datawave/docker/docker-compose.yml

volumes:
  hdfs_name:
  hdfs_data:
  zookeeper_data:
  datawave_accumulo_ext:

services:
  datawave-extlib:
    profiles: [datawave-stack]
    image: nationalsecurityagency/datawave/ingest-compose:${VERSION:-latest}
    user: root
    entrypoint: ["/bin/bash", "-c"]
    command:
      - |
        set -e
        target=/opt/accumulo/lib/ext
        rm -f "$${target}/"*.jar
        cp /opt/datawave-ingest/current/accumulo-warehouse/lib/*.jar "$${target}/"
        cp /opt/datawave-ingest/current/accumulo-warehouse/lib/ext/*.jar "$${target}/"
        cp /opt/datawave-ingest/current/lib/accumulo-access-core-*.jar "$${target}/"
        cp /opt/datawave-ingest/current/lib/jaxb-api-*.jar "$${target}/"
        chmod 0644 "$${target}/"*.jar
    volumes:
      - datawave_accumulo_ext:/opt/accumulo/lib/ext
    networks: [demo]

  hdfs-nn:
    profiles: [datawave-stack]
    image: &stack-image ghcr.io/nationalsecurityagency/datawave-stack-accumulo:${DATAWAVE_STACK_ACCUMULO_VERSION:-2.1.6}
    user: hdfs
    entrypoint: ["/bin/bash", "/stack/start-hadoop.sh"]
    command: [namenode]
    environment:
      - HADOOP_CONF_DIR=/stack
    ports:
      - "9000:9000"
      - "9870:9870"
    volumes:
      - ./stack:/stack:ro
      - hdfs_name:/var/lib/hadoop-hdfs
    networks: [demo]
    healthcheck:
      test: ["CMD-SHELL", "hdfs dfsadmin -safemode get | grep -q OFF"]
      interval: 2s
      timeout: 5s
      start_period: 15s
      retries: 30

  hdfs-dn:
    profiles: [datawave-stack]
    image: *stack-image
    user: hdfs
    entrypoint: ["/bin/bash", "/stack/start-hadoop.sh"]
    command: [datanode]
    environment:
      - HADOOP_CONF_DIR=/stack
    ports:
      - "9864:9864"
    volumes:
      - ./stack:/stack:ro
      - hdfs_data:/var/lib/hadoop-hdfs
    networks: [demo]
    depends_on:
      hdfs-nn:
        condition: service_healthy
    healthcheck:
      test: ["CMD-SHELL", "hdfs dfsadmin -report | grep -q 'Live datanodes (1)' "]
      interval: 2s
      timeout: 5s
      retries: 30

  yarn-rm:
    profiles: [datawave-stack]
    image: *stack-image
    user: hdfs
    entrypoint: ["/bin/bash", "/stack/start-hadoop.sh"]
    command: [resourcemanager]
    environment:
      - HADOOP_CONF_DIR=/stack
      - YARN_CONF_DIR=/stack
    ports:
      - "8032:8032"
      - "8088:8088"
    volumes:
      - ./stack:/stack:ro
    networks: [demo]
    depends_on:
      hdfs-dn:
        condition: service_healthy
    healthcheck:
      test: ["CMD-SHELL", "bash -c '</dev/tcp/localhost/8032'"]
      interval: 2s
      timeout: 3s
      retries: 30

  yarn-nm:
    profiles: [datawave-stack]
    image: *stack-image
    user: hdfs
    entrypoint: ["/bin/bash", "/stack/start-hadoop.sh"]
    command: [nodemanager]
    environment:
      - HADOOP_CONF_DIR=/stack
      - YARN_CONF_DIR=/stack
    ports:
      - "8042:8042"
    volumes:
      - ./stack:/stack:ro
    networks: [demo]
    depends_on:
      yarn-rm:
        condition: service_healthy
    healthcheck:
      test: ["CMD-SHELL", "bash -c '</dev/tcp/localhost/8042'"]
      interval: 2s
      timeout: 3s
      retries: 30

