k8s hudi表快速测试指南

ubuntu安装nfs服务

sudo apt-get install nfs-kernel-server

sudo vim /etc/exports

/data1/nfs/rootfs *(rw,sync,no_root_squash,no_subtree_check)

解析：

/data1/nfs/rootfs——NFS服务器端的目录，用于与nfs客户端共享

*——允许所有的网段访问，也可以使用具体的IP

rw——挂接此目录的客户端对该共享目录具有读写权限

sync——资料同步写入内存和硬盘

no_root_squash——root用户具有对根目录的完全管理访问权限

no_subtree_check——不检查父目录的权限

启动nfs服务

重启rpcbind服务与nfs服务，nfs是一个RPC程序，使用它前，需要映射好端口，通过rpcbind设定

sudo /etc/init.d/rpcbind restart 
sudo /etc/init.d/nfs-kernel-server restart

k8s部署nfs服务对应的storageClass：nfs-client

helm repo add nfs-subdir-external-provisioner https://kubernetes-sigs.github.io/nfs-subdir-external-provisioner/

helm install nfs-subdir-external-provisioner nfs-subdir-external-provisioner/nfs-subdir-external-provisioner \
    --set nfs.server=192.168.49.1 \
    --set nfs.path=/data1/nfs/rootfs

基于nfs部署minio

minio-pvc.yaml

kind: PersistentVolumeClaim
apiVersion: v1
metadata:
  name: minio-pvc
spec:
  storageClassName: nfs-client
  accessModes:
    - ReadWriteMany
  resources:
    requests:
      storage: 102400Mi

minio-pod.yaml

apiVersion: v1
kind: Pod
metadata:
  labels:
    app: minio
  name: minio
  namespace: default # Change this value to match the namespace metadata.name
spec:
  containers:
  - name: minio
    image: quay.io/minio/minio:latest
    command:
    - /bin/bash
    - -c
    args: 
    - minio server /data --console-address :9090
    volumeMounts:
    - mountPath: /data
      name: nfsvolume # Corresponds to the `spec.volumes` Persistent Volume
  volumes:
  - name: nfsvolume
    persistentVolumeClaim:
      claimName: minio-pvc

minio-service.yaml

apiVersion: v1
kind: Service
metadata:
  labels:
    expose: "true"
    app: minio
  name: minio
  namespace: default
spec:
  type: NodePort
  ports:
  - name: http1
    port: 9000
    protocol: TCP
    nodePort: 30012
  - name: http2
    port: 9090
    protocol: TCP
    nodePort: 30013
  selector:
    app: minio

minio部署juicefs

为了部署juicefs还需要部署mysql

mysql-pvc.yaml

kind: PersistentVolumeClaim
apiVersion: v1
metadata:
  name: mysql-pvc
spec:
  storageClassName: nfs-client
  accessModes:
    - ReadWriteMany
  resources:
    requests:
      storage: 5G

mysql-deployment.yaml

apiVersion: v1
kind: ReplicationController
metadata:
  name: mysql-rc
  namespace: default
  labels:
    name: mysql-rc
spec:
  replicas: 1
  selector:
    name: mysql-rc
  template:
    metadata:
      labels:
        name: mysql-rc
    spec:
      containers:
        - name: mysql
          image: mysql:5.7.39
          imagePullPolicy: IfNotPresent
          ports:
            - containerPort: 3306
          env:
            - name: MYSQL_ROOT_PASSWORD
              value: "root"
          volumeMounts:
            - name: mysql-persistent-storage
              mountPath: /var/lib/mysql          #MySQL容器的数据都是存在这个目录的，要对这个目录做数据持久化
      volumes:
        - name: mysql-persistent-storage
          persistentVolumeClaim:
            claimName: mysql-pvc                 #指定pvc的名称

mysql-service.yaml

apiVersion: v1
kind: Service
metadata:
  labels:
    expose: "true"
    name: mysql-rc
  name: mysql
spec:
  type: NodePort
  ports:
    - name: http
      port: 3306
      protocol: TCP
      nodePort: 30006
  selector:
    name: mysql-rc

使用juicefs初始化minio

minio默认账号密码为：minioadmin/minioadmin，在minio创建juicefs桶。

mysql默认账号密码为：root/root，在minio创建juicefs数据库

juicefs format --storage=minio --bucket=http://192.168.1.2:9000/juicefs --access-key=minioadmin --secret-key=minioadmin mysql://root:root@(192.168.1.2:3306)/juicefs juicefsminio

部署flink任务

在default namespace使用core-site.xml创建configmap，core-site

    
        fs.s3a.endpoint
        http://192.168.1.2:9000
        AWS S3 endpoint to connect to. An up-to-date list is
            provided in the AWS Documentation: regions and endpoints. Without this
            property, the standard region (s3.amazonaws.com) is assumed.
        
    

    
        fs.s3a.access.key
        PSBZMLL1NXZYCX55QMBI
    

    
        fs.s3a.secret.key
        CNACTHv4+fPHvYT7gwaKCyWR7K96zHXNU+f9yccJ
    

    
        fs.s3a.path.style.access
        true
        Enable S3 path style access ie disabling the default virtual hosting behaviour.
            Useful for S3A-compliant storage providers as it removes the need to set up DNS for virtual hosting.
        
