Search code examples
apache-kafkadocker-composedebezium

How can I implement a debezium connector (Oracle) through docker-compose?


I'm currently trying to implement a debezium connector. I've used JDBC connector as introduction but I need log-based CDC. I'm using a docker-compose.yml file to establish all configuration and the database is based on Oracle.

I'm stuck because I'm getting this error "ERROR io.confluent.admin.utils.ClusterStatus - Expected 1 brokers but found only 0. Brokers found []."

Here is my docker-compose file:

Is there a simpler way to build this docker-compose?

version: '2'
services:
  zookeeper:
    image: debezium/zookeeper:1.4
    hostname: zookeeper
    container_name: zookeeper
    volumes:
      - /dados/persistence/zookeeper/data:/var/lib/zookeeper/data
      - /dados/persistence/zookeeper/log:/var/lib/zookeeper/log
    ports:
      - "2181:2181"
      - "2888:2888"
      - "3888:3888"

  broker:
    image: debezium/kafka:1.4
    hostname: broker
    container_name: broker
    volumes:
      - /dados/persistence/broker/data:/var/lib/kafka/data
    depends_on:
      - zookeeper
    ports:
      - "9092:9092"
      - "9101:9101"
    environment:
      BROKER_ID: 1
      ZOOKEEPER_CONNECT: 'zookeeper:2181'
      listener.security.protocol.map: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
      advertised.listeners: PLAINTEXT://broker:29092,PLAINTEXT_HOST://localhost:9092
      metric.reports: io.confluent.metrics.reporter.ConfluentMetricsReporter
      offset.topic.replication.factor: 1
      group.initial.rebalance.delay.ms: 0
      confluent.license.topic.replication.factor: 1
      confluent.balancer.topic.replication.factor: 1
      transaction.state.log.min.isr: 1
      transaction.state.log.replication.factor: 1
      jmx.port: 9101
      jmx.hostname: localhost
      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:6.0.1
    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: debezium/connect:1.4
    hostname: connect
    container_name: connect
    volumes:
      - /dados/packages/confluent-hub/dados/packages/confluent-hub/share/confluent-hub-components:/usr/share/confluent-hub-components/custom
      - /dados/persistence/kafka-connect/jars:/etc/kafka-connect/jars
    depends_on:
      - broker
      - schema-registry
    ports:
      - "8083:8083"
    environment:
      bootstrap.servers: 'broker:29092'
      advertised.host.name: connect
      rest.port: 8083
      group.id: compose-connect-group
      CONFIG_STORAGE_TOPIC: docker-connect-configs
      config.storage.replication.factor: 1
      offset.fulsh.interval.ms: 10000
      OFFSET_STORAGE_TOPIC: docker-connect-offsets
      offset.storage.replication.factor: 1
      status.storage.topic: docker-connect-status
      status.storage.replication.factor: 1
      key.converter: org.apache.kafka.connect.storage.StringConverter
      value.converter: io.confluent.connect.avro.AvroConverter
      value.converter.schema.registry.url: http://schema-registry:8081
      internal.key.converter: "org.apache.kafka.connect.json.JsonConverter"
      internal.value.converter: "org.apache.kafka.connect.json.JsonConverter"
      # CLASSPATH required due to CC-2422
      CLASSPATH: /usr/share/java/monitoring-interceptors/monitoring-interceptors-6.0.1.jar
      producer.interceptor.classes: "io.confluent.monitoring.clients.interceptor.MonitoringProducerInterceptor"
      consumer.interceptor.classes: "io.confluent.monitoring.clients.interceptor.MonitoringConsumerInterceptor"
      plugin_path: "/usr/share/java,/usr/share/confluent-hub-components,/usr/share/confluent-hub-components/custom"
      log4j.loggers: org.apache.zookeeper=ERROR,org.I0Itec.zkclient=ERROR,org.reflections=ERROR

  control-center:
    image: confluentinc/cp-enterprise-control-center:6.0.1
    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://10.58.0.207:8088"
      CONTROL_CENTER_KSQL_KSQLDB1_ADVERTISED_URL: "http://10.58.0.207:8088"
      CONTROL_CENTER_SCHEMA_REGISTRY_URL: "http://10.58.0.207:8081"
      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:6.0.1
    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:6.0.1
    container_name: ksqldb-cli
    depends_on:
      - broker
      - connect
      - ksqldb-server
    entrypoint: /bin/sh
    tty: true

  ksql-datagen:
    image: confluentinc/ksqldb-examples:6.0.1
    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:6.0.1
    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'

Solution

  • Here's a working Docker Compose which uses the Debezium Oracle connector.

