Merge branch 'master' of https://github.com/coreos/prometheus-operator

manifests/alertmanager/alertmanager.yaml

@@ -1,9 +1,9 @@
-apiVersion: "monitoring.coreos.com/v1alpha1"
-kind: "Alertmanager"
+apiVersion: monitoring.coreos.com/v1
+kind: Alertmanager
 metadata:
-  name: "main"
+  name: main
   labels:
-    alertmanager: "main"
+    alertmanager: main
 spec:
   replicas: 3
   version: v0.7.1

manifests/examples/basic-auth/service-monitor.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:

manifests/examples/example-app/prometheus-frontend.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: Prometheus
 metadata:
   name: frontend

manifests/examples/example-app/servicemonitor-frontend.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: frontend

manifests/grafana/grafana-deployment.yaml

@@ -1,4 +1,4 @@
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1beta1
 kind: Deployment
 metadata:
   name: grafana
@@ -41,7 +41,7 @@ spec:
             memory: 200Mi
             cpu: 200m
       - name: grafana-watcher
-        image: quay.io/coreos/grafana-watcher:v0.0.7
+        image: quay.io/coreos/grafana-watcher:v0.0.8
         args:
           - '--watch-dir=/var/grafana-dashboards'
           - '--grafana-url=http://localhost:3000'

manifests/grafana/grafana-service.yaml

@@ -7,9 +7,9 @@ metadata:
 spec:
   type: NodePort
   ports:
-  - name: web
-    port: 3000
+  - port: 3000
     protocol: TCP
     nodePort: 30902
+    targetPort: web
   selector:
     app: grafana

manifests/kube-state-metrics/kube-state-metrics-cluster-role.yaml

@@ -11,6 +11,7 @@ rules:
   - resourcequotas
   - replicationcontrollers
   - limitranges
+  - persistentvolumeclaims
   verbs: ["list", "watch"]
 - apiGroups: ["extensions"]
   resources:
@@ -18,3 +19,12 @@ rules:
   - deployments
   - replicasets
   verbs: ["list", "watch"]
+- apiGroups: ["apps"]
+  resources:
+  - statefulsets
+  verbs: ["list", "watch"]
+- apiGroups: ["batch"]
+  resources:
+  - cronjobs
+  - jobs
+  verbs: ["list", "watch"]

manifests/kube-state-metrics/kube-state-metrics-deployment.yaml

@@ -12,10 +12,16 @@ spec:
       serviceAccountName: kube-state-metrics
       containers:
       - name: kube-state-metrics
-        image: quay.io/coreos/kube-state-metrics:v0.5.0
+        image: quay.io/coreos/kube-state-metrics:v1.0.1
         ports:
         - name: metrics
           containerPort: 8080
+        readinessProbe:
+          httpGet:
+            path: /healthz
+            port: 8080
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
         resources:
           requests:
             memory: 100Mi
@@ -23,4 +29,30 @@ spec:
           limits:
             memory: 200Mi
             cpu: 200m
-
+      - name: addon-resizer
+        image: gcr.io/google_containers/addon-resizer:1.0
+        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

manifests/kube-state-metrics/kube-state-metrics-role-binding.yaml

@@ -0,0 +1,12 @@
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: RoleBinding
+metadata:
+  name: kube-state-metrics
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: kube-state-metrics-resizer
+subjects:
+- kind: ServiceAccount
+  name: kube-state-metrics
+

manifests/kube-state-metrics/kube-state-metrics-role.yaml

@@ -0,0 +1,15 @@
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: Role
+metadata:
+  name: kube-state-metrics-resizer
+rules:
+- apiGroups: [""]
+  resources:
+  - pods
+  verbs: ["get"]
+- apiGroups: ["extensions"]
+  resources:
+  - deployments
+  resourceNames: ["kube-state-metrics"]
+  verbs: ["get", "update"]
+

manifests/node-exporter/node-exporter-daemonset.yaml

@@ -35,6 +35,9 @@ spec:
         - name: sys
           readOnly: true
           mountPath: /host/sys
+      tolerations:
+        - effect: NoSchedule
+          operator: Exists
       volumes:
       - name: proc
         hostPath:

manifests/prometheus-operator/prometheus-operator-cluster-role.yaml

@@ -8,7 +8,13 @@ rules:
   resources:
   - thirdpartyresources
   verbs:
-  - create
+  - "*"
+- apiGroups:
+  - apiextensions.k8s.io
+  resources:
+  - customresourcedefinitions
+  verbs:
+  - "*"
 - apiGroups:
   - monitoring.coreos.com
   resources:
@@ -40,3 +46,7 @@ rules:
   resources:
   - nodes
   verbs: ["list", "watch"]
+- apiGroups: [""]
+  resources:
+  - namespaces
+  verbs: ["list"]

manifests/prometheus-operator/prometheus-operator.yaml

@@ -15,7 +15,7 @@ spec:
       - args:
         - --kubelet-service=kube-system/kubelet
         - --config-reloader-image=quay.io/coreos/configmap-reload:v0.0.1
-        image: quay.io/coreos/prometheus-operator:v0.11.1
+        image: quay.io/coreos/prometheus-operator:v0.12.0
         name: prometheus-operator
         ports:
         - containerPort: 8080

manifests/prometheus/prometheus-k8s-rules.yaml

@@ -328,7 +328,7 @@ data:
       }
   kubelet.rules: |+
     ALERT K8SNodeNotReady
-      IF kube_node_status_ready{condition="true"} == 0
+      IF kube_node_status_condition{condition="Ready", status="true"} == 0
       FOR 1h
       LABELS {
         severity = "warning",
@@ -340,12 +340,12 @@ data:
     
     ALERT K8SManyNodesNotReady
       IF
-        count(kube_node_status_ready{condition="true"} == 0) > 1
+        count(kube_node_status_condition{condition="Ready", status="true"} == 0) > 1
         AND
           (
-            count(kube_node_status_ready{condition="true"} == 0)
+            count(kube_node_status_condition{condition="Ready", status="true"} == 0)
           /
-            count(kube_node_status_ready{condition="true"})
+            count(kube_node_status_condition{condition="Ready", status="true"})
           ) > 0.2
       FOR 1m
       LABELS {
@@ -582,8 +582,9 @@ data:
         summary = "node-exporter cannot be scraped",
         description = "Prometheus could not scrape a node-exporter for more than 10m, or node-exporters have disappeared from discovery.",
       }
+    
     ALERT K8SNodeOutOfDisk
-      IF kube_node_status_out_of_disk{condition="true"} == 1
+      IF kube_node_status_condition{condition="OutOfDisk", status="true"} == 1
       LABELS {
         service = "k8s",
         severity = "critical"
@@ -592,9 +593,9 @@ data:
         summary = "Node ran out of disk space.",
         description = "{{ $labels.node }} has run out of disk space.",
       }
-     
+    
     ALERT K8SNodeMemoryPressure
-      IF kube_node_status_memory_pressure{condition="true"} == 1
+      IF kube_node_status_condition{condition="MemoryPressure", status="true"} == 1
       LABELS {
         service = "k8s",
         severity = "warning"
@@ -603,9 +604,9 @@ data:
         summary = "Node is under memory pressure.",
         description = "{{ $labels.node }} is under memory pressure.",
       }
-     
+    
     ALERT K8SNodeDiskPressure
-      IF kube_node_status_disk_pressure{condition="true"} == 1
+      IF kube_node_status_condition{condition="DiskPressure", status="true"} == 1
       LABELS {
         service = "k8s",
         severity = "warning"

manifests/prometheus/prometheus-k8s-service-monitor-alertmanager.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: alertmanager

manifests/prometheus/prometheus-k8s-service-monitor-apiserver.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: kube-apiserver

manifests/prometheus/prometheus-k8s-service-monitor-kube-controller-manager.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: kube-controller-manager

manifests/prometheus/prometheus-k8s-service-monitor-kube-scheduler.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: kube-scheduler

manifests/prometheus/prometheus-k8s-service-monitor-kube-state-metrics.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: kube-state-metrics

manifests/prometheus/prometheus-k8s-service-monitor-kubelet.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: kubelet

manifests/prometheus/prometheus-k8s-service-monitor-node-exporter.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: node-exporter

manifests/prometheus/prometheus-k8s-service-monitor-prometheus-operator.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: prometheus-operator

manifests/prometheus/prometheus-k8s-service-monitor-prometheus.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: prometheus

manifests/prometheus/prometheus-k8s.yaml

@@ -1,4 +1,4 @@
-apiVersion: monitoring.coreos.com/v1alpha1
+apiVersion: monitoring.coreos.com/v1
 kind: Prometheus
 metadata:
   name: k8s