Merge pull request #404 from olegmayko/master

Use kube-state-metrics jsonnet dependency #369
2020-02-11 09:45:27 -06:00
parent 5cabd5eeda f043bc32d3
commit 0ed3f70014
14 changed files with 174 additions and 435 deletions
--- a/manifests/kube-state-metrics-clusterRole.yaml
+++ b/manifests/kube-state-metrics-clusterRole.yaml
@@ -1,6 +1,9 @@
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
+  labels:
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.9.4
  name: kube-state-metrics
 rules:
 - apiGroups:
@@ -93,8 +96,8 @@ rules:
 - apiGroups:
  - admissionregistration.k8s.io
  resources:
-  - validatingwebhookconfigurations
  - mutatingwebhookconfigurations
+  - validatingwebhookconfigurations
  verbs:
  - list
  - watch
@@ -105,3 +108,10 @@ rules:
  verbs:
  - list
  - watch
+- apiGroups:
+  - coordination.k8s.io
+  resources:
+  - leases
+  verbs:
+  - list
+  - watch
--- a/manifests/kube-state-metrics-clusterRoleBinding.yaml
+++ b/manifests/kube-state-metrics-clusterRoleBinding.yaml
@@ -1,6 +1,9 @@
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
+  labels:
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.9.4
  name: kube-state-metrics
 roleRef:
  apiGroup: rbac.authorization.k8s.io
--- a/manifests/kube-state-metrics-deployment.yaml
+++ b/manifests/kube-state-metrics-deployment.yaml
@@ -2,71 +2,43 @@ apiVersion: apps/v1
 kind: Deployment
 metadata:
  labels:
-    app: kube-state-metrics
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.9.4
  name: kube-state-metrics
  namespace: monitoring
 spec:
  replicas: 1
  selector:
    matchLabels:
-      app: kube-state-metrics
+      app.kubernetes.io/name: kube-state-metrics
  template:
    metadata:
      labels:
-        app: kube-state-metrics
+        app.kubernetes.io/name: kube-state-metrics
+        app.kubernetes.io/version: v1.9.4
    spec:
      containers:
-      - args:
-        - --logtostderr
-        - --secure-listen-address=:8443
-        - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256
-        - --upstream=http://127.0.0.1:8081/
-        image: quay.io/coreos/kube-rbac-proxy:v0.4.1
-        name: kube-rbac-proxy-main
-        ports:
-        - containerPort: 8443
-          name: https-main
-        resources:
-          limits:
-            cpu: 20m
-            memory: 40Mi
-          requests:
-            cpu: 10m
-            memory: 20Mi
-      - args:
-        - --logtostderr
-        - --secure-listen-address=:9443
-        - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256
-        - --upstream=http://127.0.0.1:8082/
-        image: quay.io/coreos/kube-rbac-proxy:v0.4.1
-        name: kube-rbac-proxy-self
-        ports:
-        - containerPort: 9443
-          name: https-self
-        resources:
-          limits:
-            cpu: 20m
-            memory: 40Mi
-          requests:
-            cpu: 10m
-            memory: 20Mi
-      - args:
-        - --host=127.0.0.1
-        - --port=8081
-        - --telemetry-host=127.0.0.1
-        - --telemetry-port=8082
-        image: quay.io/coreos/kube-state-metrics:v1.9.3
+      - image: quay.io/coreos/kube-state-metrics:v1.9.4
+        livenessProbe:
+          httpGet:
+            path: /healthz
+            port: 8080
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
        name: kube-state-metrics
-        resources:
-          limits:
-            cpu: 100m
-            memory: 150Mi
-          requests:
-            cpu: 100m
-            memory: 150Mi
+        ports:
+        - containerPort: 8080
+          name: http-metrics
+        - containerPort: 8081
+          name: telemetry
+        readinessProbe:
+          httpGet:
+            path: /
+            port: 8081
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        securityContext:
+          runAsUser: 65534
      nodeSelector:
        kubernetes.io/os: linux
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 65534
      serviceAccountName: kube-state-metrics
--- a/manifests/kube-state-metrics-role.yaml
+++ b/manifests/kube-state-metrics-role.yaml
@@ -1,30 +0,0 @@
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: kube-state-metrics
-  namespace: monitoring
-rules:
- apiGroups:
-  - ""
-  resources:
-  - pods
-  verbs:
-  - get