  zookeeper:
    profiles: [datawave-stack]
    image: *stack-image
    user: zookeeper
    entrypoint: ["/usr/lib/zookeeper/bin/zkServer.sh"]
    command: ["--config", "/etc/zookeeper/conf.dist", "start-foreground"]
    environment:
      - ZOOBINDIR=/usr/lib/zookeeper/bin
      - ZOO_LOG_DIR=/var/log/zookeeper
    ports:
      - "2181:2181"
    volumes:
      - zookeeper_data:/var/lib/zookeeper
    networks: [demo]
    healthcheck:
      test: ["CMD-SHELL", "echo ruok | timeout 2 bash -c 'cat > /dev/tcp/localhost/2181' "]
      interval: 2s
      timeout: 3s
      start_period: 10s
      retries: 30

  accumulo-manager:
    profiles: [datawave-stack]
    image: *stack-image
    command: [manager]
    environment:
      - ACCUMULO_INSTANCE_NAME=my-instance-01
      - ACCUMULO_ROOT_PASSWORD=secret
      - HADOOP_CONF_DIR=/stack
    volumes:
      - ./stack:/stack:ro
      - datawave_accumulo_ext:/opt/accumulo/lib/ext:ro
      - ./stack/accumulo.properties:/opt/accumulo/conf/accumulo.properties:ro
      - ./stack/accumulo-client.properties:/opt/accumulo/conf/accumulo-client.properties:ro
      - ./stack/accumulo-env.sh:/opt/accumulo/conf/accumulo-env.sh:ro
    networks: [demo]
    depends_on:
      datawave-extlib:
        condition: service_completed_successfully
      hdfs-dn:
        condition: service_healthy
      zookeeper:
        condition: service_healthy
    healthcheck:
      test: ["CMD-SHELL", "bash -c '</dev/tcp/localhost/9999'"]
      interval: 3s
      timeout: 5s
      start_period: 20s
      retries: 40

  accumulo-tserver:
    profiles: [datawave-stack]
    image: *stack-image
    command: [tserver]
    environment:
      - HADOOP_CONF_DIR=/stack
    volumes:
      - ./stack:/stack:ro
      - datawave_accumulo_ext:/opt/accumulo/lib/ext:ro
      - ./stack/accumulo.properties:/opt/accumulo/conf/accumulo.properties:ro
      - ./stack/accumulo-client.properties:/opt/accumulo/conf/accumulo-client.properties:ro
      - ./stack/accumulo-env.sh:/opt/accumulo/conf/accumulo-env.sh:ro
    networks: [demo]
    depends_on:
      accumulo-manager:
        condition: service_healthy
    healthcheck:
      test: ["CMD-SHELL", "bash -c '</dev/tcp/localhost/9997'"]
      interval: 3s
      timeout: 3s
      retries: 30

  accumulo-gc:
    profiles: [datawave-stack]
    image: *stack-image
    command: [gc]
    environment:
      - HADOOP_CONF_DIR=/stack
    volumes:
      - ./stack:/stack:ro
      - datawave_accumulo_ext:/opt/accumulo/lib/ext:ro
      - ./stack/accumulo.properties:/opt/accumulo/conf/accumulo.properties:ro
      - ./stack/accumulo-client.properties:/opt/accumulo/conf/accumulo-client.properties:ro
      - ./stack/accumulo-env.sh:/opt/accumulo/conf/accumulo-env.sh:ro
    networks: [demo]
    depends_on:
      accumulo-manager:
        condition: service_healthy

  accumulo-monitor:
    profiles: [datawave-stack]
    image: *stack-image
    command: [monitor]
    environment:
      - HADOOP_CONF_DIR=/stack
    ports:
      - "9995:9995"
    volumes:
      - ./stack:/stack:ro
      - datawave_accumulo_ext:/opt/accumulo/lib/ext:ro
      - ./stack/accumulo.properties:/opt/accumulo/conf/accumulo.properties:ro
      - ./stack/accumulo-client.properties:/opt/accumulo/conf/accumulo-client.properties:ro
      - ./stack/accumulo-env.sh:/opt/accumulo/conf/accumulo-env.sh:ro
    networks: [demo]
    depends_on:
      accumulo-manager:
        condition: service_healthy

