cluster/gce/coreos: Update addon manifests, add node-problem-detector.

Also bumped CNI version.

cluster/gce/coreos/configure-node.sh

@@ -160,6 +160,10 @@ function configure-master-addons() {
     CLUSTER_REGISTRY_DISK_SIZE=$(convert-bytes-gce-kube "${CLUSTER_REGISTRY_DISK_SIZE}")
     evaluate-manifests-dir ${MANIFESTS_DIR}/addons/registry  ${addon_dir}/registry
   fi
+
+  if [[ "${ENABLE_NODE_PROBLEM_DETECTOR}" == "true" ]]; then
+    evaluate-manifests-dir ${MANIFESTS_DIR}/addons/node-problem-detector  ${addon_dir}/node-problem-detector
+  fi
 }
 
 function configure-master-components() {

cluster/gce/coreos/kube-manifests/addons/dns/skydns-rc.yaml

@@ -1,27 +1,27 @@
 apiVersion: v1
 kind: ReplicationController
 metadata:
-  name: kube-dns-v11
+  name: kube-dns-v14
   namespace: kube-system
   labels:
     k8s-app: kube-dns
-    version: v11
+    version: v14
     kubernetes.io/cluster-service: "true"
 spec:
   replicas: ${DNS_REPLICAS}
   selector:
     k8s-app: kube-dns
-    version: v11
+    version: v14
   template:
     metadata:
       labels:
         k8s-app: kube-dns
-        version: v11
+        version: v14
         kubernetes.io/cluster-service: "true"
     spec:
       containers:
-      - name: etcd
+      - name: kubedns
-        image: gcr.io/google_containers/etcd-amd64:2.2.1
+        image: gcr.io/google_containers/kubedns-amd64:1.3
         resources:
           # TODO: Set memory limits when we've profiled the container for large
           # clusters, then set request = limit to keep this container in
@@ -29,33 +29,6 @@ spec:
           # "burstable" category so the kubelet doesn't backoff from restarting it.
           limits:
             cpu: 100m
-            memory: 500Mi
-          requests:
-            cpu: 100m
-            memory: 50Mi
-        command:
-        - /usr/local/bin/etcd
-        - -data-dir
-        - /var/etcd/data
-        - -listen-client-urls
-        - http://127.0.0.1:2379,http://127.0.0.1:4001
-        - -advertise-client-urls
-        - http://127.0.0.1:2379,http://127.0.0.1:4001
-        - -initial-cluster-token
-        - skydns-etcd
-        volumeMounts:
-        - name: etcd-storage
-          mountPath: /var/etcd/data
-      - name: kube2sky
-        image: gcr.io/google_containers/kube2sky:1.15
-        resources:
-          # TODO: Set memory limits when we've profiled the container for large
-          # clusters, then set request = limit to keep this container in
-          # guaranteed class. Currently, this container falls into the
-          # "burstable" category so the kubelet doesn't backoff from restarting it.
-          limits:
-            cpu: 100m
-            # Kube2sky watches all pods.
             memory: 200Mi
           requests:
             cpu: 100m
@@ -78,32 +51,23 @@ spec:
           # only setup the /readiness HTTP server once that's available.
           initialDelaySeconds: 30
           timeoutSeconds: 5
-        command:
-        - /kube2sky
         args:
-        # command = "/kube2sky"
+        # command = "/kube-dns"
-        - --domain=${DNS_DOMAIN}
+        - --domain=${DNS_DOMAIN}.
-      - name: skydns
+        - --dns-port=10053
-        image: gcr.io/google_containers/skydns:2015-10-13-8c72f8c
+        ports:
-        resources:
+        - containerPort: 10053
-          # TODO: Set memory limits when we've profiled the container for large
+          name: dns-local
-          # clusters, then set request = limit to keep this container in
+          protocol: UDP
-          # guaranteed class. Currently, this container falls into the
+        - containerPort: 10053
-          # "burstable" category so the kubelet doesn't backoff from restarting it.
+          name: dns-tcp-local
-          limits:
+          protocol: TCP
-            cpu: 100m
+      - name: dnsmasq
-            memory: 200Mi
+        image: gcr.io/google_containers/dnsmasq:1.1
-          requests:
-            cpu: 100m
-            memory: 50Mi
-        command:
-        - /skydns
         args:
-        # command = "/skydns"
+        - --cache-size=1000
-        - -machines=http://127.0.0.1:4001
+        - --no-resolv
-        - -addr=0.0.0.0:53
+        - --server=127.0.0.1#10053
-        - -ns-rotate=false
-        - -domain=${DNS_DOMAIN}.
         ports:
         - containerPort: 53
           name: dns
@@ -112,7 +76,7 @@ spec:
           name: dns-tcp
           protocol: TCP
       - name: healthz
-        image: gcr.io/google_containers/exechealthz:1.0
+        image: gcr.io/google_containers/exechealthz-amd64:1.0
         resources:
           # keep request = limit to keep this container in guaranteed class
           limits:
@@ -121,15 +85,10 @@ spec:
           requests:
             cpu: 10m
             memory: 20Mi
-        command:
-        - /exechealthz
         args:
         - -cmd=nslookup kubernetes.default.svc.${DNS_DOMAIN} 127.0.0.1 >/dev/null
         - -port=8080
         ports:
         - containerPort: 8080
           protocol: TCP
-      volumes:
+      dnsPolicy: Default  # Don't use cluster DNS.
-      - name: etcd-storage
-        emptyDir: {}
-      dnsPolicy: Default  # Don't use cluster DNS.

cluster/gce/coreos/kube-manifests/addons/fluentd-elasticsearch/es-controller.yaml

