Add testing manifests for (node upgrade) etcd test.

test/e2e/testing-manifests/statefulset/etcd/pdb.yaml

@@ -0,0 +1,11 @@
+apiVersion: policy/v1beta1
+kind: PodDisruptionBudget
+metadata:
+  name: etcd-pdb
+  labels:
+    pdb: etcd
+spec:
+  minAvailable: 2
+  selector:
+    matchLabels:
+      app: etcd

test/e2e/testing-manifests/statefulset/etcd/service.yaml

@@ -0,0 +1,18 @@
+apiVersion: v1
+kind: Service
+metadata:
+  annotations:
+    service.alpha.kubernetes.io/tolerate-unready-endpoints: "true"
+metadata:
+  name: etcd
+  labels:
+    app: etcd
+spec:
+  ports:
+  - port: 2380
+    name: etcd-server
+  - port: 2379
+    name: etcd-client
+  clusterIP: None
+  selector:
+    app: etcd

test/e2e/testing-manifests/statefulset/etcd/statefulset.yaml

@@ -0,0 +1,178 @@
+apiVersion: apps/v1beta1
+kind: StatefulSet
+metadata:
+  name: etcd
+  labels:
+    app: etcd
+spec:
+  serviceName: etcd
+  replicas: 3
+  template:
+    metadata:
+      name: etcd
+      labels:
+        app: etcd
+    spec:
+      containers:
+      - name: etcd
+        image: gcr.io/google_containers/etcd-amd64:2.2.5
+        imagePullPolicy: Always
+        ports:
+        - containerPort: 2380
+          name: peer
+        - containerPort: 2379
+          name: client
+        resources:
+          requests:
+            cpu: 100m
+            memory: 512Mi
+        env:
+        - name: INITIAL_CLUSTER_SIZE
+          value: "3"
+        - name: SET_NAME
+          value: etcd
+        volumeMounts:
+        - name: datadir
+          mountPath: /var/run/etcd
+        lifecycle:
+          preStop:
+            exec:
+              command:
+                - "/bin/sh"
+                - "-ec"
+                - |
+                  EPS=""
+                  for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
+                      EPS="${EPS}${EPS:+,}http://${SET_NAME}-${i}.${SET_NAME}:2379"
+                  done
+
+                  HOSTNAME=$(hostname)
+
+                  member_hash() {
+                      etcdctl member list | grep http://${HOSTNAME}.${SET_NAME}:2380 | cut -d':' -f1 | cut -d'[' -f1
+                  }
+
+                  echo "Removing ${HOSTNAME} from etcd cluster"
+
+                  ETCDCTL_ENDPOINT=${EPS} etcdctl member remove $(member_hash)
+                  if [ $? -eq 0 ]; then
+                      # Remove everything otherwise the cluster will no longer scale-up
+                      rm -rf /var/run/etcd/*
+                  fi
+        command:
+          - "/bin/sh"
+          - "-ec"
+          - |
+            HOSTNAME=$(hostname)
+
+            # store member id into PVC for later member replacement
+            collect_member() {
+                while ! etcdctl member list &>/dev/null; do sleep 1; done
+                etcdctl member list | grep http://${HOSTNAME}.${SET_NAME}:2380 | cut -d':' -f1 | cut -d'[' -f1 > /var/run/etcd/member_id
+                exit 0
+            }
+
+            eps() {
+                EPS=""
+                for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
+                    EPS="${EPS}${EPS:+,}http://${SET_NAME}-${i}.${SET_NAME}:2379"
+                done
+                echo ${EPS}
+            }
+
+            member_hash() {
+                etcdctl member list | grep http://${HOSTNAME}.${SET_NAME}:2380 | cut -d':' -f1 | cut -d'[' -f1
+            }
+
+            # re-joining after failure?
+            if [ -e /var/run/etcd/default.etcd ]; then
+                echo "Re-joining etcd member"
+                member_id=$(cat /var/run/etcd/member_id)
+
+                # re-join member
+                ETCDCTL_ENDPOINT=$(eps) etcdctl member update ${member_id} http://${HOSTNAME}.${SET_NAME}:2380
+                exec etcd --name ${HOSTNAME} \
+                    --listen-peer-urls http://${HOSTNAME}.${SET_NAME}:2380 \
+                    --listen-client-urls http://${HOSTNAME}.${SET_NAME}:2379,http://127.0.0.1:2379 \
+                    --advertise-client-urls http://${HOSTNAME}.${SET_NAME}:2379 \