  ingest:
    profiles: [datawave-stack]
    image: nationalsecurityagency/datawave/ingest-compose:${VERSION:-latest}
    user: datawave
    entrypoint: ["/bin/bash", "/stack/initialize-datawave.sh"]
    environment:
      - HADOOP_CONF_DIR=/stack
    volumes:
      - ./stack:/stack:ro
      - ./stack/accumulo.properties:/opt/accumulo/conf/accumulo.properties:ro
      - ./stack/accumulo-client.properties:/opt/accumulo/conf/accumulo-client.properties:ro
      - ./stack/accumulo-env.sh:/opt/accumulo/conf/accumulo-env.sh:ro
      - ./stack/ingest-passwd.sh:/opt/datawave-ingest/ingest-passwd.sh:ro
      - ../warehouse/ingest-wikipedia/src/test/resources/input:/opt/datawave-test-data/wikipedia:ro
      - ../warehouse/ingest-annotation/src/test/resources/input:/opt/datawave-test-data/annotation:ro
      - ../warehouse/ingest-json/src/test/resources/input:/opt/datawave-test-data/json:ro
      - ../warehouse/ingest-csv/src/test/resources/input:/opt/datawave-test-data/csv:ro
    networks: [demo]
    depends_on:
      accumulo-tserver:
        condition: service_healthy
      yarn-nm:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "test", "-f", "/tmp/datawave-ready"]
      interval: 5s
      timeout: 2s
      start_period: 30s
      retries: 120

  webservice:
    profiles: [datawave-stack]
    image: nationalsecurityagency/datawave/webservice-compose:${VERSION:-latest}
    environment:
      - ACCUMULO_PASSWORD=secret
      - KEYSTORE=/opt/jboss/wildfly/standalone/configuration/certificates/testServer.p12
      - KEYSTORE_TYPE=PKCS12
      - KEYSTORE_PASSWORD=ChangeIt
      - TRUSTSTORE=/opt/jboss/wildfly/standalone/configuration/certificates/ca.jks
      - TRUSTSTORE_TYPE=JKS
      - TRUSTSTORE_PASSWORD=ChangeIt
    ports:
      - "9443:8443" # web server
      - "9990:9990" # wildfly admin
    volumes:
      - ./stack:/stack:ro
      - ./logs:/logs
    networks: [demo]
    depends_on:
      ingest:
        condition: service_healthy
      authorization:
        condition: service_healthy
    healthcheck:
      test: ["CMD-SHELL", "bash -c '</dev/tcp/localhost/8443'"]
      interval: 5s
      timeout: 3s
      start_period: 60s
      retries: 60

  consul:
    image: docker.io/hashicorp/consul:1.15.4
    hostname: localhost
    environment:
      - 'CONSUL_LOCAL_CONFIG={"log_level": "ERROR", "datacenter": "demo_dc", "disable_update_check": true, "enable_agent_tls_for_checks": true, "addresses": {"https": "0.0.0.0"}, "ports": {"https": 8501, "grpc_tls": 8503}, "tls": {"defaults": {"key_file": "/etc/pki/testServer.key", "cert_file": "/etc/pki/testServer.crt", "ca_file": "/etc/pki/testCA.pem", "verify_outgoing": true}, "internal_rpc": {"verify_server_hostname": false}}}'
      - CONSUL_BIND_INTERFACE=eth0
    # defined as host:container
    ports:
      - "8400"
      - "8500:8500"
      - "8501:8501"
      - "8503:8503"
      - "53"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
    networks:
      - demo