@@ -20,7 +20,7 @@ spec:
         kubernetes.io/cluster-service: "true"
     spec:
       containers:
-      - image: gcr.io/google_containers/elasticsearch:1.8
+      - image: gcr.io/google_containers/elasticsearch:1.9
         name: elasticsearch-logging         
         resources:
           # keep request = limit to keep this container in guaranteed class
@@ -40,4 +40,4 @@ spec:
           mountPath: /data
       volumes:
       - name: es-persistent-storage
-        emptyDir: {}
+        emptyDir: {}

cluster/gce/coreos/kube-manifests/addons/node-problem-detector/node-problem-detector.yaml

@@ -0,0 +1,44 @@
+apiVersion: extensions/v1beta1
+kind: DaemonSet
+metadata:
+  name: node-problem-detector-v0.1
+  namespace: kube-system
+  labels:
+    k8s-app: node-problem-detector
+    version: v0.1
+    kubernetes.io/cluster-service: "true"
+spec:
+  template:
+    metadata:
+      labels:
+        k8s-app: node-problem-detector
+        version: v0.1
+        kubernetes.io/cluster-service: "true"
+    spec:
+      hostNetwork: true
+      containers:
+      - name: node-problem-detector
+        image: gcr.io/google_containers/node-problem-detector:v0.1
+        env:
+        # Config the host ip and port of apiserver.
+        - name: "KUBERNETES_SERVICE_HOST"
+          value: ${INSTANCE_PREFIX}-master
+        - name: "KUBERNETES_SERVICE_PORT"
+          value: "443"
+        securityContext:
+          privileged: true
+        resources:
+          limits:
+            cpu: "200m"
+            memory: "100Mi"
+          requests:
+            cpu: "20m"
+            memory: "20Mi"
+        volumeMounts:
+        - name: log
+          mountPath: /log
+          readOnly: true
+      volumes:
+      - name: log
+        hostPath:
+          path: /var/log/

cluster/gce/coreos/master-docker.yaml

@@ -35,7 +35,7 @@ coreos:
         Type=oneshot
         RemainAfterExit=yes
         ExecStartPre=/usr/bin/mkdir -p /opt/cni
-        ExecStartPre=/usr/bin/curl --fail --silent --show-error --location --create-dirs --output /opt/downloads/cni.tar.gz https://storage.googleapis.com/kubernetes-release/network-plugins/cni-42c4cb842dad606a84e93aad5a4484ded48e3046.tar.gz
+        ExecStartPre=/usr/bin/curl --fail --silent --show-error --location --create-dirs --output /opt/downloads/cni.tar.gz https://storage.googleapis.com/kubernetes-release/network-plugins/cni-c864f0e1ea73719b8f4582402b0847064f9883b0.tar.gz
         ExecStart=/usr/bin/tar xf /opt/downloads/cni.tar.gz -C /opt/cni/        
         
     - name: kubernetes-download-salt.service

cluster/gce/coreos/master-rkt.yaml

@@ -35,7 +35,7 @@ coreos:
         Type=oneshot
         RemainAfterExit=yes
         ExecStartPre=/usr/bin/mkdir -p /opt/cni
-        ExecStartPre=/usr/bin/curl --fail --silent --show-error --location --create-dirs --output /opt/downloads/cni.tar.gz https://storage.googleapis.com/kubernetes-release/network-plugins/cni-42c4cb842dad606a84e93aad5a4484ded48e3046.tar.gz
+        ExecStartPre=/usr/bin/curl --fail --silent --show-error --location --create-dirs --output /opt/downloads/cni.tar.gz https://storage.googleapis.com/kubernetes-release/network-plugins/cni-c864f0e1ea73719b8f4582402b0847064f9883b0.tar.gz
         ExecStart=/usr/bin/tar xf /opt/downloads/cni.tar.gz -C /opt/cni/
 
     - name: kubernetes-install-docker2aci.service

cluster/gce/coreos/node-docker.yaml

@@ -35,7 +35,7 @@ coreos:
         Type=oneshot
         RemainAfterExit=yes
         ExecStartPre=/usr/bin/mkdir -p /opt/cni
-        ExecStartPre=/usr/bin/curl --fail --silent --show-error --location --create-dirs --output /opt/downloads/cni.tar.gz https://storage.googleapis.com/kubernetes-release/network-plugins/cni-42c4cb842dad606a84e93aad5a4484ded48e3046.tar.gz
+        ExecStartPre=/usr/bin/curl --fail --silent --show-error --location --create-dirs --output /opt/downloads/cni.tar.gz https://storage.googleapis.com/kubernetes-release/network-plugins/cni-c864f0e1ea73719b8f4582402b0847064f9883b0.tar.gz
         ExecStart=/usr/bin/tar xf /opt/downloads/cni.tar.gz -C /opt/cni/        
 
     - name: kubernetes-download-manifests.service

cluster/gce/coreos/node-rkt.yaml

@@ -35,7 +35,7 @@ coreos:
         Type=oneshot
         RemainAfterExit=yes
         ExecStartPre=/usr/bin/mkdir -p /opt/cni
-        ExecStartPre=/usr/bin/curl --fail --silent --show-error --location --create-dirs --output /opt/downloads/cni.tar.gz https://storage.googleapis.com/kubernetes-release/network-plugins/cni-42c4cb842dad606a84e93aad5a4484ded48e3046.tar.gz
+        ExecStartPre=/usr/bin/curl --fail --silent --show-error --location --create-dirs --output /opt/downloads/cni.tar.gz https://storage.googleapis.com/kubernetes-release/network-plugins/cni-c864f0e1ea73719b8f4582402b0847064f9883b0.tar.gz
         ExecStart=/usr/bin/tar xf /opt/downloads/cni.tar.gz -C /opt/cni/        
 
     - name: kubernetes-install-rkt.service