# 利用K8S部署一主n从的MySQL数据库
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: mysql
  namespace: test
spec:
  selector:
    matchLabels:
      qcloud-app: mysql
  serviceName: mysql
  # 3个副本，在这里是一主两从
  replicas: 3
  template:
    metadata:
      labels:
        qcloud-app: mysql
    spec:
      initContainers:
      # init-mysql 用于给 mysql 容器按主从身份给对应的配置文件
      - name: init-mysql
        image: mysql:5.7
        command:
        - bash
        - "-c"
        - |
          set -ex
          # 按pod启动顺序ID，生成server-id
          [[ `hostname` =~ -([0-9]+)$ ]] || exit 1
          ordinal=${BASH_REMATCH[1]}
          echo [mysqld] > /mnt/conf.d/server-id.cnf
          # Add an offset to avoid reserved server-id=0 value.
          echo server-id=$((100 + $ordinal)) >> /mnt/conf.d/server-id.cnf
          # Copy appropriate conf.d files from config-map to emptyDir.
          # 只有第一个Pod做Master，其他Pod都是Slave
          if [[ $ordinal -eq 0 ]]; then
            cp /mnt/config-map/master.cnf /mnt/conf.d/
          else
            cp /mnt/config-map/slave.cnf /mnt/conf.d/
          fi
        volumeMounts:
        - name: conf
          mountPath: /mnt/conf.d
        - name: config-map
          mountPath: /mnt/config-map
      # clone-mysql 的目的是让 Slave在初始化的时候从上一个Pod复制数据
      # 还有一个 xtrabackup 容器在3307端口提供了备份服务
      - name: clone-mysql
        image: gcr.io/google-samples/xtrabackup:1.0
        command:
        - bash
        - "-c"
        - |
          set -ex
          # 如果已经有初始数据，如：之前启动过，就跳过克隆，走mysql的内部同步机制
          [[ -d /var/lib/mysql/mysql ]] && exit 0
          # 如果是Master就跳过这个克隆过程
          [[ `hostname` =~ -([0-9]+)$ ]] || exit 1
          ordinal=${BASH_REMATCH[1]}
          [[ $ordinal -eq 0 ]] && exit 0
          # 从上一个Pod的xtrabackup服务克隆数据
          ncat --recv-only mysql-$(($ordinal-1)).mysql 3307 | xbstream -x -C /var/lib/mysql
          # Prepare the backup.
          xtrabackup --prepare --target-dir=/var/lib/mysql
        volumeMounts:
        - name: data
          mountPath: /var/lib/mysql
          # 用subPath是为了避免pvc根目录下面存在文件或者目录, 影响mysql启动, subPath不存在时会自动创建
          subPath: mysql
        - name: conf
          mountPath: /etc/mysql/conf.d
      containers:
      - name: mysql
        image: mysql:5.7
        env:
        # 这里root使用了空密码, 生产环境可以从secret读取密码到环境变量MYSQL_ROOT_PASSWORD
        - name: MYSQL_ALLOW_EMPTY_PASSWORD
          value: "1"
        ports:
        - name: mysql
          containerPort: 3306
        volumeMounts:
        - name: data
          mountPath: /var/lib/mysql
          subPath: mysql
        - name: conf
          mountPath: /etc/mysql/conf.d
        resources:
          requests:
            cpu: 500m
            memory: 1Gi
        livenessProbe: # 存活检查
          exec:
            command: ["mysqladmin", "ping"]
          initialDelaySeconds: 30
          periodSeconds: 10
          timeoutSeconds: 5
        readinessProbe: # 可服务检查
          exec:
            # Check we can execute queries over TCP (skip-networking is off).
            command: ["mysql", "-h", "127.0.0.1", "-e", "SELECT 1"]
          initialDelaySeconds: 5
          periodSeconds: 2
          timeoutSeconds: 1
      # xtrabackup 在3307端口提供备份服务, 如果是slave节点，通知mysqld以slave模式启动
      - name: xtrabackup
        image: gcr.io/google-samples/xtrabackup:1.0
        ports:
        - name: xtrabackup
          containerPort: 3307
        command:
        - bash
        - "-c"
        - |
          set -ex
          cd /var/lib/mysql

          # Determine binlog position of cloned data, if any.
          if [[ -f xtrabackup_slave_info ]]; then
            # 正在从Slave克隆
            mv xtrabackup_slave_info change_master_to.sql.in
            # 删除没用的xtrabackup_binlog_info
            rm -f xtrabackup_binlog_info
          elif [[ -f xtrabackup_binlog_info ]]; then
            # 正在从Master克隆. 解析 binlog 的位置.
            [[ `cat xtrabackup_binlog_info` =~ ^(.*?)[[:space:]]+(.*?)$ ]] || exit 1
            # xtrabackup_binlog_info的格式: binlog文件名 binlog_pos
            rm xtrabackup_binlog_info
            echo "CHANGE MASTER TO MASTER_LOG_FILE='${BASH_REMATCH[1]}',\
                  MASTER_LOG_POS=${BASH_REMATCH[2]}" > change_master_to.sql.in
          fi

          # Check if we need to complete a clone by starting replication.
          if [[ -f change_master_to.sql.in ]]; then
            # 等待同Pod的mysql容器启动
            echo "Waiting for mysqld to be ready (accepting connections)"
            until mysql -h 127.0.0.1 -e "SELECT 1"; do sleep 1; done

            echo "Initializing replication from clone position"
            # 改名change_master_to.sql.in, 避免重启的时候又执行了一次
            mv change_master_to.sql.in change_master_to.sql.orig
            # 连接到本pod的mysql服务, 切换为slave模式
            # sql: CHANGE MASTER TO MASTER_LOG_FILE='binlog文件名', MASTER_LOG_POS=binlog位置,
            #      MASTER_HOST='mysql-0.mysql',
            #      MASTER_USER='root',
            #      MASTER_PASSWORD='',
            #      MASTER_CONNECT_RETRY=10;
            # sql: START SLAVE;
            mysql -h 127.0.0.1 <<EOF
          $(<change_master_to.sql.orig),
            MASTER_HOST='mysql-0.mysql',
            MASTER_USER='root',
            MASTER_PASSWORD='',
            MASTER_CONNECT_RETRY=10;
          START SLAVE;
          EOF
          fi

          # 在3307端口上为其他pods提供克隆服务, ncat成为0号主进程
          exec ncat --listen --keep-open --send-only --max-conns=1 3307 -c \
            "xtrabackup --backup --slave-info --stream=xbstream --host=127.0.0.1 --user=root"
        volumeMounts:
        - name: data
          mountPath: /var/lib/mysql
          subPath: mysql
        - name: conf
          mountPath: /etc/mysql/conf.d
        resources:
          requests:
            cpu: 100m
            memory: 100Mi
      volumes:
      - name: conf
        emptyDir: {}
      - name: config-map
        configMap:
          name: mysql
  volumeClaimTemplates:
  # 每个节点都是用10GB的存储空间
  - metadata:
      name: data
    spec:
      # 独占读写
      accessModes: ["ReadWriteOnce"]
      resources:
        requests:
          storage: 10Gi