    ---
    version: '2'
    services:
      zookeeper:
        image: confluentinc/cp-zookeeper:5.5.0
        container_name: zookeeper
        environment:
          ZOOKEEPER_CLIENT_PORT: 2181
          ZOOKEEPER_TICK_TIME: 2000
    
      kafka:
        image: confluentinc/cp-kafka:5.5.0
        container_name: kafka
        depends_on:
          - zookeeper
        ports:
        # "`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-
        # An important note about accessing Kafka from clients on other machines:
        # -----------------------------------------------------------------------
        #
        # The config used here exposes port 9092 for _external_ connections to the broker
        # i.e. those from _outside_ the docker network. This could be from the host machine
        # running docker, or maybe further afield if you've got a more complicated setup.
        # If the latter is true, you will need to change the value 'localhost' in
        # KAFKA_ADVERTISED_LISTENERS to one that is resolvable to the docker host from those
        # remote clients
        #
        # For connections _internal_ to the docker network, such as from other services
        # and components, use kafka:29092.
        #
        # See https://rmoff.net/2018/08/02/kafka-listeners-explained/ for details
        # "`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-'"`-._,-
        #
          - 9092:9092
        environment:
          KAFKA_BROKER_ID: 1
          KAFKA_ZOOKEEPER_CONNECT: zookeeper:2181
          KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
          KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
          KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:29092,PLAINTEXT_HOST://localhost:9092
          KAFKA_AUTO_CREATE_TOPICS_ENABLE: "true"
          KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
          KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
          KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
          KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 100
    
      schema-registry:
        image: confluentinc/cp-schema-registry:5.5.0
        container_name: schema-registry
        ports: 
          - 8081:8081
        depends_on:
          - zookeeper
          - kafka
        environment:
          SCHEMA_REGISTRY_HOST_NAME: schema-registry
          SCHEMA_REGISTRY_KAFKASTORE_CONNECTION_URL: zookeeper:2181
    
      kafka-connect:
        image: confluentinc/cp-kafka-connect-base:5.5.0
        container_name: kafka-connect
        depends_on:
          - zookeeper
          - kafka
          - schema-registry
        ports:
          - 8083:8083
        environment:
          CONNECT_BOOTSTRAP_SERVERS: "kafka:29092"
          CONNECT_REST_PORT: 8083
          CONNECT_GROUP_ID: compose-connect-group
          CONNECT_CONFIG_STORAGE_TOPIC: docker-connect-configs
          CONNECT_OFFSET_STORAGE_TOPIC: docker-connect-offsets
          CONNECT_STATUS_STORAGE_TOPIC: docker-connect-status
          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'
          CONNECT_INTERNAL_KEY_CONVERTER: "org.apache.kafka.connect.json.JsonConverter"
          CONNECT_INTERNAL_VALUE_CONVERTER: "org.apache.kafka.connect.json.JsonConverter"
          CONNECT_REST_ADVERTISED_HOST_NAME: "kafka-connect"
          CONNECT_LOG4J_ROOT_LOGLEVEL: "INFO"
          CONNECT_LOG4J_APPENDER_STDOUT_LAYOUT_CONVERSIONPATTERN: "[%d] %p %X{connector.context}%m (%c:%L)%n"
          CONNECT_LOG4J_LOGGERS: "org.apache.kafka.connect.runtime.rest=WARN,org.reflections=ERROR"
          CONNECT_CONFIG_STORAGE_REPLICATION_FACTOR: "1"
          CONNECT_OFFSET_STORAGE_REPLICATION_FACTOR: "1"
          CONNECT_STATUS_STORAGE_REPLICATION_FACTOR: "1"
          CONNECT_PLUGIN_PATH: '/usr/share/java,/usr/share/confluent-hub-components/'
          #
          # Make sure you set this for the correct path that the library files for InstantClient have been installed into
          LD_LIBRARY_PATH: '/usr/share/java/debezium-connector-oracle/instantclient_19_6/'
        command: 
          - bash 
          - -c 
          - |
            echo "Installing connector plugins"
            confluent-hub install --no-prompt confluentinc/kafka-connect-jdbc:5.5.0
            confluent-hub install --no-prompt confluentinc/kafka-connect-datagen:0.3.2
            #
            echo "Downloading JDBC drivers"
            cd /usr/share/confluent-hub-components/confluentinc-kafka-connect-jdbc/lib
            curl https://maven.xwiki.org/externals/com/oracle/jdbc/ojdbc8/12.2.0.1/ojdbc8-12.2.0.1.jar -o ojdbc8-12.2.0.1.jar
            # -----------
            # Install Debezium Oracle connector and required libraries
            # -- Download
            curl "https://oss.sonatype.org/service/local/repositories/snapshots/content/io/debezium/debezium-connector-oracle/1.2.0-SNAPSHOT/debezium-connector-oracle-1.2.0-20200612.041347-34-plugin.tar.gz" | \
              tar xvfz - --directory /usr/share/java/
            # -- Install the required library files
            apt-get update
            apt-get install -y --force-yes unzip libaio1
            wget "https://download.oracle.com/otn_software/linux/instantclient/19600/instantclient-basiclite-linux.x64-19.6.0.0.0dbru.zip" -O /tmp/ic.zip
            unzip /tmp/ic.zip -d /usr/share/java/debezium-connector-oracle/
            # -----------
            # Launch the Kafka Connect worker
            /etc/confluent/docker/run &
            #
            # Don't exit
            sleep infinity
    