+                    --data-dir /var/run/etcd/default.etcd
+            fi
+
+            # etcd-SET_ID
+            SET_ID=${HOSTNAME:5:${#HOSTNAME}}
+
+            # adding a new member to existing cluster (assuming all initial pods are available)
+            if [ "${SET_ID}" -ge ${INITIAL_CLUSTER_SIZE} ]; then
+                export ETCDCTL_ENDPOINT=$(eps)
+
+                # member already added?
+                MEMBER_HASH=$(member_hash)
+                if [ -n "${MEMBER_HASH}" ]; then
+                    # the member hash exists but for some reason etcd failed
+                    # as the datadir has not be created, we can remove the member
+                    # and retrieve new hash
+                    etcdctl member remove ${MEMBER_HASH}
+                fi
+
+                echo "Adding new member"
+                etcdctl member add ${HOSTNAME} http://${HOSTNAME}.${SET_NAME}:2380 | grep "^ETCD_" > /var/run/etcd/new_member_envs
+
+                if [ $? -ne 0 ]; then
+                    echo "Exiting"
+                    rm -f /var/run/etcd/new_member_envs
+                    exit 1
+                fi
+
+                cat /var/run/etcd/new_member_envs
+                source /var/run/etcd/new_member_envs
+
+                collect_member &
+
+                exec etcd --name ${HOSTNAME} \
+                    --listen-peer-urls http://${HOSTNAME}.${SET_NAME}:2380 \
+                    --listen-client-urls http://${HOSTNAME}.${SET_NAME}:2379,http://127.0.0.1:2379 \
+                    --advertise-client-urls http://${HOSTNAME}.${SET_NAME}:2379 \
+                    --data-dir /var/run/etcd/default.etcd \
+                    --initial-advertise-peer-urls http://${HOSTNAME}.${SET_NAME}:2380 \
+                    --initial-cluster ${ETCD_INITIAL_CLUSTER} \
+                    --initial-cluster-state ${ETCD_INITIAL_CLUSTER_STATE}
+            fi
+
+            for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
+                while true; do
+                    echo "Waiting for ${SET_NAME}-${i}.${SET_NAME} to come up"
+                    ping -W 1 -c 1 ${SET_NAME}-${i}.${SET_NAME} > /dev/null && break
+                    sleep 1s
+                done
+            done
+
+            PEERS=""
+            for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
+                PEERS="${PEERS}${PEERS:+,}${SET_NAME}-${i}=http://${SET_NAME}-${i}.${SET_NAME}:2380"
+            done
+
+            collect_member &
+
+            # join member
+            exec etcd --name ${HOSTNAME} \
+                --initial-advertise-peer-urls http://${HOSTNAME}.${SET_NAME}:2380 \
+                --listen-peer-urls http://${HOSTNAME}.${SET_NAME}:2380 \
+                --listen-client-urls http://${HOSTNAME}.${SET_NAME}:2379,http://127.0.0.1:2379 \
+                --advertise-client-urls http://${HOSTNAME}.${SET_NAME}:2379 \
+                --initial-cluster-token etcd-cluster-1 \
+                --initial-cluster ${PEERS} \
+                --initial-cluster-state new \
+                --data-dir /var/run/etcd/default.etcd
+  volumeClaimTemplates:
+  - metadata:
+      name: datadir
+      annotations:
+        volume.alpha.kubernetes.io/storage-class: anything
+    spec:
+      accessModes:
+        - "ReadWriteOnce"
+      resources:
+        requests:
+          # upstream recommended max is 700M
+          storage: 1Gi
+

test/e2e/testing-manifests/statefulset/etcd/tester.yaml

@@ -0,0 +1,24 @@
+apiVersion: apps/v1beta1
+kind: Deployment
+metadata:
+  name: etcd-test-server
+spec:
+  replicas: 3
+  template:
+    metadata:
+      labels:
+        app: test-server
+    spec:
+      containers:
+      - name: test-server
+        image: gcr.io/google-containers/etcd-statefulset-e2e-test:0.0
+        imagePullPolicy: Always
+        ports:
+        - containerPort: 8080
+        readinessProbe:
+          httpGet:
+            path: /healthz
+            port: 8080
+          initialDelaySeconds: 2
+          periodSeconds: 2
+