    

    
        fs.s3a.aws.credentials.provider
        
            org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider
        
        
            Comma-separated class names of credential provider classes which implement
            com.amazonaws.auth.AWSCredentialsProvider.

            When S3A delegation tokens are not enabled, this list will be used
            to directly authenticate with S3 and DynamoDB services.
            When S3A Delegation tokens are enabled, depending upon the delegation
            token binding it may be used
            to communicate with the STS endpoint to request session/role
            credentials.

            These are loaded and queried in sequence for a valid set of credentials.
            Each listed class must implement one of the following means of
            construction, which are attempted in order:
            * a public constructor accepting java.net.URI and
            org.apache.hadoop.conf.Configuration,
            * a public constructor accepting org.apache.hadoop.conf.Configuration,
            * a public static method named getInstance that accepts no
            arguments and returns an instance of
            com.amazonaws.auth.AWSCredentialsProvider, or
            * a public default constructor.

            Specifying org.apache.hadoop.fs.s3a.AnonymousAWSCredentialsProvider allows
            anonymous access to a publicly accessible S3 bucket without any credentials.
            Please note that allowing anonymous access to an S3 bucket compromises
            security and therefore is unsuitable for most use cases. It can be useful
            for accessing public data sets without requiring AWS credentials.

            If unspecified, then the default list of credential provider classes,
            queried in sequence, is:
            * org.apache.hadoop.fs.s3a.TemporaryAWSCredentialsProvider: looks
            for session login secrets in the Hadoop configuration.
            * org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider:
            Uses the values of fs.s3a.access.key and fs.s3a.secret.key.
            * com.amazonaws.auth.EnvironmentVariableCredentialsProvider: supports
            configuration of AWS access key ID and secret access key in
            environment variables named AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY,
            and AWS_SESSION_TOKEN as documented in the AWS SDK.
            * org.apache.hadoop.fs.s3a.auth.IAMInstanceCredentialsProvider: picks up
            IAM credentials of any EC2 VM or AWS container in which the process is running.
        
    

    
        fs.defaultFS
        jfs://juicefsminio/hudi-dir
        Optional, you can also specify full path "jfs://myjfs/path-to-dir" with location to use JuiceFS
    
    
        fs.jfs.impl
        io.juicefs.JuiceFileSystem
    
    
        fs.AbstractFileSystem.jfs.impl
        io.juicefs.JuiceFS
    
    
        juicefs.meta
        mysql://root:root@(192.168.1.2:3306)/juicefs
    
    
        juicefs.cache-dir
        /tmp/juicefs-cache-dir
    
    
        juicefs.cache-size
        1024
    
    
        juicefs.access-log
        /tmp/juicefs.access.log
    

基于core-site configmap以及flink-kubernetes-operator创建flink任务

如果任务名称为basic-example，那么还需要基于上述core-site.xml创建hadoop-config-basic-example configmap

apiVersion: flink.apache.org/v1beta1
kind: FlinkDeployment
metadata:
  name: basic-example
spec:
  image: xiaozhch5/flink-sql-submit:hudi-0.12-juicefs
  flinkVersion: v1_15
  flinkConfiguration:
    taskmanager.numberOfTaskSlots: "2"
    s3.endpoint: "http://192.168.1.2:9000"
    s3.path.style.access: "true"
    s3.access.key: "PSBZMLL1NXZYCX55QMBI"
    s3.secret.key: "CNACTHv4+fPHvYT7gwaKCyWR7K96zHXNU+f9yccJ"
    state.backend.incremental: "true"
    execution.checkpointing.interval: "300000ms"
    state.savepoints.dir: "s3://flink-data/savepoints"
    state.checkpoints.dir: "s3://flink-data/checkpoints"
  serviceAccount: flink
  jobManager:
    resource:
      memory: "2048m"
      cpu: 1
  taskManager:
    resource:
      memory: "2048m"
      cpu: 2
  job:
    jarURI: local:///opt/flink/lib/flink-sql-submit-1.0.jar
    args: ["-f", "s3://flink-tasks/k8s-flink-sql-test.sql", "-m", "streaming", "-e", "http://192.168.1.2:9000", "-a", "PSBZMLL1NXZYCX55QMBI", "-s", "CNACTHv4+fPHvYT7gwaKCyWR7K96zHXNU+f9yccJ"]
    parallelism: 2
    upgradeMode: stateless
  podTemplate:
    spec:
      containers:
        - name: flink-main-container
          volumeMounts:
            - mountPath: /opt/hadoop/etc/hadoop/
              name: core-site
      volumes:
        - name: core-site
          configMap:
            name: core-site

flink sql任务为：

CREATE TABLE Orders (
    order_number BIGINT,
    price        DECIMAL(32,2),
    order_time   TIMESTAMP(3),
    PRIMARY KEY (order_number) NOT ENFORCED
) WITH (
  'connector' = 'datagen',
  'rows-per-second' = '10'
);

CREATE TABLE Orders_hudi (
    order_number BIGINT,
    price        DECIMAL(32,2),
    order_time   TIMESTAMP(3),
    PRIMARY KEY (order_number) NOT ENFORCED
) WITH (
  'connector' = 'hudi',
  'path' = 'jfs://juicefsminio/orders_hudi_2',
  'table.type' = 'MERGE_ON_READ'
);

insert into Orders_hudi select * from Orders;