    | -                    | Configured       | Not configured         | -                      | Completed<sup>5</sup>             | Backbone             |
 | ArgoCD                  | Declarative GitOPS CD                | Private          | Pythagoras-b            | -          | -                    | -                    | Configured       | Configured             | -                      | Completed                         | Backbone             |
 | Vaultwarden             | Password manager                     | Public           | Pythagoras-b            | PostgreSQL | -                    | 4AM K8s CronJob      | Configured       | Not available          | Configured             | Completed                         | Completed            |
-| Gitlab                  | Version control system               | Public           | Pythagoras-b            | PostgreSQL | User created content | 5AM internal CronJob | Configured       | Configured             | Not configured         | Partial<sup>4</sup>               | Awaiting             |
+| Radarr                  | Movie collection manager             | Private          | Plato                   | PostgreSQL | -                    | -                    | Configured       | Not configured         | Not configured         | Partial                           | Awaiting             |
-| Radarr                  | Movie collection manager             | Private          | Plato                   | PostgreSQL | -                    | -                    | Configured       | Configured             | Not configured         | Partial                           | Awaiting             |
+| Gitlab                  | Version control system               | Public           | Pythagoras-b            | PostgreSQL | User created content | 5AM internal CronJob | Configured       | Not configured         | Not configured         | Partial<sup>4</sup>               | Awaiting             |
 | Flaresolverr            | Cloudflare proxy                     | Private          | Plato                   | -          | -                    | -                    | -                | -                      | -                      | Completed                         | Awaiting             |
-| Prometheus              | Metrics aggregator                   | Private          | Pythagoras-b            | TBD        | -                    | Not configured       | Configured       | Configured             | Not configured         | Partial                           | Awaiting             |
+| Prometheus              | Metrics aggregator                   | Private          | Pythagoras-b            | TBD        | -                    | Not configured       | Configured       | Not configured         | Not configured         | Partial                           | Awaiting             |
-| Loki                    | Log aggregator                       | Private          | Pythagoras-b            | TBD        | -                    | Not configured       | Configured       | Configured             | Not configured         | Partial                           | Awaiting             |
+| Loki                    | Log aggregator                       | Private          | Pythagoras-b            | TBD        | -                    | Not configured       | Configured       | Not configured         | Not configured         | Partial                           | Awaiting             |
-| Grafana                 | Graph visualizer                     | Public           | Pythagoras-b            | -          | -                    | Not configured       | Configured       | Configured             | Configured             | Partial                           | Awaiting             |
+| Grafana                 | Graph visualizer                     | Public           | Pythagoras-b            | -          | -                    | Not configured       | Configured       | Not configured         | Configured             | Partial                           | Awaiting             |
-| Sonarr                  | TV shows collection manager          | Private          | Plato                   | SQLite     | -                    | Not configured       | Configured       | Configured             | Not configured         | Partial                           | Awaiting             |
+| Sonarr                  | TV shows collection manager          | Private          | Plato                   | SQLite     | -                    | Not configured       | Configured       | Not configured         | Not configured         | Partial                           | Awaiting             |
 | Prowlarr                | Torrent indexer                      | Private          | Plato                   | PostgreSQL | -                    | Not configured       | Configured       | Not available          | Not configured         | Partial                           | Awaiting             |
-| Jellyfin                | Media streaming                      | Public           | Archimedes              | SQLite**   | -                    | -                    | Configured       | Configured             | Configured<sup>6</sup> | Completed                         | Awaiting             |
+| Jellyfin                | Media streaming                      | Public           | Archimedes              | SQLite**   | -                    | -                    | Configured       | Not configured             | Configured<sup>6</sup> | Completed                         | Awaiting             |
 | Jellyseerr              | Media requesting WebUI               | Public           | Pythagoras-b            | -          | -                    | -                    | Not configured   | Not available          | Configured<sup>7</sup> | Awaiting configuration            | Awaiting             |
 | Adguard                 | DNS ad blocker and custom DNS server | Private          | Socrates                | -          | -                    | -                    | Not configured   | Not configured         | Not configured         | Pending configuration<sup>1</sup> | Awaiting             |
 | Owncloud Infinity Scale | File hosting webUI                   | Public           | Plato                   | ?          | Drive files          | Not configured       | Configured       | Not available          | Not configured         | Pending configuration<sup>2</sup> | Awaiting             |
-| Synapse                 | Matrix server - Message centralizer  | Public           | Pythagoras-b            | PostgreSQL | User medias          | 4AM K8s CronJob      | Configured       | Configured             | Not configured         | Pending configuration<sup>3</sup> | Awaiting             |
+| Synapse                 | Matrix server - Message centralizer  | Public           | Pythagoras-b            | PostgreSQL | User medias          | 4AM K8s CronJob      | Configured       | Not configured             | Not configured         | Pending configuration<sup>3</sup> | Awaiting             |
 | therbron.com            | Personal website                     | Public           | Socrates                | -          | -                    | -                    | Not configured   | Not configured         | -                      | Awaiting configuration            | Awaiting             |
 | Home assistant          | Home automation and monitoring       | Private          | Pythagoras-a            | MariaDB    | -                    | Not configured       | Not configured   | Not configured         | Not configured         | Awaiting configuration            | Awaiting             |
 | Vikunja                 | To-do and Kanban boards              | Public           | Pythagoras-b            | -          | -                    | -                    | Not configured   | Not configured         | -                      | Migrate to Gitlab                 | Awaiting             |
@@ -65,7 +65,7 @@ longhorn
 ## TODO
 - Add AntiAffinities to `outsider` nodes
 - Migrate Homeassistant to PostgreSQL instead of MariaDB
-- Move Prometheus connection management to ServiceMonitors instead of ConfigMap
+- ~~Move Prometheus connection management to ServiceMonitors instead of ConfigMap~~
 - Schedule longhorn S3 backups
 - ~~Migrate Vaultwarden to PostgreSQL instead of MariaDB~~
 - ~~Deploy PostgresQL cluster using operator for database HA and easy maintenance~~ - To be tested properly