  rabbitmq:
    image: docker.io/rabbitmq:3.12.4
    volumes:
      - ${RABBITMQ_CONFIG_DIR:-./rabbitmq-config}:/etc/rabbitmq
      - ./logs:/logs
    environment:
      - TCP_PORTS=15672, 5672
      - RABBITMQ_ERLANG_COOKIE="mycookie"
    ports:
      - "5672:5672"
      - "15672:15672"
    networks:
      - demo
    healthcheck:
      test: ["CMD", "rabbitmq-diagnostics", "-q", "ping"]
      interval: 5s
      timeout: 5s
      start_period: 30s
      retries: 20
    depends_on:
      consul:
        condition: service_started

  qr-rabbitmq:
    image: docker.io/rabbitmq:3.12.4
    volumes:
      - ${RABBITMQ_CONFIG_DIR:-./rabbitmq-config}:/etc/rabbitmq
      - ./logs:/logs
    environment:
      - TCP_PORTS=25672, 15672, 5672
      - RABBITMQ_ERLANG_COOKIE="mycookie"
    ports:
      - "5673:5672"
      - "15673:15672"
      - "25673:25672"
    networks:
      - demo
    depends_on:
      consul:
        condition: service_started

  # When auto.create.topics.enable is true, this causes deleted topics to be recreated at random.  So, leave it disabled.
  kafka:
    profiles:
      - kafka
    image: docker.io/bitnami/kafka:3.2
    ports:
      - "9094:9094"
    networks:
      - demo
    environment:
      - KAFKA_CFG_NODE_ID=1
      - KAFKA_CFG_PROCESS_ROLES=controller,broker
      - ALLOW_PLAINTEXT_LISTENER=yes
      - KAFKA_CFG_LISTENER_SECURITY_PROTOCOL_MAP=CLIENT:PLAINTEXT,CONTROLLER:PLAINTEXT,EXTERNAL:PLAINTEXT
      - KAFKA_CFG_LISTENERS=CLIENT://:9092,CONTROLLER://:9093,EXTERNAL://:9094
      - KAFKA_CFG_ADVERTISED_LISTENERS=CLIENT://kafka:9092,EXTERNAL://${DW_HOSTNAME}:9094
      - KAFKA_CFG_CONTROLLER_QUORUM_VOTERS=1@kafka:9093
      - KAFKA_CFG_CONTROLLER_LISTENER_NAMES=CONTROLLER
      - KAFKA_INTER_BROKER_LISTENER_NAME=CLIENT
      - KAFKA_CFG_AUTO_CREATE_TOPICS_ENABLE=false
      - KAFKA_CFG_DELETE_TOPICS_ENABLE=true

  kafdrop:
    profiles:
      - kafka
    image: docker.io/obsidiandynamics/kafdrop
    ports:
      - "8999:9000"
    networks:
      - demo
    environment:
      - "KAFKA_BROKERCONNECT=${DW_HOSTNAME}:9094"
    # This mapping is required to enable kafdrop to communicate with
    # the external, host-bound port for kafka
    extra_hosts:
      - "${DW_HOSTNAME}:${DW_HOST_IP}"
      - "${DW_HOST_FQDN}:${DW_HOST_IP}"
    depends_on:
      kafka:
        condition: service_started

  configuration:
    entrypoint: [ "java","-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5009","-jar","app.jar" ]
    image: nationalsecurityagency/datawave/config-service:${VERSION:-latest}
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,native,open_actuator
      - --spring.cloud.consul.host=consul
      - --spring.cloud.config.server.native.searchLocations=file:///microservice-config
    environment:
      - 'KEYSTORE_LOCATION=file:///etc/pki/testServer.p12'
      - KEYSTORE_PASSWORD=ChangeIt
      - KEY_ALIAS=certificate
    ports:
      - "8888:8888"
      - "5009:5009"
    volumes:
      - ${CONFIG_DIR:-./config}:/microservice-config:ro
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8888/configserver/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 45s
      retries: 3
    depends_on:
      rabbitmq:
        condition: service_started

  cache:
    image: nationalsecurityagency/datawave/hazelcast-service:${VERSION:-latest}
    scale: 1
    command:
      - --spring.profiles.active=consul,compose,remoteauth
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    ports:
      - "5701-5703"
      - "8080"
      - "8843:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/cache/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 45s
      retries: 3
    depends_on:
      configuration:
        condition: service_healthy

  annotation-cache:
    profiles:
      - annotation-cache
    image: nationalsecurityagency/datawave/annotation-cache-service:${VERSION:-latest}
    scale: 2
    command:
      - --spring.profiles.active=consul,compose
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    ports:
      - "5701"
      - "8080"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/annotation-cache/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 45s
      retries: 3
    depends_on:
      configuration:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy

  annotation:
    entrypoint: [ "java","-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5959","-jar","app.jar" ]
    profiles:
      - annotation
    image: nationalsecurityagency/datawave/annotation-service:1.0.0-SNAPSHOT
    scale: 1
    command:
      - --spring.profiles.active=combined,consul,compose,remoteauth,log-disabled
      - --spring.output.ansi.enabled=NEVER
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
      - "BACKEND=${BACKEND:-rabbitmq}"
    ports:
      - "5959:5959"
      - "8748:8748"
      - "8080"
      - "9543:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/annotation/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 45s
      retries: 3
    depends_on:
      configuration:
        condition: service_healthy

  query-cache:
    profiles:
      - querycache
      # To enable an additional Hazelcast cluster, enable the "querycache" profile
      # Set an environment variable: QUERY_CACHE=query-cache. This will force the query and executor service to use a separate "query-cache" Hazelcast cluster.
    image: nationalsecurityagency/datawave/hazelcast-service:${VERSION:-latest}
    scale: 1
    command:
      - --spring.application.name=query-cache
      - --hazelcast.client.cluster-members
      - --spring.profiles.active=consul,compose,remoteauth
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    ports:
      - "5701-5703"
      - "8080"
      - "8844:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/query-cache/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 45s
      retries: 3
    depends_on:
      configuration:
        condition: service_started

  query-rabbitmq:
    profiles:
      - queryrabbit
      # To enable an additional rabbit cluster, enable the "queryrabbit" profile
      # Set an environment variable: USE_DEDICATED_INSTANCE=true. This will force the query and executor service to use a separate "query-rabbitmq" rabbit cluster.
    image: docker.io/rabbitmq:3.12.4
    volumes:
      - ${RABBITMQ_CONFIG_DIR:-./rabbitmq-query-config}:/etc/rabbitmq
      - ./logs:/logs
    environment:
      - TCP_PORTS=15672,5672
      - RABBITMQ_ERLANG_COOKIE="someothercookie"
    ports:
      - "15673:15672"
    networks:
      - demo
    depends_on:
      consul:
        condition: service_started

  # When auto.create.topics.enable is true, this causes deleted topics to be recreated at random.  So, leave it disabled.
  query-kafka:
    profiles:
      - querykafka
    # To enable an additional rabbit cluster, enable the "querykafka" profile
    # Set an environment variable: USE_DEDICATED_INSTANCE=true. This will force the query and executor service to use a separate "query-kafka" kafka cluster.
    image: docker.io/bitnami/kafka:3.2
    ports:
      - "9095:9095"
    networks:
      - demo
    environment:
      - KAFKA_CFG_NODE_ID=1
      - KAFKA_CFG_PROCESS_ROLES=controller,broker
      - ALLOW_PLAINTEXT_LISTENER=yes
      - KAFKA_CFG_LISTENER_SECURITY_PROTOCOL_MAP=CLIENT:PLAINTEXT,CONTROLLER:PLAINTEXT,EXTERNAL:PLAINTEXT
      - KAFKA_CFG_LISTENERS=CLIENT://:9092,CONTROLLER://:9093,EXTERNAL://:9095
      - KAFKA_CFG_ADVERTISED_LISTENERS=CLIENT://query-kafka:9092,EXTERNAL://${DW_HOSTNAME}:9095
      - KAFKA_CFG_CONTROLLER_QUORUM_VOTERS=1@query-kafka:9093
      - KAFKA_CFG_CONTROLLER_LISTENER_NAMES=CONTROLLER
      - KAFKA_INTER_BROKER_LISTENER_NAME=CLIENT
      - KAFKA_CFG_AUTO_CREATE_TOPICS_ENABLE=false
      - KAFKA_CFG_DELETE_TOPICS_ENABLE=true

  authorization:
    entrypoint: [ "java","-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5008","-jar","app.jar" ]
    image: nationalsecurityagency/datawave/authorization-service:${VERSION:-latest}
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,mock,compose,federation
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    ports:
      - "8080"
      - "8343:8443"
      - "5008:5008"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/authorization/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 20s
      retries: 3
    depends_on:
      cache:
        condition: service_healthy

  accumulo:
    profiles:
      - accumulo
      - full
    image: nationalsecurityagency/datawave/accumulo-service:${VERSION:-latest}
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - AUDIT_SERVER_URL=http://audit:8080/audit
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
    # This mapping is required to enable the metrics service to communicate
    # with host-deployed services like hadoop, zookeeper, and accumulo.
    # These values are set locally in .env via bootstrap.sh
    extra_hosts:
      - "${DW_HOSTNAME}:${DW_HOST_IP}"
      - "${DW_HOST_FQDN}:${DW_HOST_IP}"
    ports:
      - "9143:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/accumulo/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 45s
      retries: 3
    depends_on:
      authorization:
        condition: service_healthy

  audit:
    image: nationalsecurityagency/datawave/audit-service:${VERSION:-latest}
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
    # This mapping is required to enable the audit service to communicate
    # with host-deployed services like hadoop, zookeeper, and accumulo.
    # These values are set locally in .env via bootstrap.sh
    extra_hosts:
      - "${DW_HOSTNAME}:${DW_HOST_IP}"
      - "${DW_HOST_FQDN}:${DW_HOST_IP}"
    ports:
      - "8080"
      - "9043:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/audit/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 30s
      retries: 3
    depends_on:
      authorization:
        condition: service_healthy

  metrics:
    entrypoint: ["java","-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5007","-jar","app.jar"]
    image: nationalsecurityagency/datawave/query-metric-service
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
    # This mapping is required to enable the metrics service to communicate
    # with host-deployed services like hadoop, zookeeper, and accumulo.
    # These values are set locally in .env via bootstrap.sh
    extra_hosts:
      - "${DW_HOSTNAME}:${DW_HOST_IP}"
      - "${DW_HOST_FQDN}:${DW_HOST_IP}"
    ports:
      - "8180:8080"
      - "8543:8443"
      - "5007:5007"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/querymetric/mgmt/health
      interval: 5s
      timeout: 1s
      start_period: 40s
      retries: 10
    depends_on:
      authorization:
        condition: service_healthy
      ingest:
        condition: service_healthy

  dictionary:
    profiles:
      - dictionary
      - full
    image: nationalsecurityagency/datawave/dictionary-service
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
    # This mapping is required to enable the metrics service to communicate
    # with host-deployed services like hadoop, zookeeper, and accumulo.
    # These values are set locally in .env via bootstrap.sh
    extra_hosts:
      - "${DW_HOSTNAME}:${DW_HOST_IP}"
      - "${DW_HOST_FQDN}:${DW_HOST_IP}"
    ports:
      - "8280:8080"
      - "8643:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/dictionary/mgmt/health
    depends_on:
      authorization:
        condition: service_healthy

  file-provider:
    profiles:
      - file-provider
      - full
    image: nationalsecurityagency/datawave/file-provider-service
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    ports:
      - "8580:8080"
      - "8943:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    depends_on:
      authorization:
        condition: service_healthy

  # If you want to test cached results, enable the cachedresults profile
  mysql:
    profiles:
      - cachedresults
    image: docker.io/mysql:8.0.32
    environment:
      - MYSQL_RANDOM_ROOT_PASSWORD=true
      - MYSQL_DATABASE=cachedresults
      - MYSQL_USER=datawave
      - MYSQL_PASSWORD=secret
    networks:
      - demo
    healthcheck:
      test: ["CMD", "mysqladmin", "ping", "-h", "localhost"]
      timeout: 20s
      retries: 10

  # If you want to test cached results, set the CACHED_RESULTS environment variable to 'true'
  query:
    entrypoint: ["java","-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5005","-jar","app.jar"]
    image: nationalsecurityagency/datawave/query-service
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth,querymessaging,metricssource,query,mrquery,cachedresults,federation
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - AUDIT_SERVER_URL=http://audit:8080/audit
      - HADOOP_HOST=${DW_HADOOP_HOST}
      - YARN_HOST=${DW_YARN_HOST}
      - HADOOP_CONF_DIR=/etc/hadoop/conf
      - "BACKEND=${BACKEND:-rabbitmq}"
      - CACHED_RESULTS=${CACHED_RESULTS:-false}
      - QUERY_CACHE=${QUERY_CACHE:-cache}
      - USE_DEDICATED_INSTANCE=${USE_DEDICATED_INSTANCE:-false}
    ports:
      - "8080:8080"
      - "8443:8443"
      - "5005:5005"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
      - ${HADOOP_CONF_SOURCE:-./stack}:/etc/hadoop/conf:ro
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/query/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 30s
      retries: 3
    depends_on:
      audit:
        condition: service_healthy
      authorization:
        condition: service_healthy
      metrics:
        condition: service_healthy
      executor-pool1:
        condition: service_started

  mapreduce-query:
    profiles:
      - full
    entrypoint: ["java","-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5005","-jar","app.jar"]
    image: nationalsecurityagency/datawave/mapreduce-query-service
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth,query,mrquery,federation
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
      - HADOOP_HOST=${DW_HADOOP_HOST}
      - YARN_HOST=${DW_YARN_HOST}
      - HADOOP_CONF_DIR=/etc/hadoop/conf
    ports:
      - "50005:5005"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
      - ${HADOOP_CONF_SOURCE:-./stack}:/etc/hadoop/conf:ro
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/mrquery/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 30s
      retries: 3
    depends_on:
      audit:
        condition: service_healthy
      authorization:
        condition: service_healthy
      metrics:
        condition: service_healthy
      executor-pool1:
        condition: service_started

  executor-pool1:
    entrypoint: ["java","-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5006","-jar","app.jar"]
    image: nationalsecurityagency/datawave/query-executor-service
    command:
      - --spring.application.name=executor-pool1
      - --spring.cloud.config.name=executor
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth,querymessaging,metricssource,query,pool1,federation
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
      - HADOOP_HOST=${DW_HADOOP_HOST}
      - BACKEND=${BACKEND:-rabbitmq}
      - HADOOP_CONF_DIR=/etc/hadoop/conf
      - QUERY_CACHE=${QUERY_CACHE:-cache}
      - USE_DEDICATED_INSTANCE=${USE_DEDICATED_INSTANCE:-false}
    # This mapping is required to enable the metrics service to communicate
    # with host-deployed services like hadoop, zookeeper, and accumulo.
    # These values are set locally in .env via bootstrap.sh
    extra_hosts:
      - "${DW_HOSTNAME}:${DW_HOST_IP}"
      - "${DW_HOST_FQDN}:${DW_HOST_IP}"
    ports:
      - "8380:8080"
      - "8743:8443"
      - "5006:5006"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs/pool1:/logs
      - ${HADOOP_CONF_SOURCE:-./stack}:/etc/hadoop/conf:ro
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/executor/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 30s
      retries: 3
    depends_on:
      rabbitmq:
        condition: service_started
      authorization:
        condition: service_healthy
      metrics:
        condition: service_healthy

  executor-pool2:
    profiles:
      - pool2
      - full
    image: nationalsecurityagency/datawave/query-executor-service
    command:
      - --spring.application.name=executor-pool2
      - --spring.cloud.config.name=executor
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth,querymessaging,metricssource,query,pool2,federation
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
      - HADOOP_HOST=${DW_HADOOP_HOST}
      - BACKEND=${BACKEND:-rabbitmq}
      - HADOOP_CONF_DIR=/etc/hadoop/conf
      - QUERY_CACHE=${QUERY_CACHE:-cache}
      - USE_DEDICATED_INSTANCE=${USE_DEDICATED_INSTANCE:-false}
    # This mapping is required to enable the metrics service to communicate
    # with host-deployed services like hadoop, zookeeper, and accumulo.
    # These values are set locally in .env via bootstrap.sh
    extra_hosts:
      - "${DW_HOSTNAME}:${DW_HOST_IP}"
      - "${DW_HOST_FQDN}:${DW_HOST_IP}"
    ports:
      - "8480:8080"
      - "8243:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs/pool2:/logs
      - ${HADOOP_CONF_SOURCE:-./stack}:/etc/hadoop/conf:ro
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/executor/mgmt/health
      interval: 10s
      timeout: 1s
      start_period: 30s
      retries: 3
    depends_on:
      rabbitmq:
        condition: service_started
      authorization:
        condition: service_healthy
      metrics:
        condition: service_healthy

  modification:
    entrypoint: ["java","-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5010","-jar","app.jar"]
    profiles:
      - modification
      - full
    image: nationalsecurityagency/datawave/modification-service
    command:
      - --spring.output.ansi.enabled=ALWAYS
      - --spring.profiles.active=consul,compose,remoteauth,query
      - --spring.cloud.consul.host=consul
      - --spring.cloud.consul.discovery.instance-id=$${spring.application.name}:$${random.value}
    environment:
      - ZOOKEEPER_HOST=${DW_ZOOKEEPER_HOST}
    # This mapping is required to enable the metrics service to communicate
    # with host-deployed services like hadoop, zookeeper, and accumulo.
    # These values are set locally in .env via bootstrap.sh
    extra_hosts:
      - "${DW_HOSTNAME}:${DW_HOST_IP}"
      - "${DW_HOST_FQDN}:${DW_HOST_IP}"
    ports:
      - "8680:8080"
      - "9343:8443"
      - "5010:5010"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
      - ./logs:/logs
    networks:
      - demo
    healthcheck:
      test: curl -f http://localhost:8080/dictionary/mgmt/health
    depends_on:
      authorization:
        condition: service_healthy

  # If you use the management center, you can connect to the hazelcast cache as follows:
  # In your browser connect to https://localhost:9243/
  # Enable 'dev' mode
  # Click 'Add Cluster Config'
  # Enter the following for the cache service:
  #  - Cluster Name: cache
  #  - Cluster Config: Enabled
  #  - Member Addresses: cache
  # Enter the following for the query metric service:
  #  - Cluster Name: metrics
  #  - Cluster Config: Enabled
  #  - Member Addresses: metrics
  # Use the console to view the cache contents
  #  - Select the 'cache' cluster
  #  - Select 'Console' under the 'CLUSTER' navigation entry
  #  - Run the following commands to list all entries in the 'datawaveUsers' map:
  #    - ns datawaveUsers
  #    - m.entries
  management-center:
    profiles:
      - management
      - full
    image: docker.io/hazelcast/management-center:5.1.2
    environment:
      - |-
        JAVA_OPTS=
        -Dhazelcast.mc.healthCheck.enable=true
        -Dhazelcast.mc.tls.enabled=true
        -Dhazelcast.mc.tls.keyStore=/etc/pki/testServer.p12
        -Dhazelcast.mc.tls.keyStorePassword=ChangeIt
        -Dhazelcast.mc.tls.trustStore=/etc/pki/testCA.p12
        -Dhazelcast.mc.tls.trustStorePassword=ChangeIt
    ports:
      - "8081"
      - "9243:8443"
    volumes:
      - ${PKI_DIR:-./pki}:/etc/pki:ro
    networks:
      - demo
    healthcheck:
      test: wget -q http://localhost:8081/health -O /dev/null || exit 1
    depends_on:
      cache:
        condition: service_healthy

networks:
  demo: