Add node problem detector as an addon pod.

kubernetes · May 20, 2016 · 195e249 · 195e249
1 parent 9625926
commit 195e249
Show file tree

Hide file tree

Showing 9 changed files with 82 additions and 1 deletion.
diff --git a/cluster/addons/addon-manager/kube-addon-update.sh b/cluster/addons/addon-manager/kube-addon-update.sh
@@ -476,6 +476,7 @@ function update-addons() {
     # be careful, reconcile-objects uses global variables
     reconcile-objects ${addon_path} ReplicationController "-" &
     reconcile-objects ${addon_path} Deployment "-" &
+    reconcile-objects ${addon_path} DaemonSet "-" &
 
     # We don't expect names to be versioned for the following kinds, so
     # we match the entire name, ignoring version suffix.

diff --git a/cluster/addons/node-problem-detector/MAINTAINERS.md b/cluster/addons/node-problem-detector/MAINTAINERS.md
@@ -0,0 +1,6 @@
+# Maintainers
+
+Lantao Liu <lantaol@google.com>
+
+
+[![Analytics](https://kubernetes-site.appspot.com/UA-36037335-10/GitHub/cluster/addons/node-problem-detector/MAINTAINERS.md?pixel)]()
diff --git a/cluster/addons/node-problem-detector/README.md b/cluster/addons/node-problem-detector/README.md
@@ -0,0 +1,10 @@
+# Node Problem Detector
+==============
+
+Node Problem Detector is a DaemonSet running on each node, detecting node
+problems.
+
+Learn more at: https://github.com/kubernetes/node-problem-detector
+
+
+[![Analytics](https://kubernetes-site.appspot.com/UA-36037335-10/GitHub/cluster/addons/node-problem-detector/README.md?pixel)]()
diff --git a/cluster/addons/node-problem-detector/node-problem-detector.yaml.in b/cluster/addons/node-problem-detector/node-problem-detector.yaml.in
@@ -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: "{{ pillar['master_node'] }}"
+        - name: "KUBERNETES_SERVICE_PORT"
+          value: "443"
+        securityContext:
+          privileged: true
+        resources:
+          limits:
+            cpu: "200m"
+            memory: "100Mi"
+          requests:
+            cpu: "50m"
+            memory: "20Mi"
+        volumeMounts:
+        - name: log
+          mountPath: /log
+          readOnly: true
+      volumes:
+      - name: log
+        hostPath:
+          path: /var/log/
diff --git a/cluster/common.sh b/cluster/common.sh
@@ -485,6 +485,7 @@ ENABLE_CLUSTER_MONITORING: $(yaml-quote ${ENABLE_CLUSTER_MONITORING:-none})
 ENABLE_L7_LOADBALANCING: $(yaml-quote ${ENABLE_L7_LOADBALANCING:-none})
 ENABLE_CLUSTER_LOGGING: $(yaml-quote ${ENABLE_CLUSTER_LOGGING:-false})
 ENABLE_CLUSTER_UI: $(yaml-quote ${ENABLE_CLUSTER_UI:-false})
+ENABLE_NODE_PROBLEM_DETECTOR: $(yaml-quote ${ENABLE_NODE_PROBLEM_DETECTOR:-false})
 ENABLE_NODE_LOGGING: $(yaml-quote ${ENABLE_NODE_LOGGING:-false})
 LOGGING_DESTINATION: $(yaml-quote ${LOGGING_DESTINATION:-})
 ELASTICSEARCH_LOGGING_REPLICAS: $(yaml-quote ${ELASTICSEARCH_LOGGING_REPLICAS:-})
@@ -578,6 +579,7 @@ ENABLE_MANIFEST_URL: $(yaml-quote ${ENABLE_MANIFEST_URL:-false})
 MANIFEST_URL: $(yaml-quote ${MANIFEST_URL:-})
 MANIFEST_URL_HEADER: $(yaml-quote ${MANIFEST_URL_HEADER:-})
 NUM_NODES: $(yaml-quote ${NUM_NODES})
+MASTER_NAME: $(yaml-quote ${MASTER_NAME})
 EOF
     if [ -n "${APISERVER_TEST_ARGS:-}" ]; then
       cat >>$file <<EOF

diff --git a/cluster/gce/config-default.sh b/cluster/gce/config-default.sh
@@ -104,6 +104,9 @@ CLUSTER_REGISTRY_DISK_TYPE_GCE="${CLUSTER_REGISTRY_DISK_TYPE_GCE:-pd-standard}"
 # Optional: Install Kubernetes UI
 ENABLE_CLUSTER_UI="${KUBE_ENABLE_CLUSTER_UI:-true}"
 
