Docker-Compose.yaml

# Specifies the version of Docker compose that is being used.
# Then informs Docker compose that what follows is configurations of the
# services (containers) that form the cluster.
version: "3"
services:

  zookeeper:
    image: confluentinc/cp-zookeeper:5.5.1
    hostname: zookeeper
    container_name: zookeeper
    environment:
      # Instructs ZooKeeper where to listen for connections by clients
      ZOOKEEPER_CLIENT_PORT: 2181
      # `ZOOKEEPER_TICK_TIME` is a configuration parameter that determines the
      # length of a ZooKeeper tick in milliseconds. The tick is a basic time
      # unit used by ZooKeeper for various purposes, including:
      # (1) heartbeats (to detect the liveliness of nodes in the cluster) and
      # (2) timeouts (If a client does not receive a heartbeat within a certain
      # multiple of `ZOOKEEPER_TICK_TIME`, it may consider its session as
      # expired and needs to re-establish a connection).
      # In this case, it is set to 2000 milliseconds (2 seconds).
      ZOOKEEPER_TICK_TIME: 2000

  # Confluent Server (cp-server) includes Kafka and role-based access control
  # (RBAC), self-balancing clusters, and other features. Our interest in this
  # lab is Kafka.
  broker:
    image: confluentinc/cp-server:5.5.1
    hostname: broker
    container_name: broker
    depends_on:
      - zookeeper
    ports:
      - 29092:29092
    environment:
      KAFKA_BROKER_ID: 1
      # The Kafka Broker connects to the cluster and informs ZooKeeper of its
      # presence. This is assuming that ZooKeeper is running on the
      # container/server called "ZooKeeper" and port 2181. Notice that we can
      # refer to the container using its container_name instead of its
      # IP address. Using its IP address can be cumbersome in cases where the
      # container restarts and is assigned a different dynamic IP address.
      KAFKA_ZOOKEEPER_CONNECT: 'zookeeper:2181'
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT, PLAINTEXT_HOST:PLAINTEXT
      # Required for ZooKeeper mode. Describes how the host name that is
      # advertised can be reached by clients. The value is published to
      # ZooKeeper for clients to use.
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://broker:9092,PLAINTEXT_HOST://localhost:29092
      # This is set to `1` when you are running with a single-node
      # Kafka cluster. If you have three or more nodes, you can use the
      # default.
      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: 0
      CONFLUENT_METRICS_ENABLE: 'false'
      KAFKA_CONFLUENT_LICENSE_TOPIC_REPLICATION_FACTOR: 1

  # The schema registry provides a centralized repository for managing the
  # schemas used by producers and consumers.
  # Its primary purpose is to ensure that the data exchanged between different
  # components of a Kafka system are well-structured, consistent, and follow
  # a specified schema
  schema-registry:
    image: confluentinc/cp-schema-registry:5.5.1
    hostname: schema-registry
    container_name: schema-registry
    depends_on:
      - zookeeper
      - broker
    ports:
      - 8081:8081
    environment:
      SCHEMA_REGISTRY_HOST_NAME: schema-registry
      SCHEMA_REGISTRY_LISTENERS: 'http://0.0.0.0:8081'
      SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: 'PLAINTEXT://broker:9092'

# Required to install all the source and sink connectors as well as the JDBC
# driver required by the sink connector. This takes several minutes to start
# depending on the hardware resources available partly because of the
# installation of the connectors and drivers as the container is created (at
# runtime). Be patient and wait for the message "Kafka Connect started" in the logs.
  kafka-connect:
    image: confluentinc/cp-kafka-connect-base:6.2.0
    hostname: kafka-connect
    container_name: kafka-connect
    depends_on:
      - broker
      - schema-registry
    ports:
      - 8083:8083
    environment:
      CONNECT_BOOTSTRAP_SERVERS: "broker:9092"
      CONNECT_REST_PORT: 8083
      CONNECT_GROUP_ID: kafka-connect
      CONNECT_CONFIG_STORAGE_TOPIC: _connect-configs
      CONNECT_OFFSET_STORAGE_TOPIC: _connect-offsets
      CONNECT_STATUS_STORAGE_TOPIC: _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_REST_ADVERTISED_HOST_NAME: "kafka-connect"
      CONNECT_LOG4J_APPENDER_STDOUT_LAYOUT_CONVERSIONPATTERN: "[%d] %p %X{connector.context}%m (%c:%L)%n"
      CONNECT_CONFIG_STORAGE_REPLICATION_FACTOR: "1"
      CONNECT_OFFSET_STORAGE_REPLICATION_FACTOR: "1"
      CONNECT_STATUS_STORAGE_REPLICATION_FACTOR: "1"
    #  *Identifying the correct location of the JDBC drivers is important*
      CONNECT_PLUGIN_PATH: /usr/share/java,/usr/share/confluent-hub-components,/data/connect-jars

    # If you want to make the installed connectors available offline, then
    # spin up the stack once and then run : 
    #   docker cp kafka-connect:/usr/share/confluent-hub-components ./kafka/CONNECT_PLUGIN_PATH

    # volumes:
      # - ./kafka/data:/data
      # - ./kafka/CONNECT_PLUGIN_PATH:/usr/share/java
      # - ./kafka/CONNECT_PLUGIN_PATH:/usr/share/confluent-hub-components
      # - ./kafka/CONNECT_PLUGIN_PATH:/usr/share/confluent-hub-components/confluentinc-kafka-connect-jdbc/lib
      # - ./kafka/CONNECT_PLUGIN_PATH:/data/connect-jars
      # - ./kafka/CONNECT_PLUGIN_PATH:/share/java/kafka-connect-jdbc
      
    command:
      - bash
      - -c
      - |
        echo "Installing Connectors"
        pwd
        # The commands used are documented here: https://www.confluent.io/hub/

        echo "debezium-connector-mysql:1.7.0"
        # confluent-hub install --no-prompt debezium/debezium-connector-mysql:1.7.0
        echo "debezium-connector-mysql:2.2.1"
        confluent-hub install --no-prompt debezium/debezium-connector-mysql:2.2.1
        echo "kafka-connect-jdbc:10.7.4"
        confluent-hub install --no-prompt confluentinc/kafka-connect-jdbc:10.7.4
        echo "clickhouse-kafka-connect:v1.0.5"
        confluent-hub install --no-prompt clickhouse/clickhouse-kafka-connect:v1.0.5
        
        #
        echo "Installing JDBC Drivers"
        cd /usr/share/confluent-hub-components/confluentinc-kafka-connect-jdbc/lib
        echo "Location of JDBC Driver isntallation is:"
        pwd

        # Additional drivers are available here on the Maven repository: https://mvnrepository.com/open-source/jdbc-drivers
        echo "pinot-jdbc-client-1.0.0.jar"
        curl https://repo1.maven.org/maven2/org/apache/pinot/pinot-jdbc-client/1.0.0/pinot-jdbc-client-1.0.0.jar -o pinot-jdbc-client-1.0.0.jar
        echo "clickhouse-jdbc-0.5.0.jar"
        curl https://repo1.maven.org/maven2/com/clickhouse/clickhouse-jdbc/0.5.0/clickhouse-jdbc-0.5.0.jar -o clickhouse-jdbc-0.5.0.jar
        echo "druid-1.2.20.jar"
        curl https://repo1.maven.org/maven2/com/alibaba/druid/1.2.20/druid-1.2.20.jar -o druid-1.2.20.jar
        echo "postgresql-42.6.0.jar"
        curl https://repo1.maven.org/maven2/org/postgresql/postgresql/42.6.0/postgresql-42.6.0.jar -o postgresql-42.6.0.jar
        echo "jdbc11-23.3.0.23.09.jar"
        curl https://repo1.maven.org/maven2/com/oracle/database/jdbc/ojdbc11/23.3.0.23.09/ojdbc11-23.3.0.23.09.jar -o jdbc11-23.3.0.23.09.jar
        
        rm /usr/share/java/cp-base-new/slf4j-log4j12-*.jar
        
        cd /home/appuser
        #

        #
        echo "Launching Kafka Connect Worker"
        /etc/confluent/docker/run &
        #

        # Let the worker run as long as the server is up
        sleep infinity

  # Required for a GUI to view the messages in each topic and in each partition
  # of the topic
  kafdrop:
    image: obsidiandynamics/kafdrop:4.0.2-SNAPSHOT
    container_name: kafdrop
    depends_on:
      - broker
    restart: "no"
    ports:
      - 9000:9000
    environment:
      KAFKA_BROKERCONNECT: "broker:9092"
      # JVM_OPTS: "-Xms16M -Xmx48M -Xss180K -XX:-TieredCompilation -XX:+UseStringDeduplication -noverify"
      CMD_ARGS: "--message.format=AVRO --schemaregistry.connect=http://schema-registry:8081"

  # Required to provide persistent storage of Kafka topics before being loaded
  # into the destination. Used to demonstrate the support for real-time analytics.
  ksqldb-server:
    image: confluentinc/ksqldb-server:0.29.0
    hostname: ksqldb-server
    container_name: ksqldb-server
    depends_on:
      - broker
      - schema-registry
    ports:
      - 8088:8088
    environment:
      KSQL_CONFIG_DIR: "/etc/ksqldb"
      KSQL_LOG4J_OPTS: "-Dlog4j.configuration=file:/etc/ksqldb/log4j.properties"
      KSQL_BOOTSTRAP_SERVERS: "broker:9092"
      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"

  # Required to provide a CLI to access ksqlDB server.
  ksqldb-cli:
    image: confluentinc/ksqldb-cli:0.29.0
    hostname: ksqldb-cli
    container_name: ksqldb-cli
    depends_on:
      - broker
      - ksqldb-server
    entrypoint: /bin/sh
    environment:
      KSQL_CONFIG_DIR: "/etc/ksqldb"
    tty: true

# This can also be a distributed database as shown in the previous lab.
# It has been implemented as a standalone database (only 1 container)
# instead of a distributed database like MySQL NDB/InnoDB Cluster (at least 5
# containers) so that it can be supported by the hardware resources available
# on a “normal” student laptop).

# Be patient and wait for the server to display "ready for connections" in the
# logs. There should be a total of 4 "ready for connections" messages in the
# logs.

  mysql:
    image: mysql:8.0.35
    hostname: mysql
    container_name: mysql
    ports:
      - 33006:3306
    environment:
      MYSQL_ROOT_PASSWORD: 5trathm0re
    volumes:
      - ./mysql/sample-data:/docker-entrypoint-initdb.d/
      - ./mysql/var-lib-mysql:/var/lib/mysql

  clickhouse-server:
    image: yandex/clickhouse-server:21.3.20.1
    hostname: clickhouse-server
    container_name: clickhouse-server
    volumes:
      - ./clickhouse/config/config.xml:/etc/clickhouse-server/config.xml
      - ./clickhouse/config/zookeeper-servers.xml:/etc/clickhouse-server/conf.d/zookeeper-servers.xml
      - ./clickhouse/var-lib-clickhouse:/var/lib/clickhouse
    ports:
      - 8123:8123
      - 9002:9002

  clickhouse-client:
    image: yandex/clickhouse-client:21.3.20.1
    hostname: clickhouse-client
    container_name: clickhouse-client
    depends_on:
      - clickhouse-server
    entrypoint:
      - /bin/sleep
    command:
      - infinity