kubernetes/common/etcd/templates/statefulset.yaml

# Copyright © 2019 Intel Corporation Inc
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#       http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

apiVersion: apps/v1beta1
kind: StatefulSet
metadata:
  name: {{ include "common.fullname" .  }}
  labels:
    heritage: "{{ .Release.Service }}"
    release: "{{ .Release.Name }}"
    chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
    app: {{ include "common.name" . }}
spec:
  serviceName: {{ include "common.servicename" .}}
  replicas: {{ .Values.replicaCount }}
  template:
    metadata:
      labels:
        heritage: "{{ .Release.Service }}"
        release: "{{ .Release.Name }}"
        chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
        app: {{ include "common.name" . }}
    spec:
{{- if .Values.affinity }}
      affinity:
{{ toYaml .Values.affinity | indent 8 }}
{{- end }}
{{- if .Values.nodeSelector }}
      nodeSelector:
{{ toYaml .Values.nodeSelector | indent 8 }}
{{- end }}
{{- if .Values.tolerations }}
      tolerations:
{{ toYaml .Values.tolerations | indent 8 }}
{{- end }}
      containers:
      - name: {{ include "common.fullname" .  }}
        image: "{{ .Values.repository }}/{{ .Values.image }}"
        imagePullPolicy: "{{ .Values.pullPolicy }}"
        ports:
        - containerPort: {{ .Values.service.peerInternalPort }}
          name: {{ .Values.service.peerPortName }}
        - containerPort: {{ .Values.service.clientInternalPort }}
          name: {{ .Values.service.clientPortName }}
        {{- if eq .Values.liveness.enabled true }}
        livenessProbe:
          exec:
            command: ["/bin/sh", "-c", "etcdctl cluster-health | grep -w healthy" ]
            initialDelaySeconds: {{ .Values.liveness.initialDelaySeconds }}
            periodSeconds: {{ .Values.liveness.periodSeconds }}
            timeoutSeconds: {{ .Values.liveness.timeoutSeconds }}
          {{ end -}}
        readinessProbe:
          exec:
            command: ["/bin/sh", "-c", "etcdctl cluster-health | grep -w healthy" ]
            initialDelaySeconds: {{ .Values.readiness.initialDelaySeconds }}
            periodSeconds: {{ .Values.readiness.periodSeconds }}
        resources:
{{ include "common.resources" . | indent 10 }}
        env:
        - name: INITIAL_CLUSTER_SIZE
          value: {{ .Values.replicaCount | quote }}
        - name: SET_NAME
          value: {{ include "common.fullname" . }}
        - name: SERVICE_NAME
          value: {{ include "common.servicename" . }}
{{- if .Values.extraEnv }}
{{ toYaml .Values.extraEnv | indent 8 }}
{{- end }}
        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}.${SERVICE_NAME}:2379"
                  done

                  HOSTNAME=$(hostname)

                  member_hash() {
                      etcdctl member list | grep http://${HOSTNAME}.${SERVICE_NAME}:2380 | cut -d':' -f1 | cut -d'[' -f1
                  }

                  SET_ID=${HOSTNAME##*[^0-9]}

                  if [ "${SET_ID}" -ge ${INITIAL_CLUSTER_SIZE} ]; then
                      echo "Removing ${HOSTNAME} from etcd cluster"
                      ETCDCTL_ENDPOINT=${EPS} etcdctl member remove $(member_hash)
                      if [ $? -eq 0 ]; then
                          # Remove everything otherwise the cluster will no longer scale-up
                          rm -rf /var/run/etcd/*
                      fi
                  fi
        command:
          - "/bin/sh"
          - "-ec"
          - |
            HOSTNAME=$(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://${HOSTNAME}.${SERVICE_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}.${SERVICE_NAME}:2379"
                done
                echo ${EPS}
            }

            member_hash() {
                etcdctl member list | grep http://${HOSTNAME}.${SERVICE_NAME}:2380 | cut -d':' -f1 | cut -d'[' -f1
            }

            # we should wait for other pods to be up before trying to join
            # otherwise we got "no such host" errors when trying to resolve other members
            for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
                while true; do
                    echo "Waiting for ${SET_NAME}-${i}.${SERVICE_NAME} to come up"
                    ping -W 1 -c 1 ${SET_NAME}-${i}.${SERVICE_NAME} > /dev/null && break
                    sleep 1s
                done
            done

            # 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}.${SERVICE_NAME}:2380 | true
                exec etcd --name ${HOSTNAME} \
                    --listen-peer-urls http://0.0.0.0:2380 \
                    --listen-client-urls http://0.0.0.0:2379\
                    --advertise-client-urls http://${HOSTNAME}.${SERVICE_NAME}:2379 \
                    --data-dir /var/run/etcd/default.etcd
            fi

            # etcd-SET_ID
            SET_ID=${HOSTNAME##*[^0-9]}

            # 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}.${SERVICE_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 ${HOSTNAME} \
                    --listen-peer-urls http://0.0.0.0:2380 \
                    --listen-client-urls http://0.0.0.0:2379 \
                    --advertise-client-urls http://${HOSTNAME}.${SERVICE_NAME}:2379 \
                    --data-dir /var/run/etcd/default.etcd \
                    --initial-advertise-peer-urls http://${HOSTNAME}.${SERVICE_NAME}:2380 \
                    --initial-cluster ${ETCD_INITIAL_CLUSTER} \
                    --initial-cluster-state ${ETCD_INITIAL_CLUSTER_STATE}
            fi

            PEERS=""
            for i in $(seq 0 $((${INITIAL_CLUSTER_SIZE} - 1))); do
                PEERS="${PEERS}${PEERS:+,}${SET_NAME}-${i}=http://${SET_NAME}-${i}.${SERVICE_NAME}:2380"
            done

            collect_member &

            # join member
            exec etcd --name ${HOSTNAME} \
                --initial-advertise-peer-urls http://${HOSTNAME}.${SERVICE_NAME}:2380 \
                --listen-peer-urls http://0.0.0.0:2380 \
                --listen-client-urls http://0.0.0.0:2379 \
                --advertise-client-urls http://${HOSTNAME}.${SERVICE_NAME}:2379 \
                --initial-cluster-token etcd-cluster-1 \
                --initial-cluster ${PEERS} \
                --initial-cluster-state new \
                --data-dir /var/run/etcd/default.etcd
        volumeMounts:
        - name: {{ include "common.fullname" . }}-data
          mountPath: /var/run/etcd
  {{- if .Values.persistence.enabled }}
  volumeClaimTemplates:
  - metadata:
      name: {{ include "common.fullname" . }}-data
    spec:
      accessModes:
        - "{{ .Values.persistence.accessMode }}"
      resources:
        requests:
          # upstream recommended max is 700M
          storage: "{{ .Values.persistence.storage }}"
      storageClassName: {{ include "common.fullname" . }}-data
  {{- else }}
      volumes:
      - name: {{ include "common.fullname" . }}-data
      {{- if .Values.memoryMode }}
        emptyDir:
          medium: Memory
      {{- else }}
        emptyDir: {}
      {{- end }}
  {{- end }}