fix(infrastructure): prometheus

tofu/modules/prometheus/grafana-ui.yaml

@@ -0,0 +1,14 @@
+apiVersion: networking.cfargotunnel.com/v1alpha1
+kind: TunnelBinding
+metadata:
+  name: grafana-tunnel-binding
+  namespace: monitoring
+subjects:
+  - name: grafana
+    spec:
+      target: http://kube-prometheus-stack-grafana.monitoring.svc.cluster.local
+      fqdn: grafana.${base_domain}
+      noTlsVerify: true
+tunnelRef:
+  kind: ClusterTunnel
+  name: cluster-tunnel

tofu/modules/prometheus/main.tf

@@ -0,0 +1,66 @@
+terraform {
+  required_providers {
+    kubectl = {
+      source  = "gavinbunney/kubectl"
+      version = "1.19.0"
+    }
+    helm = {
+      source  = "hashicorp/helm"
+      version = "3.0.2"
+    }
+    kubernetes = {
+      source  = "hashicorp/kubernetes"
+      version = "2.38.0"
+    }
+    kustomization = {
+      source  = "kbst/kustomization"
+      version = "0.9.6"
+    }
+    time = {
+      source  = "hashicorp/time"
+      version = "0.13.1"
+    }
+  }
+}
+
+# Create namespace for monitoring
+resource "kubernetes_namespace" "monitoring" {
+  metadata {
+    name = "monitoring"
+    labels = {
+      "pod-security.kubernetes.io/enforce" = "privileged"
+    }
+  }
+}
+
+# Deploy kube-prometheus-stack
+resource "helm_release" "kube_prometheus_stack" {
+  name       = "kube-prometheus-stack"
+  repository = "https://prometheus-community.github.io/helm-charts"
+  chart      = "kube-prometheus-stack"
+  namespace  = kubernetes_namespace.monitoring.metadata[0].name
+  version    = "67.2.1" # Check for latest version
+
+  # Wait for CRDs to be created
+  wait          = true
+  timeout       = 600
+  force_update  = false
+  recreate_pods = false
+
+  # Reference the values file
+  values = [
+    file("${path.module}/values.yaml")
+  ]
+
+  depends_on = [
+    kubernetes_namespace.monitoring
+  ]
+}
+
+resource "kubectl_manifest" "argocd-tunnel-bind" {
+  depends_on = [helm_release.kube_prometheus_stack]
+
+  yaml_body = templatefile("${path.module}/grafana-ui.yaml", {
+    base_domain = var.cloudflare_domain
+  })
+}

tofu/modules/prometheus/values.yaml

@@ -0,0 +1,189 @@
+# Prometheus configuration
+prometheus:
+  prometheusSpec:
+    retention: 30d
+    retentionSize: "45GB"
+
+    # Storage configuration
+    storageSpec:
+      volumeClaimTemplate:
+        spec:
+          accessModes:
+            - ReadWriteOnce
+          resources:
+            requests:
+              storage: 50Gi
+          # storageClassName: "your-storage-class" # Uncomment and specify if needed
+
+    # Resource limits
+    resources:
+      requests:
+        cpu: 500m
+        memory: 2Gi
+      limits:
+        cpu: 2000m
+        memory: 4Gi
+
+    # Scrape interval
+    scrapeInterval: 30s
+    evaluationInterval: 30s
+
+  # Service configuration
+  service:
+    type: ClusterIP
+    port: 9090
+
+  # Ingress (disabled by default)
+  ingress:
+    enabled: false
+    # ingressClassName: nginx
+    # hosts:
+    #   - prometheus.example.com
+    # tls:
+    #   - secretName: prometheus-tls
+    #     hosts:
+    #       - prometheus.example.com
+
+# Grafana configuration
+grafana:
+  enabled: true
+
+  # Admin credentials
+  adminPassword: "admin" # CHANGE THIS IN PRODUCTION!
+
+  # Persistence
+  persistence:
+    enabled: true
+    size: 10Gi
+    # storageClassName: "your-storage-class" # Uncomment and specify if needed
+
+  # Resource limits
+  resources:
+    requests:
+      cpu: 100m
+      memory: 256Mi
+    limits:
+      cpu: 500m
+      memory: 512Mi
+
+  # Service configuration
+  service:
+    type: ClusterIP
+    port: 80
+
+  # Ingress (disabled by default)
+  ingress:
+    enabled: false
+    # ingressClassName: nginx
+    # hosts:
+    #   - grafana.example.com
+    # tls:
+    #   - secretName: grafana-tls
+    #     hosts:
+    #       - grafana.example.com
+
+  # Default dashboards
+  defaultDashboardsEnabled: true
+  defaultDashboardsTimezone: Europe/Prague
+
+# Alertmanager configuration
+alertmanager:
+  enabled: true
+
+  alertmanagerSpec:
+    # Storage configuration
+    storage:
+      volumeClaimTemplate:
+        spec:
+          accessModes:
+            - ReadWriteOnce
+          resources:
+            requests:
+              storage: 10Gi
+          # storageClassName: "your-storage-class" # Uncomment and specify if needed
+
+    # Resource limits
+    resources:
+      requests:
+        cpu: 100m
+        memory: 128Mi
+      limits:
+        cpu: 500m
+        memory: 256Mi
+
+  # Service configuration
+  service:
+    type: ClusterIP
+    port: 9093
+
+  # Ingress (disabled by default)
+  ingress:
+    enabled: false
+    # ingressClassName: nginx
+    # hosts:
+    #   - alertmanager.example.com
+    # tls:
+    #   - secretName: alertmanager-tls
+    #     hosts:
+    #       - alertmanager.example.com
+
+  # Alertmanager configuration
+  config:
+    global:
+      resolve_timeout: 5m
+
+    route:
+      group_by: [ 'alertname', 'cluster', 'service' ]
+      group_wait: 10s
+      group_interval: 10s
+      repeat_interval: 12h
+      receiver: 'null'
+      routes:
+        - match:
+            alertname: Watchdog
+          receiver: 'null'
+
+    receivers:
+      - name: 'null'
+      # Add your receivers here (email, slack, pagerduty, etc.)
+      # - name: 'slack'
+      #   slack_configs:
+      #     - api_url: 'YOUR_SLACK_WEBHOOK_URL'
+      #       channel: '#alerts'
+      #       title: '{{ range .Alerts }}{{ .Annotations.summary }}\n{{ end }}'
+      #       text: '{{ range .Alerts }}{{ .Annotations.description }}\n{{ end }}'
+
+# Node Exporter
+nodeExporter:
+  enabled: true
+
+# Kube State Metrics
+kubeStateMetrics:
+  enabled: true
+
+# Prometheus Operator
+prometheusOperator:
+  enabled: true
+
+  resources:
+    requests:
+      cpu: 100m
+      memory: 128Mi
+    limits:
+      cpu: 500m
+      memory: 256Mi
+
+# Service Monitors
+# Automatically discover and monitor services with appropriate labels
+prometheus-node-exporter:
+  prometheus:
+    monitor:
+      enabled: true
+
+# Additional ServiceMonitors can be defined here
+# additionalServiceMonitors: []
+
+# Global settings
+global:
+  rbac:
+    create: true

tofu/modules/prometheus/variables.tf

@@ -0,0 +1,5 @@
+variable "cloudflare_domain" {
+  type     = string
+  default  = "Base cloudflare domain, e.g. example.com"
+  nullable = false
+}