k8s 搭建 MySQL 主从失败

nfs 作为存储，pvc 和 pv 都是 bound 状态，而且还测试过 pod 都能够向 nfs 里面写入文件，但搭建 mysql 就报错：

Events: Type Reason Age From Message ---- ------ ---- ---- ------- Warning FailedScheduling 25m default-scheduler 0/4 nodes are available: 4 pod has unbound immediate PersistentVolumeClaims. preemption: 0/4 nodes are available: 4 Preemption is not helpful for scheduling. Normal Scheduled 25m default-scheduler Successfully assigned lzipant/mysql-0 to arch124 Normal Pulling 25m kubelet Pulling image "mysql:5.7" Normal Pulled 25m kubelet Successfully pulled image "mysql:5.7" in 3.099960834s Normal Created 24m (x5 over 25m) kubelet Created container init-mysql Normal Pulled 24m (x4 over 25m) kubelet Container image "mysql:5.7" already present on machine Normal Started 24m (x5 over 25m) kubelet Started container init-mysql Warning BackOff 43s (x117 over 25m) kubelet Back-off restarting failed container 

各项 yaml 如下：

configMap.yaml:

apiVersion: v1 kind: ConfigMap metadata: name: mysql namespace: lzipant labels: app: mysql data: master.cnf: | [mysqld] log-bin slave.cnf: | [mysqld] super-read-only 

service.yaml:

apiVersion: v1 kind: ConfigMap metadata: name: mysql namespace: lzipant labels: app: mysql data: master.cnf: | [mysqld] log-bin slave.cnf: | [mysqld] super-read-only 