monitoring/grafana/datasources.yaml

@@ -24,6 +24,6 @@ data:
     - name: Prometheus
       type: prometheus
       access: proxy
-      url: "http://prometheus-svc:9090"
+      url: "http://prometheus-operated:9090"
       version: 1
       isDefault: false

monitoring/prometheus/clusterrole.yaml

@@ -6,29 +6,19 @@ rules:
   - apiGroups: [""]
     resources:
       - nodes
-      - nodes/proxy
+      - nodes/metrics
       - services
       - endpoints
       - pods
-    verbs: ["get", "list", "watch"]
+    verbs: ["get", "list","watch"]
+  - apiGroups: [""]
+    resources:
+      - configmaps
+    verbs: ["get"]
   - apiGroups: 
-    - extensions
+      - networking.k8s.io
     resources:
       - ingresses
     verbs: ["get", "list", "watch"]
   - nonResourceURLs: ["/metrics"]
     verbs: ["get"]
-
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: prometheus
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: prometheus
-subjects:
-- kind: ServiceAccount
-  name: default
-  namespace: monitoring

monitoring/prometheus/clusterrolebinding.yaml

@@ -0,0 +1,12 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+  - kind: ServiceAccount
+    name: prometheus
+    namespace: monitoring

monitoring/prometheus/configmap.yaml

@@ -1,227 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: prometheus-server-conf
-  labels:
-    name: prometheus-server-conf
-  namespace: monitoring
-data:
-  prometheus.rules: |-
-    groups:
-    - name: devopscube demo alert
-      rules:
-      - alert: High Pod Memory
-        expr: sum(container_memory_usage_bytes) > 1
-        for: 1m
-        labels:
-          severity: slack
-        annotations:
-          summary: High Memory Usage
-  prometheus.yml: |-
-    global:
-      scrape_interval: 5s
-      evaluation_interval: 5s
-    rule_files:
-      - /etc/prometheus/prometheus.rules
-    alerting:
-      alertmanagers:
-      - scheme: http
-        static_configs:
-        - targets:
-          - "alertmanager.monitoring.svc:9093"
-
-    scrape_configs:
-      - job_name: 'gitlab-node_metrics'
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local:9100
-      - job_name: 'gitlab-workhorse_metrics'
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local:9229
-      - job_name: 'gitlab-exporter-database_metrics'
-        metrics_path: "/database"
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local:9168
-      - job_name: 'gitab-exporter-sidekiq_metrics'
-        metrics_path: "/sidekiq"
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local:9168
-      - job_name: 'gitlab-sidekiq_metrics'
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local:8082
-      - job_name: 'gitlab-redis_metrics'
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local:9121
-      - job_name: 'gitlab-postgres_metrics'
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local:9187
-      - job_name: 'gitlab-gitaly_metrics'
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local:9236
-      - job_name: 'gitlab-rails_metrics'
-        metrics_path: "/-/metrics"
-        scheme: https
-        static_configs: 
-        - targets:
-          - gitlab-svc.gitlab.svc.cluster.local
-      - job_name: 'synapse'
-        scrape_interval: 15s
-        metrics_path: "/_synapse/metrics"
-        static_configs:
-        - targets: 
-          - synapse-svc.synapse.svc.cluster.local:9000
-      - job_name: 'sonarr'
-        static_configs:
-        - targets:
-          - sonarr-svc.torrent.svc.cluster.local:9707
-      - job_name: 'radarr'
-        static_configs:
-        - targets:
-          - radarr-svc.torrent.svc.cluster.local:9707
-      - job_name: 'prowlarr'
-        static_configs:
-        - targets:
-          - prowlarr-svc.torrent.svc.cluster.local:9707
-      - job_name: 'jellyfin'
-        metrics_path: "/metrics"
-        static_configs:
-        - targets:
-          - jellyfin-svc.streaming.svc.cluster.local:80
-      - job_name: 'node-exporter'
-        kubernetes_sd_configs:
-          - role: endpoints
-        relabel_configs:
-        - source_labels: [__meta_kubernetes_endpoints_name]
-          regex: 'node-exporter'
-          action: keep
-      - job_name: 'argocd'
-        metrics_path: "/metrics"
-        static_configs:
-        - targets:
-          - argocd-metrics.argocd.svc.cluster.local:8082
-      
-      - job_name: 'kubernetes-apiservers'
-
-        kubernetes_sd_configs:
-        - role: endpoints
-        scheme: https
-
-        tls_config:
-          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
-
-        relabel_configs:
-        - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
-          action: keep
-          regex: default;kubernetes;https
-
-      - job_name: 'kubernetes-nodes'
-
-        scheme: https
-
-        tls_config:
-          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
-
-        kubernetes_sd_configs:
-        - role: node
-
-        relabel_configs:
-        - action: labelmap
-          regex: __meta_kubernetes_node_label_(.+)
-        - target_label: __address__
-          replacement: kubernetes.default.svc:443
-        - source_labels: [__meta_kubernetes_node_name]
-          regex: (.+)
-          target_label: __metrics_path__
-          replacement: /api/v1/nodes/${1}/proxy/metrics     
-      
-      - job_name: 'kubernetes-pods'
-
-        kubernetes_sd_configs:
-        - role: pod
-
-        relabel_configs:
-        - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
-          action: keep
-          regex: true
-        - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
-          action: replace
-          target_label: __metrics_path__
-          regex: (.+)
-        - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
-          action: replace
-          regex: ([^:]+)(?::\d+)?;(\d+)
-          replacement: $1:$2
-          target_label: __address__
-        - action: labelmap
-          regex: __meta_kubernetes_pod_label_(.+)
-        - source_labels: [__meta_kubernetes_namespace]
-          action: replace
-          target_label: kubernetes_namespace
-        - source_labels: [__meta_kubernetes_pod_name]
-          action: replace
-          target_label: kubernetes_pod_name
-      
-      - job_name: 'kube-state-metrics'
-        static_configs:
-          - targets: ['kube-state-metrics.kube-system.svc.cluster.local:8080']
-
-      - job_name: 'kubernetes-cadvisor'
-
-        scheme: https
-
-        tls_config:
-          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
-
-        kubernetes_sd_configs:
-        - role: node
-
-        relabel_configs:
-        - action: labelmap
-          regex: __meta_kubernetes_node_label_(.+)
-        - target_label: __address__
-          replacement: kubernetes.default.svc:443
-        - source_labels: [__meta_kubernetes_node_name]
-          regex: (.+)
-          target_label: __metrics_path__
-          replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
-      
-      - job_name: 'kubernetes-service-endpoints'
-
-        kubernetes_sd_configs:
-        - role: endpoints
-
-        relabel_configs:
-        - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
-          action: keep
-          regex: true
-        - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
-          action: replace
-          target_label: __scheme__
-          regex: (https?)
-        - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
-          action: replace
-          target_label: __metrics_path__
-          regex: (.+)
-        - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
-          action: replace
-          target_label: __address__
-          regex: ([^:]+)(?::\d+)?;(\d+)
-          replacement: $1:$2
-        - action: labelmap
-          regex: __meta_kubernetes_service_label_(.+)
-        - source_labels: [__meta_kubernetes_namespace]
-          action: replace
-          target_label: kubernetes_namespace
-        - source_labels: [__meta_kubernetes_service_name]
-          action: replace
-          target_label: kubernetes_name