      ksqldb:
        image: confluentinc/ksqldb-server:0.9.0
        container_name: ksqldb
        depends_on:
          - kafka
          - kafka-connect
        ports:
          - "8088:8088"
        environment:
          KSQL_LISTENERS: http://0.0.0.0:8088
          KSQL_BOOTSTRAP_SERVERS: kafka:29092
          KSQL_KSQL_LOGGING_PROCESSING_STREAM_AUTO_CREATE: "true"
          KSQL_KSQL_LOGGING_PROCESSING_TOPIC_AUTO_CREATE: "true"
          KSQL_KSQL_CONNECT_URL: http://kafka-connect:8083
          KSQL_KSQL_SCHEMA_REGISTRY_URL: http://schema-registry:8081
          KSQL_KSQL_SERVICE_ID: confluent_rmoff_01
          KSQL_KSQL_HIDDEN_TOPICS: '^_.*'
    
    # Other systems
      oracle:
        # You need to build this image first, following the instructions at 
        # https://github.com/oracle/docker-images/blob/master/OracleDatabase/SingleInstance/README.md
        #
        # NB: There's no sudo on the image but you can run stuff as root using
        # docker exec -it -u root oracle <cmd>
        # e.g.: docker exec -it -u root oracle bash -c "rpm -Uvh https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm &&  yum install -y rlwrap"
        image: oracle/database:12.2.0.1-ee
        container_name: oracle
        environment:
          - ORACLE_PWD=Admin123
        ports:
          - 1521:1521
        volumes:
          - $PWD/oradata:/opt/oracle/oradata
          - $PWD/oradata/recovery_area:/opt/oracle/oradata/recovery_area
          - $PWD/ora-setup-scripts:/opt/oracle/scripts/setup
          - $PWD/ora-startup-scripts:/opt/oracle/scripts/startup
    
      postgres:
        # *-----------------------------*
        # To connect to the DB: 
        #   docker exec -it postgres bash -c 'psql -U $POSTGRES_USER $POSTGRES_DB'
        # *-----------------------------*
        image: postgres:12
        container_name: postgres
        environment:
         - POSTGRES_USER=postgres
         - POSTGRES_PASSWORD=postgres
    
      kafkacat:
        image: edenhill/kafkacat:1.5.0
        container_name: kafkacat
        links:
          - kafka
          - schema-registry
        entrypoint: 
          - /bin/sh 
          - -c 
          - |
            apk add jq; 
            while [ 1 -eq 1 ];do sleep 60;done