statefulSet.yaml：

apiVersion: apps/v1 kind: StatefulSet metadata: name: mysql namespace: lzipant spec: selector: matchLabels: # 适用于所有 label 包括 app=mysql 的 pod app: mysql serviceName: mysql replicas: 3 # 定义 pod template: metadata: labels: app: mysql spec: # 在 init 容器中为 pod 中的 mysql 容器做初始化工作 initContainers: # init-mysql 容器会分配 pod 的角色是 master 还是 slave, 然后生成配置文件 - name: init-mysql image: mysql:5.7 command: - bash - "-c" - | set -ex # 生成 server-id [[ `hostname` =~ -([0-9]+)$ ]] || exit 1 ordinal=${BASH_REMATCH[1]} echo [mysqld] > /mnt/conf.d/server-id.cnf # 写入 server-id echo server-id=$((100 + $ordinal)) >> /mnt/conf.d/server-id.cnf # server-id 尾号为 0 作为 master, 否则作为 slave # 这里 cp 到 pod 中的 cnf 会与 server-id.cnf 一块被 mysql.cnf include 进去 # 这里指定了序号为 0 的 pod 会作为 master 节点提供写, 其他 pod 作为 slave 节点提供读 if [[ $ordinal -eq 0 ]]; then cp /mnt/config-map/master.cnf /mnt/conf.d/ else cp /mnt/config-map/slave.cnf /mnt/conf.d/ fi volumeMounts: # 将 conf 临时卷挂载到了 pod 的 /mnt/conf.d 路径下 - name: conf mountPath: /mnt/conf.d # 这里把 ConfigMap 中的配置怪哉到了 pod 的 /mnt/config-map 路径下 - name: config-map mountPath: /mnt/config-map # 这一个 init 容器会正在 pod 启动时假定之前已经存在数据, 并将之前的数据复制过来, 以确保新 pod 中有数据可以提供使用 - name: clone-mysql # xtrabackup 是一个开源工具, 用于克隆 mysql 的数据 image: ist0ne/xtrabackup:latest command: - bash - "-c" - | set -ex # Skip the clone if data already exists. [[ -d /var/lib/mysql/mysql ]] && exit 0 # Skip the clone on master (ordinal index 0). [[ `hostname` =~ -([0-9]+)$ ]] || exit 1 ordinal=${BASH_REMATCH[1]} [[ $ordinal -eq 0 ]] && exit 0 # Clone data from previous peer. ncat --recv-only mysql-$(($ordinal-1)).mysql 3307 | xbstream -x -C /var/lib/mysql # Prepare the backup. xtrabackup --prepare --target-dir=/var/lib/mysql volumeMounts: - name: mysql-data mountPath: /var/lib/mysql subPath: mysql - name: conf mountPath: /etc/mysql/conf.d containers: # 实际运行 mysqld 服务的 mysql 容器 - name: mysql image: mysql:5.7 env: - name: MYSQL_ROOT_PASSWORD value: "abcdef" ports: - name: mysql containerPort: 3306 volumeMounts: # 将 data 卷的 mysql 目录挂在到容器的 /var/lib/mysql - name: mysql-data mountPath: /var/lib/mysql subPath: mysql - name: conf mountPath: /etc/mysql/conf.d resources: requests: cpu: 500m memory: 1Gi # 启动存活探针, 如果失败会重启 pod livenessProbe: exec: command: ["mysqladmin", "ping"] initialDelaySeconds: 30 periodSeconds: 10 timeoutSeconds: 5 # 启动就绪探针确保容器的运行正常, 如果有失败会将 pod 从 service 关联的 endpoint 中剔除 readinessProbe: exec: # Check we can execute queries over TCP (skip-networking is off). command: ["mysql", "-h", "127.0.0.1", "-e", "SELECT 1"] initialDelaySeconds: 5 periodSeconds: 2 timeoutSeconds: 1 # init 结束后还会在启动一个 xtrabackup 容器作为 mysqld 容器的 sidecar 运行 - name: xtrabackup image: ist0ne/xtrabackup:latest ports: - name: xtrabackup containerPort: 3307 command: - bash - "-c" - | set -ex cd /var/lib/mysql # 他会在启动时查看之前是否有数据克隆文件存在, 如果有那就去其他从节点复制数据, 如果没有就去主节点复制数据 # Determine binlog position of cloned data, if any. if [[ -f xtrabackup_slave_info && "x$(<xtrabackup_slave_info)" != "x" ]]; then # XtraBackup already generated a partial "CHANGE MASTER TO" query # because we're cloning from an existing slave. (Need to remove the tailing semicolon!) cat xtrabackup_slave_info | sed -E 's/;$//g' > change_master_to.sql.in # Ignore xtrabackup_binlog_info in this case (it's useless). rm -f xtrabackup_slave_info xtrabackup_binlog_info elif [[ -f xtrabackup_binlog_info ]]; then # We're cloning directly from master. Parse binlog position. [[ `cat xtrabackup_binlog_info` =~ ^(.*?)[[:space:]]+(.*?)$ ]] || exit 1 rm -f xtrabackup_binlog_info xtrabackup_slave_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 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" mysql -h 127.0.0.1 \ -e "$(<change_master_to.sql.in), \ MASTER_HOST='mysql-0.mysql', \ MASTER_USER='root', \ MASTER_PASSWORD='', \ MASTER_CONNECT_RETRY=10; \ START SLAVE;" || exit 1 # In case of container restart, attempt this at-most-once. mv change_master_to.sql.in change_master_to.sql.orig fi # Start a server to send backups when requested by peers. 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: # 将 data 卷的 mysql 目录挂在到容器的 /var/lib/mysql - name: mysql-data mountPath: /var/lib/mysql subPath: mysql - name: conf mountPath: /etc/mysql/conf.d volumes: - name: conf # pod 在节点上被移除时, emptyDir 会同时被删除 # emptyDir 一般被用作缓存目录, 这里用在 config emptyDir: {} - name: config-map # ConfigMap 对象中存储的数据可以被 configMap 类型的卷引用, 然后被 Pod 中运行的容器使用 # 这里引用了前面定义了名称为 mysql 的 ConfigMap 对象 configMap: name: mysql volumeClaimTemplates: # 这里面定义的是对 PVC 的模板, 这里没有单独为 mysql 创建 pvc, 而是动态创建的 - metadata: name: mysql-data namespace: lzipant spec: accessModes: ["ReadWriteOnce"] # 如果没有配置默认的 storageClass 的话, 需要指定 storageClassName storageClassName: managed-nfs-storage resources: requests: storage: 5Gi 

storageClass.yaml:

apiVersion: storage.k8s.io/v1 kind: StorageClass metadata: name: managed-nfs-storage namespace: lzipant provisioner: fuseim.pri/ifs # must match deployement env PROVISIONER_NAME reclaimPolicy: Retain