docker-compose.yml

version: '3.8'

services:
  zookeeper:
    container_name: zookeeper
    image: zookeeper:3.5.8
    environment:
      ZOO_MY_ID: 1
      JVMFLAGS: "-Xms64m -Xmx128m"
      ZOO_4LW_COMMANDS_WHITELIST: "srvr,ruok"
    volumes:
      - storage_zookeeper_datalog:/datalog
      - storage_zookeeper_data:/data
    healthcheck:
      test: ["CMD-SHELL", 'echo "ruok" | nc -w 2 -q 2 localhost 2181 | grep imok']
      interval: 5s
      retries: 5

  kafka:
    container_name: kafka
    # It is used for kafka logs.dir - can't be randomly changed
    hostname: kafka
    image: wurstmeister/kafka:2.13-2.8.1
    ports:
      - "3032:3032"
    environment:
      HOSTNAME_COMMAND: "docker info | grep ^Name: | cut -d' ' -f 2"
      KAFKA_LISTENERS: INTERNAL://0.0.0.0:9092,EXTERNAL://0.0.0.0:3032
      KAFKA_ADVERTISED_LISTENERS: INTERNAL://kafka:9092,EXTERNAL://localhost:3032
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: INTERNAL:PLAINTEXT,EXTERNAL:PLAINTEXT
      KAFKA_INTER_BROKER_LISTENER_NAME: INTERNAL
      KAFKA_ZOOKEEPER_CONNECT: zookeeper:2181
      KAFKA_CREATE_TOPICS: "tweets:1:1"
      KAFKA_BROKER_ID: 1
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_HEAP_OPTS: -Xms128m -Xmx512m
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
      - storage_kafka_data:/kafka
    healthcheck:
      test: ["CMD-SHELL", "/opt/kafka/bin/kafka-topics.sh --bootstrap-server localhost:9092 --topic tweets --describe"]
      interval: 10s
      retries: 5
    depends_on:
      - zookeeper

  akhq:
    container_name: akhq
    image: tchiotludo/akhq:0.22.0
    environment:
      AKHQ_CONFIGURATION: |
        akhq:
          security:
            default-group: admin
          connections:
            kafka:
              properties:
                bootstrap.servers: "kafka:9092"
              schema-registry:
                url: "http://schemaregistry:8081"
              connect:
                - name: connect
                  url: "http://connect:8083"
    ports:
      - 8085:8080
    links:
      - kafka
      - schemaregistry
      - connect

  schemaregistry:
    container_name: schemaregistry
    image: confluentinc/cp-schema-registry:7.2.3
    environment:
      SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: kafka:9092
      SCHEMA_REGISTRY_HOST_NAME: schemaregistry
    ports:
      - "3082:8081"
    depends_on:
      - kafka
    healthcheck:
      test: ["CMD-SHELL", "curl localhost:8081/subjects"]
      interval: 20s
      retries: 5

  connect:
    image: ghcr.io/touk/kafka-connect-twitter:7.2.3
    container_name: connect
    depends_on:
      - zookeeper
      - kafka
    ports:
      - 8083:8083
    environment:
      CONNECT_BOOTSTRAP_SERVERS: "kafka:9092"

      CONNECT_LISTENERS: http://0.0.0.0:8083
      CONNECT_GROUP_ID: "connect-cluster"
      CONNECT_PRODUCER_CLIENT_ID: "connect-worker-producer"
      CONNECT_PRODUCER_ENABLE_IDEMPOTENCE: 'true'

      CONNECT_CONFIG_STORAGE_TOPIC: connect-configs
      CONNECT_OFFSET_STORAGE_TOPIC: connect-offsets
      CONNECT_STATUS_STORAGE_TOPIC: connect-statuses

      CONNECT_REPLICATION_FACTOR: 1
      CONNECT_CONFIG_STORAGE_REPLICATION_FACTOR: 1
      CONNECT_OFFSET_STORAGE_REPLICATION_FACTOR: 1
      CONNECT_STATUS_STORAGE_REPLICATION_FACTOR: 1

      CONNECT_KEY_CONVERTER_SCHEMAS_ENABLE: 'true'
      CONNECT_KEY_CONVERTER: 'io.confluent.connect.avro.AvroConverter'
      CONNECT_KEY_CONVERTER_SCHEMA_REGISTRY_URL: 'http://schemaregistry:8081'
      CONNECT_VALUE_CONVERTER_SCHEMAS_ENABLE: 'true'
      CONNECT_VALUE_CONVERTER: 'io.confluent.connect.avro.AvroConverter'
      CONNECT_VALUE_CONVERTER_SCHEMA_REGISTRY_URL: 'http://schemaregistry: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: connect
      CONNECT_PLUGIN_PATH: /usr/share/java,/usr/share/confluent-hub-components,/data/connect-jars

      CONNECT_LOG4J_ROOT_LOGLEVEL: INFO
      CONNECT_LOG4J_LOGGERS: org.reflections=ERROR

      # Reduce Connect memory utilization
      KAFKA_JVM_PERFORMANCE_OPTS: -server -XX:+UseG1GC -XX:GCTimeRatio=1
        -XX:MinHeapFreeRatio=10 -XX:MaxHeapFreeRatio=20
        -XX:MaxGCPauseMillis=10000 -XX:InitiatingHeapOccupancyPercent=35 -XX:+ExplicitGCInvokesConcurrent
        -XX:MaxInlineLevel=15 -Djava.awt.headless=true
    healthcheck:
      test: ["CMD-SHELL", "curl http://localhost:8083"]
      interval: 10s
      retries: 5

  designer:
    container_name: designer
    image: touk/nussknacker:1.6.1
    ports:
      - "3081:8080"
    environment:
      JDK_JAVA_OPTIONS: -Xmx256M
      INFLUXDB_URL: http://influxdb:8086
      KAFKA_ADDRESS: kafka:9092
      SCHEMA_REGISTRY_URL: http://schemaregistry:8081
      DEFAULT_SCENARIO_TYPE: streaming-lite-embedded
      USAGE_REPORTS_FINGERPRINT: twitter-example
    volumes:
      - storage_designer:/opt/nussknacker/storage

  influxdb:
    container_name: influxdb
    hostname: influxdb
    image: influxdb:1.8.10
    ports:
      - "3086:8086"
    environment:
      INFLUXDB_DB: esp
      INFLUXDB_DATA_QUERY_LOG_ENABLED: "false"
      INFLUXDB_HTTP_LOG_ENABLED: "false"
    volumes:
      - storage_influxdb:/var/lib/influxdb

  grafana:
    container_name: grafana
    image: grafana/grafana:8.4.2
    volumes:
      - ./grafana:/etc/grafana/provisioning
      - ./grafana/dashboards:/var/lib/grafana/dashboards
    environment:
      - GF_AUTH_ANONYMOUS_ENABLED=true
      - GF_SERVER_ROOT_URL=%(protocol)s://%(domain)s:/grafana
      - GF_SECURITY_ALLOW_EMBEDDING=true
    depends_on:
      - influxdb

  nginx:
    container_name: nginx
    image: nginx:1.17.6
    ports:
      - "8081:80"
    volumes:
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
    #we restart over 30s to let additional services (grafana etc.) come up
    deploy:
      restart_policy:
        condition: on-failure
        max_attempts: 6

volumes:
  storage_zookeeper_datalog:
    name: storage_zookeeper_datalog
  storage_zookeeper_data:
    name: storage_zookeeper_data
  storage_kafka_data:
    name: storage_kafka_data
  storage_influxdb:
    name: storage_influxdb
  storage_designer:
    name: storage_designer