Merge pull request #62849 from serathius/prometheus-components

Automatic merge from submit-queue. If you want to cherry-pick this change to another branch, please follow the instructions <a href="https://github.com/kubernetes/community/blob/master/contributors/devel/cherry-picks.md">here</a>. Add other prometheus monitoring components This PR adds core prometheus monitoring components like alertmanager, kube-state-metrics, node exporter. Configuration for manifests is extracted from Helm manifests. ```release-note NONE ``` /cc @kawych @brancz

Merge pull request #62849 from serathius/prometheus-components
2f13ffb0 · Kubernetes Submit Queue · GitHub · 37f0fc01 · b691f2ab · 2f13ffb0
Unverified Commit 2f13ffb0 authored Apr 27, 2018 by Kubernetes Submit Queue Committed by GitHub Apr 27, 2018
9 changed files
--- a/cluster/addons/prometheus/alertmanager-configmap.yaml
+++ b/cluster/addons/prometheus/alertmanager-configmap.yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: alertmanager-config
+  namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: EnsureExists
+data:
+  alertmanager.yml: |
+    global: null
+    receivers:
+    - name: default-receiver
+    route:
+      group_interval: 5m
+      group_wait: 10s
+      receiver: default-receiver
+      repeat_interval: 3h
--- a/cluster/addons/prometheus/alertmanager-deployment.yaml
+++ b/cluster/addons/prometheus/alertmanager-deployment.yaml
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: alertmanager
+  namespace: kube-system
+  labels:
+    k8s-app: alertmanager
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    version: v0.14.0
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      k8s-app: alertmanager
+      version: v0.14.0
+  template:
+    metadata:
+      labels:
+        k8s-app: alertmanager
+        version: v0.14.0
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ''
+    spec:
+      priorityClassName: system-cluster-critical
+      containers:
+        - name: prometheus-alertmanager
+          image: "prom/alertmanager:v0.14.0"
+          imagePullPolicy: "IfNotPresent"
+          args:
+            - --config.file=/etc/config/alertmanager.yml
+            - --storage.path=/data
+            - --web.external-url=/
+          ports:
+            - containerPort: 9093
+          readinessProbe:
+            httpGet:
+              path: /#/status
+              port: 9093
+            initialDelaySeconds: 30
+            timeoutSeconds: 30
+          volumeMounts:
+            - name: config-volume
+              mountPath: /etc/config
+            - name: storage-volume
+              mountPath: "/data"
+              subPath: ""
+          resources:
+            limits:
+              cpu: 10m
+              memory: 50Mi
+            requests:
+              cpu: 10m
+              memory: 50Mi
+        - name: prometheus-alertmanager-configmap-reload
+          image: "jimmidyson/configmap-reload:v0.1"
+          imagePullPolicy: "IfNotPresent"
+          args:
+            - --volume-dir=/etc/config
+            - --webhook-url=http://localhost:9093/-/reload
+          volumeMounts:
+            - name: config-volume
+              mountPath: /etc/config
+              readOnly: true
+          resources:
+            limits:
+              cpu: 10m
+              memory: 10Mi
+            requests:
+              cpu: 10m
+              memory: 10Mi
+      volumes:
+        - name: config-volume
+          configMap:
+            name: alertmanager-config
+        - name: storage-volume
+          persistentVolumeClaim:
+            claimName: alertmanager
--- a/cluster/addons/prometheus/alertmanager-pvc.yaml
+++ b/cluster/addons/prometheus/alertmanager-pvc.yaml
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: alertmanager
+  namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: EnsureExists
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: "2Gi"
--- a/cluster/addons/prometheus/alertmanager-service.yaml
+++ b/cluster/addons/prometheus/alertmanager-service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: alertmanager
+  namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    kubernetes.io/name: "Alertmanager"
+spec:
+  ports:
+    - name: http
+      port: 80
+      protocol: TCP
+      targetPort: 9093
+  selector:
+    k8s-app: alertmanager 
+  type: "ClusterIP"
--- a/cluster/addons/prometheus/kube-state-metrics-deployment.yaml
+++ b/cluster/addons/prometheus/kube-state-metrics-deployment.yaml
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: kube-state-metrics
+  namespace: kube-system
+  labels:
+    k8s-app: kube-state-metrics
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    version: v1.3.0
+spec:
+  selector:
+    matchLabels:
+      k8s-app: kube-state-metrics
+      version: v1.3.0
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        k8s-app: kube-state-metrics
+        version: v1.3.0
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ''
+    spec:
+      priorityClassName: system-cluster-critical
+      serviceAccountName: kube-state-metrics
+      containers:
+      - name: kube-state-metrics
+        image: quay.io/coreos/kube-state-metrics:v1.3.0
+        ports:
+        - name: http-metrics
+          containerPort: 8080
+        - name: telemetry
+          containerPort: 8081
+        readinessProbe:
+          httpGet:
+            path: /healthz
+            port: 8080
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+      - name: addon-resizer
+        image: k8s.gcr.io/addon-resizer:1.7
+        resources:
+          limits:
+            cpu: 100m
+            memory: 30Mi
+          requests:
+            cpu: 100m
+            memory: 30Mi
+        env:
+          - name: MY_POD_NAME
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.name
+          - name: MY_POD_NAMESPACE
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.namespace
+        command:
+          - /pod_nanny
+          - --container=kube-state-metrics
+          - --cpu=100m
+          - --extra-cpu=1m
+          - --memory=100Mi
+          - --extra-memory=2Mi
+          - --threshold=5
+          - --deployment=kube-state-metrics
--- a/cluster/addons/prometheus/kube-state-metrics-rbac.yaml
+++ b/cluster/addons/prometheus/kube-state-metrics-rbac.yaml
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: kube-state-metrics
+  namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: kube-state-metrics
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+rules:
+- apiGroups: [""]
+  resources:
+  - configmaps
+  - secrets
+  - nodes
+  - pods
+  - services
+  - resourcequotas
+  - replicationcontrollers
+  - limitranges
+  - persistentvolumeclaims
+  - persistentvolumes
+  - namespaces
+  - endpoints
+  verbs: ["list", "watch"]
+- apiGroups: ["extensions"]
+  resources:
+  - daemonsets
+  - deployments
+  - replicasets
+  verbs: ["list", "watch"]
+- apiGroups: ["apps"]
+  resources:
+  - statefulsets
+  verbs: ["list", "watch"]
+- apiGroups: ["batch"]
+  resources:
+  - cronjobs
+  - jobs
+  verbs: ["list", "watch"]
+- apiGroups: ["autoscaling"]
+  resources:
+  - horizontalpodautoscalers
+  verbs: ["list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: kube-state-metrics-resizer
+  namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+rules:
+- apiGroups: [""]
+  resources:
+  - pods
+  verbs: ["get"]
+- apiGroups: ["extensions"]
+  resources:
+  - deployments
+  resourceNames: ["kube-state-metrics"]
+  verbs: ["get", "update"]
+---
+apiVersion: rbac.authorization.k8s.io/v1 
+kind: ClusterRoleBinding
+metadata:
+  name: kube-state-metrics
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: kube-state-metrics
+subjects:
+- kind: ServiceAccount
+  name: kube-state-metrics
+  namespace: kube-system
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: kube-state-metrics
+  namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: kube-state-metrics-resizer
+subjects:
+- kind: ServiceAccount
+  name: kube-state-metrics
+  namespace: kube-system
--- a/cluster/addons/prometheus/kube-state-metrics-service.yaml
+++ b/cluster/addons/prometheus/kube-state-metrics-service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: kube-state-metrics
+  namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    kubernetes.io/name: "kube-state-metrics"
+  annotations:
+    prometheus.io/scrape: 'true'
+spec:
+  ports:
+  - name: http-metrics
+    port: 8080
+    targetPort: http-metrics
+    protocol: TCP
+  - name: telemetry
+    port: 8081
+    targetPort: telemetry
+    protocol: TCP
+  selector:
+    k8s-app: kube-state-metrics
--- a/cluster/addons/prometheus/node-exporter-ds.yml
+++ b/cluster/addons/prometheus/node-exporter-ds.yml
+apiVersion: extensions/v1beta1
+kind: DaemonSet
+metadata:
+  name: node-exporter 
+  namespace: kube-system 
+  labels:
+    k8s-app: node-exporter 
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    version: v0.15.2
+spec:
+  updateStrategy:
+    type: OnDelete
+  template:
+    metadata:
+      labels:
+        k8s-app: node-exporter 
+        version: v0.15.2
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ''
+    spec:
+      priorityClassName: system-node-critical
+      containers:
+        - name: prometheus-node-exporter
+          image: "prom/node-exporter:v0.15.2"
+          imagePullPolicy: "IfNotPresent"
+          args:
+            - --path.procfs=/host/proc
+            - --path.sysfs=/host/sys
+          ports:
+            - name: metrics
+              containerPort: 9100
+              hostPort: 9100
+          volumeMounts:
+            - name: proc
+              mountPath: /host/proc
+              readOnly:  true
+            - name: sys
+              mountPath: /host/sys
+              readOnly: true
+          resources:
+            limits:
+              cpu: 10m
+              memory: 50Mi
+            requests:
+              cpu: 10m
+              memory: 50Mi
+      hostNetwork: true
+      hostPID: true
+      volumes:
+        - name: proc
+          hostPath:
+            path: /proc
+        - name: sys
+          hostPath:
+            path: /sys
--- a/cluster/addons/prometheus/node-exporter-service.yaml
+++ b/cluster/addons/prometheus/node-exporter-service.yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: node-exporter
+  namespace: kube-system
+  annotations:
+    prometheus.io/scrape: "true"
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    kubernetes.io/name: "NodeExporter"
+spec:
+  clusterIP: None
+  ports:
+    - name: metrics
+      port: 9100
+      protocol: TCP
+      targetPort: 9100
+  selector:
+    k8s-app: node-exporter