monitoring/prometheus/deployment.yaml

@@ -1,45 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: prometheus
-  namespace: monitoring
-  labels:
-    app: prometheus
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: prometheus
-  template:
-    metadata:
-      labels:
-        app: prometheus
-    spec:
-      containers:
-        - name: prometheus
-          image: prom/prometheus
-          args:
-            - "--storage.tsdb.retention.time=12h"
-            - "--config.file=/etc/prometheus/prometheus.yml"
-            - "--storage.tsdb.path=/prometheus/"
-          ports:
-            - containerPort: 9090
-          resources:
-            requests:
-              cpu: 500m
-              memory: 500M
-            limits:
-              cpu: 1
-              memory: 1Gi
-          volumeMounts:
-            - name: prometheus-config-volume
-              mountPath: /etc/prometheus
-            - name: prometheus-storage-volume
-              mountPath: /prometheus/
-      volumes:
-        - name: prometheus-config-volume
-          configMap:
-            defaultMode: 420
-            name: prometheus-server-conf
-        - name: prometheus-storage-volume
-          emptyDir: {}

monitoring/prometheus/kustomization.yaml

@@ -1,8 +1,11 @@
+
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
+namespace: monitoring
 
 resources:
+  - bundle.yaml
+  - serviceaccount.yaml
   - clusterrole.yaml
-  - configmap.yaml
+  - clusterrolebinding.yaml
-  - deployment.yaml
+  - prometheus.yaml
-  - service.yaml

monitoring/prometheus/prometheus.yaml

@@ -0,0 +1,14 @@
+apiVersion: monitoring.coreos.com/v1
+kind: Prometheus
+metadata:
+  name: prometheus
+spec:
+  serviceAccountName: prometheus
+  serviceMonitorNamespaceSelector: {}
+  serviceMonitorSelector:
+    matchLabels:
+      team: core
+  resources:
+    requests:
+      memory: 400Mi
+  enableAdminAPI: false

monitoring/prometheus/service.yaml

@@ -1,13 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: prometheus-svc
-  namespace: monitoring
-spec:
-  ports:
-    - name: http
-      port: 9090
-      protocol: TCP
-      targetPort: 9090
-  selector:
-    app: prometheus

monitoring/prometheus/serviceaccount.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: prometheus