+# Optional: Install node problem detector.
+ENABLE_NODE_PROBLEM_DETECTOR="${KUBE_ENABLE_NODE_PROBLEM_DETECTOR:-true}"
+
 # Optional: Create autoscaler for cluster's nodes.
 ENABLE_NODE_AUTOSCALER="${KUBE_ENABLE_NODE_AUTOSCALER:-false}"
 if [[ "${ENABLE_NODE_AUTOSCALER}" == "true" ]]; then
@@ -126,6 +129,5 @@ OPENCONTRAIL_PUBLIC_SUBNET="${OPENCONTRAIL_PUBLIC_SUBNET:-10.1.0.0/16}"
 
 # How should the kubelet configure hairpin mode?
 HAIRPIN_MODE="${HAIRPIN_MODE:-promiscuous-bridge}" # promiscuous-bridge, hairpin-veth, none
-
 # Optional: if set to true, kube-up will configure the cluster to run e2e tests.
 E2E_STORAGE_TEST_ENVIRONMENT=${KUBE_E2E_STORAGE_TEST_ENVIRONMENT:-false}
diff --git a/cluster/gce/config-test.sh b/cluster/gce/config-test.sh
@@ -125,6 +125,9 @@ CLUSTER_REGISTRY_DISK_TYPE_GCE="${CLUSTER_REGISTRY_DISK_TYPE_GCE:-pd-standard}"
 # Optional: Install Kubernetes UI
 ENABLE_CLUSTER_UI="${KUBE_ENABLE_CLUSTER_UI:-true}"
 
+# Optional: Install node problem detector.
+ENABLE_NODE_PROBLEM_DETECTOR="${KUBE_ENABLE_NODE_PROBLEM_DETECTOR:-true}"
+
 # Optional: Create autoscaler for cluster's nodes.
 ENABLE_NODE_AUTOSCALER="${KUBE_ENABLE_NODE_AUTOSCALER:-false}"
 if [[ "${ENABLE_NODE_AUTOSCALER}" == "true" ]]; then

diff --git a/cluster/gce/configure-vm.sh b/cluster/gce/configure-vm.sh
@@ -429,6 +429,7 @@ service_cluster_ip_range: '$(echo "$SERVICE_CLUSTER_IP_RANGE" | sed -e "s/'/''/g
 enable_cluster_monitoring: '$(echo "$ENABLE_CLUSTER_MONITORING" | sed -e "s/'/''/g")'
 enable_cluster_logging: '$(echo "$ENABLE_CLUSTER_LOGGING" | sed -e "s/'/''/g")'
 enable_cluster_ui: '$(echo "$ENABLE_CLUSTER_UI" | sed -e "s/'/''/g")'
+enable_node_problem_detector: '$(echo "$ENABLE_NODE_PROBLEM_DETECTOR" | sed -e "s/'/''/g")'
 enable_l7_loadbalancing: '$(echo "$ENABLE_L7_LOADBALANCING" | sed -e "s/'/''/g")'
 enable_node_logging: '$(echo "$ENABLE_NODE_LOGGING" | sed -e "s/'/''/g")'
 logging_destination: '$(echo "$LOGGING_DESTINATION" | sed -e "s/'/''/g")'
@@ -448,6 +449,7 @@ enable_manifest_url: '$(echo "${ENABLE_MANIFEST_URL:-}" | sed -e "s/'/''/g")'
 manifest_url: '$(echo "${MANIFEST_URL:-}" | sed -e "s/'/''/g")'
 manifest_url_header: '$(echo "${MANIFEST_URL_HEADER:-}" | sed -e "s/'/''/g")'
 num_nodes: $(echo "${NUM_NODES:-}" | sed -e "s/'/''/g")
+master_node: $(echo "${MASTER_NAME:-}" | sed -e "s/'/''/g")
 e2e_storage_test_environment: '$(echo "$E2E_STORAGE_TEST_ENVIRONMENT" | sed -e "s/'/''/g")'
 kube_uid: '$(echo "${KUBE_UID}" | sed -e "s/'/''/g")'
 EOF

diff --git a/cluster/saltbase/salt/kube-addons/init.sls b/cluster/saltbase/salt/kube-addons/init.sls
@@ -150,6 +150,17 @@ addon-dir-create:
     - file_mode: 644
 {% endif %}
 
+{% if pillar.get('enable_node_problem_detector', '').lower() == 'true' %}
+/etc/kubernetes/addons/node-problem-detector/node-problem-detector.yaml:
+  file.managed:
+    - source: salt://kube-addons/node-problem-detector/node-problem-detector.yaml.in
+    - template: jinja
+    - user: root
+    - group: root
+    - file_mode: 644
+    - makedirs: True
+{% endif %}
+
 /etc/kubernetes/manifests/kube-addon-manager.yaml:
   file.managed:
     - source: salt://kube-addons/kube-addon-manager.yaml