feat: add monitoring

_apps/kissj-monitoring.yml

@@ -0,0 +1,18 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: kissj-monitoring
+  namespace: argocd
+spec:
+  destination:
+    namespace: kissj-monitoring
+    server: https://kubernetes.default.svc
+  project: kissj
+  source:
+    path: monitoring
+    repoURL: https://gitlab.mareshq.com/gitops/skautdevs/kissj.git
+    targetRevision: HEAD
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true

monitoring/Chart.lock

@@ -0,0 +1,6 @@
+dependencies:
+- name: kube-prometheus-stack
+  repository: https://prometheus-community.github.io/helm-charts
+  version: 39.11.0
+digest: sha256:2000f95ea7c9e6ac6ec0cc0ed3f08ee6adebf5e3ad383a0e8d89d80ab61439eb
+generated: "2022-09-03T10:54:33.34106+02:00"

monitoring/Chart.yaml

@@ -0,0 +1,11 @@
+apiVersion: v2
+name: prometheus-stack
+description: A Helm chart for Kubernetes
+type: application
+version: 0.1.0
+appVersion: "1.0"
+
+dependencies:
+- name: kube-prometheus-stack
+  version: 39.11.0
+  repository: https://prometheus-community.github.io/helm-charts

monitoring/values.yaml

@@ -0,0 +1,123 @@
+kube-prometheus-stack:
+  fullnameOverride: kissj
+
+  # Do not deploy Prometheus operator, since that has already been done
+  # and this is only to monitor KISSJ
+  prometheusOperator:
+    enabled: false
+
+  prometheus:
+    prometheusSpec:
+      serviceMonitorSelectorNilUsesHelmValues: false
+      podMonitorSelectorNilUsesHelmValues: false
+      ruleSelectorNilUsesHelmValues: false
+
+      storageSpec:
+        volumeClaimTemplate:
+          spec:
+            storageClassName: longhorn
+            accessModes: ["ReadWriteOnce"]
+            resources:
+              requests:
+                storage: 20Gi
+
+      serviceMonitorNamespaceSelector:
+        # Example which selects ServiceMonitors in namespaces with label "prometheus" set to "somelabel"
+        serviceMonitorNamespaceSelector:
+          matchLabels:
+            prometheus: kissj
+
+    ingress:
+      enabled: true
+      pathType: Prefix
+      annotations:
+        cert-manager.io/cluster-issuer: letsencrypt-prod
+      hosts:
+        - prometheus.kissj.cloud.mareshq.com
+      paths:
+        - /
+      tls:
+        - hosts:
+          - prometheus.kissj.cloud.mareshq.com
+          secretName: prometheus-tls
+
+    serviceMonitor:
+      selfMonitor: true
+
+  grafana:
+    fullnameOverride: kissj
+
+    defaultDashboardsEnabled: false
+
+    adminPassword: ayf@fqb9pxw7NRH8erx
+
+    ingress:
+      enabled: true
+      pathType: Prefix
+      annotations:
+        cert-manager.io/cluster-issuer: letsencrypt-prod
+      hosts:
+        - grafana.kissj.cloud.mareshq.com
+      paths:
+        - /
+      tls:
+        - hosts:
+          - grafana.kissj.cloud.mareshq.com
+          secretName: grafana-tls
+
+    serviceMonitor:
+      selfMonitor: true
+
+    persistence:
+      enabled: false
+      storageClassName: longhorn
+
+  alertmanager:
+    ingress:
+      enabled: true
+      pathType: Prefix
+      annotations:
+        cert-manager.io/cluster-issuer: letsencrypt-prod
+      hosts:
+        - alertmanager.kissj.cloud.mareshq.com
+      paths:
+        - /
+      tls:
+        - hosts:
+          - alertmanager.kissj.cloud.mareshq.com
+          secretName: alertmanager-tls
+
+    serviceMonitor:
+      selfMonitor: true
+
+    # This AM is for KISSJ, cluster components are monitored by different instance
+    kubeApiServer:
+      enabled: false
+
+    kubelet:
+      enabled: false
+
+    kubeControllerManager:
+      enabled: false
+
+    coreDns:
+      enabled: false
+
+    kubeScheduler:
+      enabled: false
+
+    kubeProxy:
+      enabled: false
+
+    kubeStateMetrics:
+      enabled: false
+
+    nodeExporter:
+      enabled: false
+
+    prometheusOperator:
+      serviceMonitor:
+        selfMonitor: false
+
+    defaultRules:
+      create: false