将 PySpark 从 Docker 容器连接到 Kafka

Question

我有一个使用 Docker 管理的 Kafka 集群。

我有一个运行代理的容器和另一个运行 pyspark 程序的容器，该程序应该连接到代理容器内的 kafka 主题。

如果我在本地笔记本电脑上运行 pyspark 脚本，一切运行良好，但如果我尝试从 pyspark 容器内运行相同的代码，我会收到以下错误：

AnalysisException: Failed to find data source: kafka. Please deploy the application as per the deployment section of "Structured Streaming + Kafka Integration Guide"

有人知道如何从另一个外部容器访问在 docker 容器中运行的 Kafka 主题吗？

这是 PySpark 代码

df = spark \
    .readStream \
    .format("kafka") \
    .option("kafka.bootstrap.servers", "localhost:9092") \
    .option("failOnDataLoss", "false") \
    .option("subscribe", "tweets") \
    .option("startingOffsets", "earliest") \
    .load()

这是我的 docker-compose.yml

version: "2"
services:
  zookeeper:
    image: confluentinc/cp-zookeeper:6.1.0
    hostname: zookeeper
    container_name: zookeeper
    ports:
      - "2181:2181"
    environment:
      ZOOKEEPER_CLIENT_PORT: 2181
      ZOOKEEPER_TICK_TIME: 2000

  broker:
    image: confluentinc/cp-server:6.1.0
    hostname: broker
    container_name: broker
    depends_on:
      - zookeeper
    ports:
      - "9092:9092"
      - "9101:9101"
    environment:
      KAFKA_BROKER_ID: 1
      KAFKA_ZOOKEEPER_CONNECT: "zookeeper:2181"
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://broker:29092,PLAINTEXT_HOST://localhost:9092
      KAFKA_METRIC_REPORTERS: io.confluent.metrics.reporter.ConfluentMetricsReporter
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 0
      KAFKA_CONFLUENT_LICENSE_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_CONFLUENT_BALANCER_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
      KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
      KAFKA_JMX_PORT: 9101
      KAFKA_JMX_HOSTNAME: localhost
      KAFKA_CONFLUENT_SCHEMA_REGISTRY_URL: http://schema-registry:8081
      CONFLUENT_METRICS_REPORTER_BOOTSTRAP_SERVERS: broker:29092
      CONFLUENT_METRICS_REPORTER_TOPIC_REPLICAS: 1
      CONFLUENT_METRICS_ENABLE: "true"
      CONFLUENT_SUPPORT_CUSTOMER_ID: "anonymous"

  schema-registry:
    image: confluentinc/cp-schema-registry:6.1.0
    hostname: schema-registry
    container_name: schema-registry
    depends_on:
      - broker
    ports:
      - "8081:8081"
    environment:
      SCHEMA_REGISTRY_HOST_NAME: schema-registry
      SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: "broker:29092"
      SCHEMA_REGISTRY_LISTENERS: http://0.0.0.0:8081

  connect:
    image: cnfldemos/cp-server-connect-datagen:latest
    hostname: connect
    container_name: connect
    build:
      context: .
      dockerfile: Dockerfile_connect
    depends_on:
      - broker
      - schema-registry
    ports:
      - "8083:8083"
    environment:
      CONNECT_BOOTSTRAP_SERVERS: "broker:29092"
      CONNECT_REST_ADVERTISED_HOST_NAME: connect
      CONNECT_REST_PORT: 8083
      CONNECT_GROUP_ID: compose-connect-group
      CONNECT_CONFIG_STORAGE_TOPIC: docker-connect-configs
      CONNECT_CONFIG_STORAGE_REPLICATION_FACTOR: 1
      CONNECT_OFFSET_FLUSH_INTERVAL_MS: 10000
      CONNECT_OFFSET_STORAGE_TOPIC: docker-connect-offsets
      CONNECT_OFFSET_STORAGE_REPLICATION_FACTOR: 1
      CONNECT_STATUS_STORAGE_TOPIC: docker-connect-status
      CONNECT_STATUS_STORAGE_REPLICATION_FACTOR: 1
      CONNECT_KEY_CONVERTER: org.apache.kafka.connect.storage.StringConverter
      CONNECT_VALUE_CONVERTER: io.confluent.connect.avro.AvroConverter
      CONNECT_VALUE_CONVERTER_SCHEMA_REGISTRY_URL: http://schema-registry:8081
      # CLASSPATH required due to CC-2422
      CLASSPATH: /usr/share/java/monitoring-interceptors/monitoring-interceptors-6.1.0.jar
      CONNECT_PRODUCER_INTERCEPTOR_CLASSES: "io.confluent.monitoring.clients.interceptor.MonitoringProducerInterceptor"
      CONNECT_CONSUMER_INTERCEPTOR_CLASSES: "io.confluent.monitoring.clients.interceptor.MonitoringConsumerInterceptor"
      CONNECT_PLUGIN_PATH: "/usr/share/java,/usr/share/confluent-hub-components"
      CONNECT_LOG4J_LOGGERS: org.apache.zookeeper=ERROR,org.I0Itec.zkclient=ERROR,org.reflections=ERROR

  control-center:
    image: confluentinc/cp-enterprise-control-center:6.1.0
    hostname: control-center
    container_name: control-center
    depends_on:
      - broker
      - schema-registry
      - connect
      - ksqldb-server
    ports:
      - "9021:9021"
    environment:
      CONTROL_CENTER_BOOTSTRAP_SERVERS: "broker:29092"
      CONTROL_CENTER_CONNECT_CLUSTER: "connect:8083"
      CONTROL_CENTER_KSQL_KSQLDB1_URL: "http://ksqldb-server:8088"
      CONTROL_CENTER_KSQL_KSQLDB1_ADVERTISED_URL: "http://localhost:8088"
      CONTROL_CENTER_SCHEMA_REGISTRY_URL: "http://schema-registry:8081"
      CONTROL_CENTER_REPLICATION_FACTOR: 1
      CONTROL_CENTER_INTERNAL_TOPICS_PARTITIONS: 1
      CONTROL_CENTER_MONITORING_INTERCEPTOR_TOPIC_PARTITIONS: 1
      CONFLUENT_METRICS_TOPIC_REPLICATION: 1
      PORT: 9021

  ksqldb-server:
    image: confluentinc/cp-ksqldb-server:6.1.0
    hostname: ksqldb-server
    container_name: ksqldb-server
    depends_on:
      - broker
      - connect
    ports:
      - "8088:8088"
    environment:
      KSQL_CONFIG_DIR: "/etc/ksql"
      KSQL_BOOTSTRAP_SERVERS: "broker:29092"
      KSQL_HOST_NAME: ksqldb-server
      KSQL_LISTENERS: "http://0.0.0.0:8088"
      KSQL_CACHE_MAX_BYTES_BUFFERING: 0
      KSQL_KSQL_SCHEMA_REGISTRY_URL: "http://schema-registry:8081"
      KSQL_PRODUCER_INTERCEPTOR_CLASSES: "io.confluent.monitoring.clients.interceptor.MonitoringProducerInterceptor"
      KSQL_CONSUMER_INTERCEPTOR_CLASSES: "io.confluent.monitoring.clients.interceptor.MonitoringConsumerInterceptor"
      KSQL_KSQL_CONNECT_URL: "http://connect:8083"
      KSQL_KSQL_LOGGING_PROCESSING_TOPIC_REPLICATION_FACTOR: 1
      KSQL_KSQL_LOGGING_PROCESSING_TOPIC_AUTO_CREATE: "true"
      KSQL_KSQL_LOGGING_PROCESSING_STREAM_AUTO_CREATE: "true"

  ksqldb-cli:
    image: confluentinc/cp-ksqldb-cli:6.1.0
    container_name: ksqldb-cli
    depends_on:
      - broker
      - connect
      - ksqldb-server
    entrypoint: /bin/sh
    tty: true

  ksql-datagen:
    image: confluentinc/ksqldb-examples:6.1.0
    hostname: ksql-datagen
    container_name: ksql-datagen
    depends_on:
      - ksqldb-server
      - broker
      - schema-registry
      - connect
    command: "bash -c 'echo Waiting for Kafka to be ready... && \
      cub kafka-ready -b broker:29092 1 40 && \
      echo Waiting for Confluent Schema Registry to be ready... && \
      cub sr-ready schema-registry 8081 40 && \
      echo Waiting a few seconds for topic creation to finish... && \
      sleep 11 && \
      tail -f /dev/null'"
    environment:
      KSQL_CONFIG_DIR: "/etc/ksql"
      STREAMS_BOOTSTRAP_SERVERS: broker:29092
      STREAMS_SCHEMA_REGISTRY_HOST: schema-registry
      STREAMS_SCHEMA_REGISTRY_PORT: 8081

  rest-proxy:
    image: confluentinc/cp-kafka-rest:6.1.0
    depends_on:
      - broker
      - schema-registry
    ports:
      - 8082:8082
    hostname: rest-proxy
    container_name: rest-proxy
    environment:
      KAFKA_REST_HOST_NAME: rest-proxy
      KAFKA_REST_BOOTSTRAP_SERVERS: "broker:29092"
      KAFKA_REST_LISTENERS: "http://0.0.0.0:8082"
      KAFKA_REST_SCHEMA_REGISTRY_URL: "http://schema-registry:8081"

  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:7.11.2
    container_name: elasticsearch
    environment:
      - xpack.security.enabled=false
      - discovery.type=single-node
    ulimits:
      memlock:
        soft: -1
        hard: -1
      nofile:
        soft: 65536
        hard: 65536
    cap_add:
      - IPC_LOCK
    volumes:
      - elasticsearch-data:/usr/share/elasticsearch/data
    ports:
      - 9200:9200
      - 9300:9300

  kibana:
    container_name: kibana
    image: docker.elastic.co/kibana/kibana:7.11.2
    environment:
      - ELASTICSEARCH_HOSTS=http://elasticsearch:9200
    ports:
      - 5601:5601
    depends_on:
      - elasticsearch

  pyspark:
    image: jupyter/pyspark-notebook:latest
    hostname: pyspark
    container_name: pyspark
    ports:
      - 8888:8888
    #volumes:
    #  - pySpark: pySpark/
    depends_on:
      - broker

volumes:
  elasticsearch-data:
    driver: local
  pySpark:
    driver: local

Answer 1

您的设置中有几个问题：

• 如文档中所述，您不会为 Kafka 支持添加 package。 它要么需要在启动pyspark时添加，要么在初始化 session 时添加，类似这样（将3.0.1更改为 jupyter 容器中使用的版本）：

SparkSession.builder.appName('my_app')\
    .config('spark.jars.packages', 'org.apache.spark:spark-sql-kafka-0-10_2.12:3.0.1')\
    .getOrCreate()

• 您正在连接到"localhost:9092" ，但它在容器内部是不正确的，因为带有 Jupyter 的容器有自己的localhost ，它与 Kafka 容器的 localhost 不同。 您需要改用名称broker ，因为它在 docker-compose.yaml 中声明