Add kube-prometheus stack

Author: lottspot

k8s/infra/kube-prometheus/alertmanager-alertmanager.yaml

@@ -0,0 +1,18 @@
+apiVersion: monitoring.coreos.com/v1
+kind: Alertmanager
+metadata:
+  labels:
+    alertmanager: main
+  name: main
+  namespace: monitoring
+spec:
+  image: quay.io/prometheus/alertmanager:v0.20.0
+  nodeSelector:
+    kubernetes.io/os: linux
+  replicas: 3
+  securityContext:
+    fsGroup: 2000
+    runAsNonRoot: true
+    runAsUser: 1000
+  serviceAccountName: alertmanager-main
+  version: v0.20.0

k8s/infra/kube-prometheus/alertmanager-secret.yaml

@@ -0,0 +1,44 @@
+apiVersion: v1
+data: {}
+kind: Secret
+metadata:
+  name: alertmanager-main
+  namespace: monitoring
+stringData:
+  alertmanager.yaml: |-
+    "global":
+      "resolve_timeout": "5m"
+    "inhibit_rules":
+    - "equal":
+      - "namespace"
+      - "alertname"
+      "source_match":
+        "severity": "critical"
+      "target_match_re":
+        "severity": "warning|info"
+    - "equal":
+      - "namespace"
+      - "alertname"
+      "source_match":
+        "severity": "warning"
+      "target_match_re":
+        "severity": "info"
+    "receivers":
+    - "name": "Default"
+    - "name": "Watchdog"
+    - "name": "Critical"
+    "route":
+      "group_by":
+      - "namespace"
+      "group_interval": "5m"
+      "group_wait": "30s"
+      "receiver": "Default"
+      "repeat_interval": "12h"
+      "routes":
+      - "match":
+          "alertname": "Watchdog"
+        "receiver": "Watchdog"
+      - "match":
+          "severity": "critical"
+        "receiver": "Critical"
+type: Opaque

k8s/infra/kube-prometheus/alertmanager-service.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    alertmanager: main
+  name: alertmanager-main
+  namespace: monitoring
+spec:
+  ports:
+  - name: web
+    port: 9093
+    targetPort: web
+  selector:
+    alertmanager: main
+    app: alertmanager
+  sessionAffinity: ClientIP

k8s/infra/kube-prometheus/alertmanager-serviceAccount.yaml

@@ -0,0 +1,5 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: alertmanager-main
+  namespace: monitoring

k8s/infra/kube-prometheus/alertmanager-serviceMonitor.yaml

@@ -0,0 +1,14 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  labels:
+    k8s-app: alertmanager
+  name: alertmanager
+  namespace: monitoring
+spec:
+  endpoints:
+  - interval: 30s
+    port: web
+  selector:
+    matchLabels:
+      alertmanager: main

k8s/infra/kube-prometheus/grafana-dashboardDatasources.yaml

@@ -0,0 +1,8 @@
+apiVersion: v1
+data:
+  datasources.yaml: ewogICAgImFwaVZlcnNpb24iOiAxLAogICAgImRhdGFzb3VyY2VzIjogWwogICAgICAgIHsKICAgICAgICAgICAgImFjY2VzcyI6ICJwcm94eSIsCiAgICAgICAgICAgICJlZGl0YWJsZSI6IGZhbHNlLAogICAgICAgICAgICAibmFtZSI6ICJwcm9tZXRoZXVzIiwKICAgICAgICAgICAgIm9yZ0lkIjogMSwKICAgICAgICAgICAgInR5cGUiOiAicHJvbWV0aGV1cyIsCiAgICAgICAgICAgICJ1cmwiOiAiaHR0cDovL3Byb21ldGhldXMtazhzLm1vbml0b3Jpbmcuc3ZjOjkwOTAiLAogICAgICAgICAgICAidmVyc2lvbiI6IDEKICAgICAgICB9CiAgICBdCn0=
+kind: Secret
+metadata:
+  name: grafana-datasources
+  namespace: monitoring
+type: Opaque