- apiGroups:
-  - extensions
-  resourceNames:
-  - kube-state-metrics
-  resources:
-  - deployments
-  verbs:
-  - get
-  - update
- apiGroups:
-  - apps
-  resourceNames:
-  - kube-state-metrics
-  resources:
-  - deployments
-  verbs:
-  - get
-  - update
--- a/manifests/kube-state-metrics-roleBinding.yaml
+++ b/manifests/kube-state-metrics-roleBinding.yaml
@@ -1,12 +0,0 @@
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: kube-state-metrics
-  namespace: monitoring
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: kube-state-metrics
-subjects:
- kind: ServiceAccount
-  name: kube-state-metrics
--- a/manifests/kube-state-metrics-service.yaml
+++ b/manifests/kube-state-metrics-service.yaml
@@ -2,17 +2,18 @@ apiVersion: v1
 kind: Service
 metadata:
  labels:
-    k8s-app: kube-state-metrics
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.9.4
  name: kube-state-metrics
  namespace: monitoring
 spec:
  clusterIP: None
  ports:
-  - name: https-main
-    port: 8443
-    targetPort: https-main
-  - name: https-self
-    port: 9443
-    targetPort: https-self
+  - name: http-metrics
+    port: 8080
+    targetPort: http-metrics
+  - name: telemetry
+    port: 8081
+    targetPort: telemetry
  selector:
-    app: kube-state-metrics
+    app.kubernetes.io/name: kube-state-metrics
--- a/manifests/kube-state-metrics-serviceAccount.yaml
+++ b/manifests/kube-state-metrics-serviceAccount.yaml
@@ -1,5 +1,8 @@
 apiVersion: v1
 kind: ServiceAccount
 metadata:
+  labels:
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.9.4
  name: kube-state-metrics
  namespace: monitoring
--- a/manifests/kube-state-metrics-serviceMonitor.yaml
+++ b/manifests/kube-state-metrics-serviceMonitor.yaml
@@ -2,29 +2,23 @@ apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
  labels:
-    k8s-app: kube-state-metrics
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.9.4
  name: kube-state-metrics
  namespace: monitoring
 spec:
  endpoints:
-  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
-    honorLabels: true
+  - honorLabels: true
    interval: 30s
-    port: https-main
+    port: http-metrics
    relabelings:
    - action: labeldrop
      regex: (pod|service|endpoint|namespace)
-    scheme: https
    scrapeTimeout: 30s
-    tlsConfig:
-      insecureSkipVerify: true
-  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
-    interval: 30s
-    port: https-self
-    scheme: https
-    tlsConfig:
-      insecureSkipVerify: true
-  jobLabel: k8s-app
+  - interval: 30s
+    port: telemetry
+  jobLabel: app.kubernetes.io/name
  selector:
    matchLabels:
-      k8s-app: kube-state-metrics
+      app.kubernetes.io/name: kube-state-metrics
+      app.kubernetes.io/version: v1.9.4
--- a/manifests/prometheus-rules.yaml
+++ b/manifests/prometheus-rules.yaml
@@ -271,6 +271,36 @@ spec:
      record: count:up1
    - expr: count without(instance, pod, node) (up == 0)
      record: count:up0
+  - name: kube-state-metrics
+    rules:
+    - alert: KubeStateMetricsListErrors
+      annotations:
+        message: kube-state-metrics is experiencing errors at an elevated rate in
+          list operations. This is likely causing it to not be able to expose metrics
+          about Kubernetes objects correctly or at all.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricslisterrors
+      expr: |
+        (sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m]))
+          /
+        sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])))
+        > 0.01
+      for: 15m
+      labels:
+        severity: critical
+    - alert: KubeStateMetricsWatchErrors
+      annotations:
+        message: kube-state-metrics is experiencing errors at an elevated rate in
+          watch operations. This is likely causing it to not be able to expose metrics
+          about Kubernetes objects correctly or at all.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricswatcherrors
+      expr: |
+        (sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m]))
+          /
+        sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])))
+        > 0.01
+      for: 15m
+      labels:
+        severity: critical
  - name: node-exporter
    rules:
    - alert: NodeFilesystemSpaceFillingUp