Add stackdriver monitoring option

cluster/addons/cluster-monitoring/stackdriver/heapster-controller.yaml

@@ -0,0 +1,96 @@
+{% set base_metrics_memory = "140Mi" -%}
+{% set base_metrics_cpu = "80m" -%}
+{% set metrics_memory_per_node = 4 -%}
+{% set metrics_cpu_per_node = 0.5 -%}
+{% set num_nodes = pillar.get('num_nodes', -1) -%}
+{% set nanny_memory = "90Mi" -%}
+{% set nanny_memory_per_node = 200 -%}
+{% if num_nodes >= 0 -%}
+  {% set nanny_memory = (90 * 1024 + num_nodes * nanny_memory_per_node)|string + "Ki" -%}
+{% endif -%}
+
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: heapster-v1.3.0
+  namespace: kube-system
+  labels:
+    k8s-app: heapster
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    version: v1.3.0
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      k8s-app: heapster
+      version: v1.3.0
+  template:
+    metadata:
+      labels:
+        k8s-app: heapster
+        version: v1.3.0
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ''
+    spec:
+      containers:
+        - image: gcr.io/google_containers/heapster-amd64:v1.3.0
+          name: heapster
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: 8082
+              scheme: HTTP
+            initialDelaySeconds: 180
+            timeoutSeconds: 5
+          command:
+            - /heapster
+            - --source=kubernetes.summary_api:''
+            - --sink=stackdriver
+              # TODO: add --disable_export when it's merged into Heapster release
+          volumeMounts:
+            - name: ssl-certs
+              mountPath: /etc/ssl/certs
+              readOnly: true
+            - name: usr-ca-certs
+              mountPath: /usr/share/ca-certificates
+              readOnly: true
+        - image: gcr.io/google_containers/addon-resizer:1.7
+          name: heapster-nanny
+          resources:
+            limits:
+              cpu: 50m
+              memory: {{ nanny_memory }}
+            requests:
+              cpu: 50m
+              memory: {{ nanny_memory }}
+          env:
+            - name: MY_POD_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.name
+            - name: MY_POD_NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+          command:
+            - /pod_nanny
+            - --cpu={{ base_metrics_cpu }}
+            - --extra-cpu={{ metrics_cpu_per_node }}m
+            - --memory={{ base_metrics_memory }}
+            - --extra-memory={{metrics_memory_per_node}}Mi
+            - --threshold=5
+            - --deployment=heapster-v1.3.0
+            - --container=heapster
+            - --poll-period=300000
+            - --estimator=exponential
+      volumes:
+        - name: ssl-certs
+          hostPath:
+            path: "/etc/ssl/certs"
+        - name: usr-ca-certs
+          hostPath:
+            path: "/usr/share/ca-certificates"
+      tolerations:
+        - key: "CriticalAddonsOnly"
+          operator: "Exists"

cluster/addons/cluster-monitoring/stackdriver/heapster-service.yaml

@@ -0,0 +1,15 @@
+kind: Service
+apiVersion: v1
+metadata: 
+  name: heapster
+  namespace: kube-system
+  labels: 
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    kubernetes.io/name: "Heapster"
+spec: 
+  ports: 
+    - port: 80
+      targetPort: 8082
+  selector: 
+    k8s-app: heapster

cluster/gce/config-default.sh

@@ -102,6 +102,7 @@ ENABLE_L7_LOADBALANCING="${KUBE_ENABLE_L7_LOADBALANCING:-glbc}"
 #   none           - No cluster monitoring setup
 #   influxdb       - Heapster, InfluxDB, and Grafana
 #   google         - Heapster, Google Cloud Monitoring, and Google Cloud Logging
+#   stackdriver    - Heapster, Google Cloud Monitoring (schema container), and Google Cloud Logging
 #   googleinfluxdb - Enable influxdb and google (except GCM)
 #   standalone     - Heapster only. Metrics available via Heapster REST API.
 ENABLE_CLUSTER_MONITORING="${KUBE_ENABLE_CLUSTER_MONITORING:-influxdb}"

cluster/gce/config-test.sh

@@ -106,6 +106,7 @@ ENABLE_L7_LOADBALANCING="${KUBE_ENABLE_L7_LOADBALANCING:-glbc}"
 #   none           - No cluster monitoring setup
 #   influxdb       - Heapster, InfluxDB, and Grafana
 #   google         - Heapster, Google Cloud Monitoring, and Google Cloud Logging
+#   stackdriver    - Heapster, Google Cloud Monitoring (schema container), and Google Cloud Logging
 #   googleinfluxdb - Enable influxdb and google (except GCM)
 #   standalone     - Heapster only. Metrics available via Heapster REST API.
 ENABLE_CLUSTER_MONITORING="${KUBE_ENABLE_CLUSTER_MONITORING:-influxdb}"

cluster/gce/container-linux/configure-helper.sh

@@ -1113,6 +1113,7 @@ function start-kube-addons {
   # Set up manifests of other addons.
   if [[ "${ENABLE_CLUSTER_MONITORING:-}" == "influxdb" ]] || \
      [[ "${ENABLE_CLUSTER_MONITORING:-}" == "google" ]] || \
+     [[ "${ENABLE_CLUSTER_MONITORING:-}" == "stackdriver" ]] || \
      [[ "${ENABLE_CLUSTER_MONITORING:-}" == "standalone" ]] || \
      [[ "${ENABLE_CLUSTER_MONITORING:-}" == "googleinfluxdb" ]]; then
     local -r file_dir="cluster-monitoring/${ENABLE_CLUSTER_MONITORING}"

cluster/gce/gci/configure-helper.sh

@@ -1322,6 +1322,7 @@ function start-kube-addons {
   # Set up manifests of other addons.
   if [[ "${ENABLE_CLUSTER_MONITORING:-}" == "influxdb" ]] || \
      [[ "${ENABLE_CLUSTER_MONITORING:-}" == "google" ]] || \
+     [[ "${ENABLE_CLUSTER_MONITORING:-}" == "stackdriver" ]] || \
      [[ "${ENABLE_CLUSTER_MONITORING:-}" == "standalone" ]] || \
      [[ "${ENABLE_CLUSTER_MONITORING:-}" == "googleinfluxdb" ]]; then
     local -r file_dir="cluster-monitoring/${ENABLE_CLUSTER_MONITORING}"

cluster/saltbase/salt/kube-addons/init.sls

@@ -47,6 +47,18 @@ addon-dir-create:
     - file_mode: 644
 {% endif %}
 
+{% if pillar.get('enable_cluster_monitoring', '').lower() == 'stackdriver' %}
+/etc/kubernetes/addons/cluster-monitoring/stackdriver:
+  file.recurse:
+    - source: salt://kube-addons/cluster-monitoring/stackdriver
+    - include_pat: E@(^.+\.yaml$|^.+\.json$)
+    - template: jinja
+    - user: root
+    - group: root
+    - dir_mode: 755
+    - file_mode: 644
+{% endif %}
+
 {% if pillar.get('enable_cluster_monitoring', '').lower() == 'standalone' %}
 /etc/kubernetes/addons/cluster-monitoring/standalone:
   file.recurse: