In production I will have two sites that each has a Kafka cluster and Postgres instance.
I would like to simulate that and create on my Dev machine two Kafka "clusters" each with a single broker and two Postgres instances. Each Kafka "cluster" is going to run a source connector which will copy data to the other site. The docker-compose below has two Postgres instances, but only one Kafka + source connector. What do I need to duplicate/change to create a second Kafka cluster with another source connector?
---
version: '2'
services:
zookeeper:
image: confluentinc/cp-zookeeper:6.0.0
hostname: zookeeper
container_name: zookeeper
ports:
- "2181:2181"
environment:
ZOOKEEPER_CLIENT_PORT: 2181
ZOOKEEPER_TICK_TIME: 2000
networks:
- syncNetwork
broker:
image: confluentinc/cp-kafka:6.0.0
hostname: broker
container_name: broker
depends_on:
- zookeeper
ports:
- "29092:29092"
- "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_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
KAFKA_JMX_PORT: 9101
networks:
- syncNetwork
schema-registry:
image: confluentinc/cp-schema-registry:6.0.0
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'
networks:
- syncNetwork
postgres12x_nms:
image: "postgres:12.4"
container_name: "pg12x_nms"
ports:
- "5430:5432"
environment:
POSTGRES_USER: "postgres"
POSTGRES_PASSWORD: "postgres"
POSTGRES_DB: "n_db"
volumes:
- vpg_nms:/var/lib/postgresql/data_nms
- ./schema_nms.sql:/docker-entrypoint-initdb.d/schema_nms.sql
networks:
- syncNetwork
pgadmin4:
image: dpage/pgadmin4
links:
- postgres12x_nms
networks:
- syncNetwork
postgres12x_mgr:
image: "postgres:12.4"
container_name: "pg12x_mgr"
ports:
- "5431:5432"
environment:
POSTGRES_USER: "postgres"
POSTGRES_PASSWORD: "postgres"
POSTGRES_DB: "n_db"
volumes:
- vpg_mgr:/var/lib/postgresql/data_mgr
- ./schema_mgr.sql:/docker-entrypoint-initdb.d/schema_mgr.sql
networks:
- syncNetwork
connect:
image: confluentinc/cp-kafka-connect
hostname: connect
container_name: 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
CONNECT_INTERNAL_KEY_CONVERTER: "org.apache.kafka.connect.json.JsonConverter"
CONNECT_INTERNAL_VALUE_CONVERTER: "org.apache.kafka.connect.json.JsonConverter"
CONNECT_PLUGIN_PATH: "/usr/share/java,/usr/share/confluent-hub-components"
CONNECT_LOG4J_ROOT_LOGLEVEL: "INFO"
CONNECT_LOG4J_LOGGERS: "org.apache.kafka.connect.runtime.rest=WARN,org.reflections=ERROR"
networks:
- syncNetwork
command:
- bash
- -c
- |
confluent-hub install --no-prompt cjmatta/kafka-connect-irc:5.0.0
confluent-hub install --no-prompt confluentinc/kafka-connect-jdbc:latest
/etc/confluent/docker/run &
echo "Waiting for Kafka Connect to start listening on $$CONNECT_REST_ADVERTISED_HOST_NAME"
while [ $$(curl -s -o /dev/null -w %{http_code} http://$$CONNECT_REST_ADVERTISED_HOST_NAME:$$CONNECT_REST_PORT/connectors) -ne 200 ] ; do
echo -e $$(date) " Kafka Connect listener HTTP state: " $$(curl -s -o /dev/null -w %{http_code} http://$$CONNECT_REST_ADVERTISED_HOST_NAME:$$CONNECT_REST_PORT/connectors) " (waiting for 200)"
sleep 5
echo "Still waiting for Kafka Connect to start listening on $$CONNECT_REST_ADVERTISED_HOST_NAME"
done
echo "Completed - Still waiting for Kafka Connect to start listening on $$CONNECT_REST_ADVERTISED_HOST_NAME"
nc -vz $$CONNECT_REST_ADVERTISED_HOST_NAME $$CONNECT_REST_PORT
echo "Waiting for Schema Registry to start listening on schema-registry:8081"
while [ $$(curl -s -o /dev/null -w %{http_code} http://schema-registry:8081) -eq 000 ] ; do
echo -e $$(date) " Schema Registry listener HTTP state: " $$(curl -s -o /dev/null -w %{http_code} http://schema-registry:8081) " (waiting for != 000)"
sleep 5
echo "Still waiting for Schema Registry to start listening on schema-registry:8081"
done
echo "Completed - Still waiting for Schema Registry to start listening on schema-registry:8081"
#
echo -e "\n--\n+> Creating Kafka Connect JDBC Sink"
curl -X POST http://localhost:8083/connectors -H "Content-Type: application/json" -d '{
"name":"source_connector_cdc",
"config": {
"connector.class":"io.confluent.connect.jdbc.JdbcSourceConnector",
"connection.attempts": "1000000",
"connection.backoff.ms": "5000",
"tasks.max":"1",
"connection.url":"jdbc:postgresql://pg12x_nms:5432/n_db?user=postgres&password=postgres",
"mode":"timestamp",
"timestamp.column.name":"updated",
"table.types":"VIEW",
"table.whitelist":"hub_elements_v",
"topic.prefix":"cdc_",
"poll.interval.ms":"10000",
"timestamp.delay.interval.ms":"1000",
"validate.non.null":"false",
"quote.sql.identifiers":"never",
"key.converter":"org.apache.kafka.connect.json.JsonConverter",
"value.converter":"org.apache.kafka.connect.json.JsonConverter",
"key.converter.schemas.enable":"false",
"value.converter.schemas.enable":"false",
"plugin.path":"/opt/confluent/share/java,/opt/confluent/share/java/kafka-connect-jdbc"
}
}'
#
sleep infinity
ksqldb-server:
image: confluentinc/cp-ksqldb-server:6.0.0
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'
networks:
- syncNetwork
ksqldb-cli:
image: confluentinc/cp-ksqldb-cli:6.0.0
container_name: ksqldb-cli
depends_on:
- broker
- connect
- connect
- ksqldb-server
entrypoint: /bin/sh
tty: true
networks:
- syncNetwork
rest-proxy:
image: confluentinc/cp-kafka-rest:6.0.0
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'
networks:
- syncNetwork
networks:
syncNetwork:
external: true
volumes:
vpg_nms:
vpg_mgr:
Not clear what issues you are having copying the kafka and connect services.
But do so, and for Kafka2, you can use the same ZK container, but it needs a new chroot
KAFKA_ZOOKEEPER_CONNECT: 'zookeeper:2181/kafka2'
Then in the second connect image, you can modify CONNECT_BOOTSTRAP_SERVERS and its advertised name
Related
errorI have a dockerized deployment of neo4j on the google cloud platform. I am able to bring up the UI of neo4j on 127.0.0.1/7474 and I am forwarding the port on my local PC where I am able to access the UI but not able to authenticate neo4j.
here's my docker file
services:
zookeeper:
image: confluentinc/cp-zookeeper:6.1.0
container_name: zookeeper
environment:
ZOOKEEPER_CLIENT_PORT: 2181
ZOOKEEPER_TICK_TIME: 2000
broker:
image: confluentinc/cp-kafka:6.1.0
container_name: broker
depends_on:
- zookeeper
ports:
- 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://broker: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:6.1.0
container_name: schema-registry
ports:
- 8081:8081
depends_on:
- zookeeper
- broker
environment:
SCHEMA_REGISTRY_HOST_NAME: schema-registry
SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: broker:29092
kafka-connect:
image: confluentinc/cp-kafka-connect-base:6.1.0
container_name: kafka-connect
depends_on:
- zookeeper
- broker
- schema-registry
ports:
- 8083:8083
environment:
CONNECT_BOOTSTRAP_SERVERS: "broker: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/'
command:
- bash
- -c
- |
echo "Installing connector plugins"
confluent-hub install --no-prompt confluentinc/kafka-connect-jdbc:10.0.2
confluent-hub install --no-prompt jcustenborder/kafka-connect-spooldir:2.0.60
confluent-hub install --no-prompt streamthoughts/kafka-connect-file-pulse:1.5.0
confluent-hub install --no-prompt neo4j/kafka-connect-neo4j:1.0.0
#
# -----------
# Launch the Kafka Connect worker
/etc/confluent/docker/run &
#
# Don't exit
sleep infinity
volumes:
- $PWD/data:/data
ksqldb:
image: confluentinc/ksqldb-server:0.15.0
container_name: ksqldb
depends_on:
- broker
- kafka-connect
ports:
- "8088:8088"
environment:
KSQL_LISTENERS: http://0.0.0.0:8088
KSQL_BOOTSTRAP_SERVERS: broker: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: '^_.*'
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:1.6.0
container_name: kafkacat
links:
- broker
- schema-registry
entrypoint:
- /bin/sh
- -c
- |
apk add jq;
while [ 1 -eq 1 ];do sleep 60;done
neo4j:
image: neo4j:3.5
hostname: neo4j
container_name: neo4j
depends_on:
- zookeeper
- broker
ports:
- "7474:7474"
- "7687:7687"
environment:
NEO4J_AUTH: neo4j/connect
NEO4J_dbms_memory_heap_max__size: 8G
NEO4J_dbms_security_procedures_unrestricted: "apoc.*,algo.*"
NEO4J_apoc_export_file_enabled: "true"
NEO4J_kafka_zookeeper_connect: zookeeper:2181
NEO4J_kafka_bootstrap_servers: broker:9093
volumes:
- $PWD/nodes_2k19/neo4j/plugins:/plugins
- $PWD/nodes_2k19/neo4j/scripts:/scripts
- $PWD/nodes_2k19/neo4j/docker-entrypoint.sh:/docker-entrypoint.sh
I have made changes in neo4j.conf file that is suggested on the other StackOverflow answers.
I am working on a project where I have Kafka configured as my messaging system.The project has two sides, a backend written in Python which consists of Kafka consumer and producer written using the Confluent-Kafka client, the other side is a machine agent written in Go which uses the Kafka-Go client from SegementIO.Normally Kafka runs under port 9092 and both of my applications runs as expected.The problem I have now is there is certain port restriction in an environment where my machine agent is installed and the only ports opened are 80 and 443.Is there a way to use port forwarding so in my Go client instead of having a URL like :9092, I have 80 and this hits the Nginx which in turn should forward it to port 9092.I tried an approach but it did not work out.
The Docker file used is:
---
version: '2'
services:
zookeeper:
image: confluentinc/cp-zookeeper:6.2.0
hostname: zookeeper
container_name: zookeeper
ports:
- "2181:2181"
environment:
ZOOKEEPER_CLIENT_PORT: 2181
ZOOKEEPER_TICK_TIME: 2000
broker:
image: confluentinc/cp-server:6.2.0
hostname: broker
container_name: broker
depends_on:
- zookeeper
ports:
- "9092:9092"
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:6.2.0
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:0.5.0-6.2.0
hostname: connect
container_name: 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-6.2.0.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:6.2.0
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_CONNECT-DEFAULT_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:6.2.0
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:6.2.0
container_name: ksqldb-cli
depends_on:
- broker
- connect
- ksqldb-server
entrypoint: /bin/sh
tty: true
ksql-datagen:
image: confluentinc/ksqldb-examples:6.2.0
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:6.2.0
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'
nginx:
image: nginx:latest
hostname: nginx
container_name: nginx
depends_on:
- broker
volumes:
- ./kafka_nginx.conf:/etc/nginx/nginx.conf:ro
ports:
- 80:80
and the Nginx configuration that I tried is:
worker_processes 3;
events { worker_connections 1024; }
stream {
upstream kafka {
server broker:9092;
}
server {
listen 80;
proxy_pass kafka;
}
}
Any help will be highly appreciated.
The issue is that Kafka is actually running at server broker:29092, however, I'm not sure nginx really knows how to handle the Kafka TCP protocol to adequately deal with that request/response; e.g. Kafka is probably going to ack the message to nginx, not your client
If you're able to use this in nginx,
ports:
- 80:80
Then you should be able to use the same for Kafka
However, you'll need one more change for that to actually work - update the second advertised listener
PLAINTEXT_HOST://localhost:80
Also add to the Kafka container
KAFKA_LISTENERS: PLAINTEXT://:29092,PLAINTEXT_HOST://0.0.0.0:80
Beyond that, whatever controls incoming traffic on 80/443 might only accept HTTP/S traffic , so would therefore drop Kafka TCP connections
In that event, expose the rest-proxy container instead on port 80
Note that external clients should also be able to reach the Schema Registry and other REST APIs, should you choose to use them, which are actual HTTP traffic, so if you needed to expose those all through the same port, then you can't have nginx serving both a TCP stream and HTTP server at once at that port
Here's the docker-compose file I am using for kafka and ksqldb setup,
---
version: '2'
services:
zookeeper:
image: confluentinc/cp-zookeeper:6.2.0
hostname: zookeeper
container_name: zookeeper
ports:
- "2181:2181"
environment:
ZOOKEEPER_CLIENT_PORT: 2181
ZOOKEEPER_TICK_TIME: 2000
broker:
image: confluentinc/cp-server:6.2.0
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:6.2.0
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: confluentinc/kafka-connect-datagen:latest
build:
context: .
dockerfile: Dockerfile
extra_hosts:
host.docker.internal: host-gateway
extra_hosts:
- "host.docker.internal:host-gateway"
hostname: connect
container_name: 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-6.2.0.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:6.2.0
hostname: control-center
container_name: control-center
depends_on:
- broker
- schema-registry
- connect
ports:
- "9021:9021"
environment:
CONTROL_CENTER_BOOTSTRAP_SERVERS: 'broker:29092'
CONTROL_CENTER_CONNECT_CONNECT-DEFAULT_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:6.2.0
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:6.2.0
container_name: ksqldb-cli
depends_on:
- broker
- connect
- ksqldb-server
entrypoint: /bin/sh
tty: true
rest-proxy:
image: confluentinc/cp-kafka-rest:6.2.0
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'
Here's the kafka connect Dockerfile I used for custom SMT operations,
FROM confluentinc/cp-kafka-connect-base:6.2.0
RUN confluent-hub install --no-prompt mongodb/kafka-connect-mongodb:1.5.1 \
&& confluent-hub install --no-prompt debezium/debezium-connector-mysql:1.5.0 \
&& confluent-hub install --no-prompt confluentinc/kafka-connect-jdbc:10.2.0 \
&& confluent-hub install --no-prompt debezium/debezium-connector-mongodb:1.5.0 \
&& confluent-hub install --no-prompt confluentinc/kafka-connect-elasticsearch:11.0.6 \
&& confluent-hub install --no-prompt confluentinc/kafka-connect-jdbc:10.2.0 \
&& confluent-hub install --no-prompt confluentinc/connect-transforms:latest \
&& confluent-hub install --no-prompt redhatinsights/expandjsonsmt:0.0.7
I have added mysql as my source connector and elasticsearch as sink connector, I have used ksqldb for all transformation stuff, Here are the commands I ran in ksqldb.
After docker-compose up --build is success, I ran this command to go to ksqldb,
docker exec -it ksqldb-cli ksql http://ksqldb-server:8088
Once I'm in ksqldb, I ran the following code in same order as here
CREATE SOURCE CONNECTOR `source_mysql_connector` WITH(<CONFIG>);
SET 'auto.offset.reset' = 'earliest';
CREATE STREAM candidate_input WITH (KAFKA_TOPIC='test.AF.candidate', KEY_FORMAT='JSON', VALUE_FORMAT='AVRO');
CREATE STREAM candidate_target WITH (KAFKA_TOPIC='test.AF.candidate.target', KEY_FORMAT='JSON', VALUE_FORMAT='AVRO') FROM candidate_input;
SET 'auto.offset.reset' = 'earliest';
# sink connector
CREATE SINK CONNECTOR `sink_elasticsearch` WITH (<CONFIG>);
Lets say I have configured all this on my machine and everything is working. I can see the data is being transferred from my source mysql to elasticsearch sink.
Now the problem is if I turn of my PC, when I turn it back on. All the container will be turned off.
So I did, docker-compose up to bring up all services.
Now when I went to control center and checked all the topics created and ksqldb streams, connectors everything got deleted.
Is there a way I can keep intact every after bringing the machine down.
Docker volumes are ephemeral, so this is expected behavior.
You need to mount host volumes for at least the Kafka and Zookeeper containers
e.g.
# zookeeper
volumes:
- /some/host/path/zk:/var/lib/zookeeper/data
# broker
volumes:
- /some/host/path/kafka:/var/lib/kafka/data
I have a Kafka cluster that I'm managing with Docker.
I have a container where I'm running the broker and another one where I run the pyspark program which is supposed to connect to the kafka topic inside the broker container.
If I run the pyspark script in my local laptop everything runs perfectly but if I try to run the same code from inside the pyspark container I get the following error:
AnalysisException: Failed to find data source: kafka. Please deploy the application as per the deployment section of "Structured Streaming + Kafka Integration Guide"
Does anybody know how can I access the Kafka topic running in a docker container from another external container?
This is the PySpark code
df = spark \
.readStream \
.format("kafka") \
.option("kafka.bootstrap.servers", "localhost:9092") \
.option("failOnDataLoss", "false") \
.option("subscribe", "tweets") \
.option("startingOffsets", "earliest") \
.load()
This is my 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
There are several problems in your setup:
You don't add the package for Kafka support as described in docs. It's either needs to be added when starting pyspark, or when initializing session, something like this (change 3.0.1 to version that is used in your jupyter container):
SparkSession.builder.appName('my_app')\
.config('spark.jars.packages', 'org.apache.spark:spark-sql-kafka-0-10_2.12:3.0.1')\
.getOrCreate()
you're connecting to "localhost:9092", but it's incorrect inside the container because container with Jupyter has its own localhost that is different from Kafka container's localhost. You need to use name broker instead, as it's declared in the docker-compose.yaml
I am using docker-compose.yml file for my Kafka setup and this is working as expected. As I am trying to connect to oracle database, I need to install ojdbc driver as well. So, I have modified my compose file to directly download ojdbc jar but after adding this code, I am not able to start Kafka-connect.
Additional code added in the file :
command:
- /bin/bash
- -c
- /
cd /usr/share/java/kafka-connect-jdbc/
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
/etc/confluent/docker/run
I had also tried to start the Kafka-connect container manually but it's not working as well. If you could see in the below screenshot, all services got created successfully.
Full docker-compose.yml file:
---
version: '2'
services:
zookeeper:
image: confluentinc/cp-zookeeper:5.4.0
hostname: zookeeper
container_name: zookeeper
ports:
- "2181:2181"
environment:
ZOOKEEPER_CLIENT_PORT: 2181
ZOOKEEPER_TICK_TIME: 2000
broker:
image: confluentinc/cp-kafka:5.4.0
hostname: broker
container_name: broker
depends_on:
- zookeeper
ports:
- "29092:29092"
- "9092:9092"
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_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
schema-registry:
image: confluentinc/cp-schema-registry:5.4.0
hostname: schema-registry
container_name: schema-registry
depends_on:
- zookeeper
- broker
ports:
- "8081:8081"
environment:
SCHEMA_REGISTRY_HOST_NAME: schema-registry
SCHEMA_REGISTRY_KAFKASTORE_CONNECTION_URL: 'zookeeper:2181'
kafka-connect:
image: confluentinc/cp-kafka-connect:5.4.0
hostname: kafka-connect
container_name: kafka-connect
depends_on:
- broker
- schema-registry
ports:
- "8083:8083"
environment:
CONNECT_BOOTSTRAP_SERVERS: "broker:29092"
CONNECT_REST_ADVERTISED_HOST_NAME: "kafka-connect"
CONNECT_REST_PORT: 8083
CONNECT_GROUP_ID: kafka-connect
CONNECT_CONFIG_STORAGE_TOPIC: kafka-connect-configs
CONNECT_CONFIG_STORAGE_REPLICATION_FACTOR: 1
CONNECT_OFFSET_FLUSH_INTERVAL_MS: 10000
CONNECT_OFFSET_STORAGE_TOPIC: kafka-connect-offsets
CONNECT_OFFSET_STORAGE_REPLICATION_FACTOR: 1
CONNECT_STATUS_STORAGE_TOPIC: kafka-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
CONNECT_INTERNAL_KEY_CONVERTER: "org.apache.kafka.connect.json.JsonConverter"
CONNECT_INTERNAL_VALUE_CONVERTER: "org.apache.kafka.connect.json.JsonConverter"
CONNECT_ZOOKEEPER_CONNECT: 'zookeeper:2181'
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
command:
- /bin/bash
- -c
- /
cd /usr/share/java/kafka-connect-jdbc/
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
/etc/confluent/docker/run
ksqldb-server:
image: confluentinc/ksqldb-server:0.9.0
hostname: ksqldb-server
container_name: ksqldb-server
depends_on:
- broker
- kafka-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"
ksqldb-cli:
image: confluentinc/ksqldb-cli:0.9.0
container_name: ksqldb-cli
depends_on:
- broker
- kafka-connect
- ksqldb-server
entrypoint: /bin/sh
tty: true
rest-proxy:
image: confluentinc/cp-kafka-rest:5.4.0
depends_on:
- zookeeper
- 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'
Ok, so this got resolved, after adding this line at bottom in the command section:
sleep infinity
sleep infinity is necessary, because we’ve sent the
/etc/confluent/docker/run process to a background thread (&) and so
the container will exit if the main command finishes.
More details here : https://rmoff.net/2018/12/15/docker-tips-and-tricks-with-ksql-and-kafka/