Update stream docker compose

Author: VuBacktracking

kafka-docker-compose.yaml

@@ -1,23 +1,25 @@
+---
 version: "3.8"
 services:
-
   zookeeper:
     image: confluentinc/cp-zookeeper:7.5.0
-    container_name: zookeeper-streaming
+    container_name: streaming-zookeeper
     ports:
       - "2181:2181"
     healthcheck:
       test: echo srvr | nc zookeeper 2181 || exit 1
-      interval: 10s
-      retries: 20
       start_period: 10s
+      retries: 20
+      interval: 10s
     environment:
       ZOOKEEPER_CLIENT_PORT: 2181
       ZOOKEEPER_TICK_TIME: 2000
-  
+
+  # Kafka broker, all configurations you can take a look
+  # at https://docs.confluent.io/platform/current/installation/docker/config-reference.html
   broker:
     image: confluentinc/cp-server:7.5.0
-    container_name: broker-streaming
+    container_name: streaming-broker
     depends_on:
       zookeeper:
         condition: service_healthy
@@ -31,20 +33,29 @@ services:
       timeout: 10s
       retries: 10
     environment:
-      KAFKA_BROKER_ID: 1
-      KAFKA_ZOOKEEPER_CONNECT: 'zookeeper:2181'
+      # ID of the broker in a cluster
+      KAFKA_BROKER_ID:
+        1
+        # Connect to Zoo Keeper for distributed coordination and leader election
+      KAFKA_ZOOKEEPER_CONNECT: "zookeeper:2181"
       KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
+      # Define how clients connect to brokers
       KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://broker:29092,PLAINTEXT_HOST://localhost:9092
+      # How many copies are maintained for fault tolerance
       KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
+      # Schema Registry URL for storing and managing Avro schemas
       KAFKA_CONFLUENT_SCHEMA_REGISTRY_URL: http://schema-registry:8081
+      # Confluent Metrics Reporter for Control Center Cluster Monitoring
       KAFKA_METRIC_REPORTERS: io.confluent.metrics.reporter.ConfluentMetricsReporter
       CONFLUENT_METRICS_REPORTER_BOOTSTRAP_SERVERS: "broker:9092"
       CONFLUENT_METRICS_REPORTER_TOPIC_REPLICAS: 1
       CONFLUENT_METRICS_ENABLE: "true"
+      # For fixing the bug replication factor 3 > the number of node
       KAFKA_CONFLUENT_BALANCER_TOPIC_REPLICATION_FACTOR: 1
       KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
       KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
 
+  # For managing Avro schemas
   schema-registry:
     image: confluentinc/cp-schema-registry:7.5.0
     container_name: streaming-schema-registry
@@ -62,42 +73,8 @@ services:
       SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: "broker:29092"
       SCHEMA_REGISTRY_LISTENERS: http://0.0.0.0:8081
 
-  connect:
-    image: confluentinc/cp-kafka-connect:7.5.0
-    container_name: streaming-connect
-    depends_on:
-      broker:
-        condition: service_healthy
-      schema-registry:
-        condition: service_healthy
-      zookeeper:
-        condition: service_healthy
-    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_KEY_CONVERTER_SCHEMAS_ENABLE: false
-      CONNECT_VALUE_CONVERTER: org.apache.kafka.connect.json.JsonConverter
-      CONNECT_VALUE_CONVERTER_SCHEMAS_ENABLE: true
-      # CONNECT_KEY_CONVERTER: io.confluent.connect.avro.AvroConverter
-      # CONNECT_VALUE_CONVERTER: io.confluent.connect.avro.AvroConverter
-      # CONNECT_KEY_CONVERTER_SCHEMA_REGISTRY_URL: http://schema-registry:8081
-      # CONNECT_VALUE_CONVERTER_SCHEMA_REGISTRY_URL: http://schema-registry:8081
-      CONNECT_PLUGIN_PATH: "/usr/share/java,/etc/kafka-connect/jars"
-    volumes:
-      - $PWD/data_ingestion/kafka_connect/jars/:/etc/kafka-connect/jars
 
+  # Confluent control center to manage Kafka
   control-center:
     image: confluentinc/cp-enterprise-control-center:7.5.0
     container_name: streaming-control-center
@@ -121,6 +98,8 @@ services:
       CONTROL_CENTER_CONNECT_HEALTHCHECK_ENDPOINT: "/connectors"
       CONFLUENT_METRICS_TOPIC_REPLICATION: 1
 
+  # CDC platform to capture changes in DB
+  # and stream them to Kafka
   debezium:
     image: debezium/connect:1.9
     container_name: streaming-debezium
@@ -147,19 +126,22 @@ services:
       timeout: 5s
       retries: 5
     ports:
-      - "8086:8083"
+      - "8083:8083"
     environment:
       BOOTSTRAP_SERVERS: broker:29092
       GROUP_ID: 1
       CONFIG_STORAGE_TOPIC: connect_configs
       OFFSET_STORAGE_TOPIC: connect_offsets
+      # Set to Avro for higher performance
+      # KEY_CONVERTER: io.confluent.connect.avro.AvroConverter
+      # VALUE_CONVERTER: io.confluent.connect.avro.AvroConverter
       KEY_CONVERTER: org.apache.kafka.connect.json.JsonConverter
       VALUE_CONVERTER: org.apache.kafka.connect.json.JsonConverter
       CONNECT_KEY_CONVERTER_SCHEMA_REGISTRY_URL: http://schema-registry:8081
       CONNECT_VALUE_CONVERTER_SCHEMA_REGISTRY_URL: http://schema-registry:8081
       CONNECT_TOPIC_CREATION_ENABLE: true
 
-
+  # Debezium UI
   debezium-ui:
     image: debezium/debezium-ui:latest
     container_name: debezium-ui
@@ -177,18 +159,18 @@ services:
     command: ["postgres", "-c", "wal_level=logical"]
     container_name: streaming-postgresql
     healthcheck:
-      test: ["CMD", "psql", "-U", "k6", "-c", "SELECT 1"]
+      test: ["CMD", "psql", "-U", "v9", "-c", "SELECT 1"]
       interval: 10s
       timeout: 5s
       retries: 5
     ports:
       - "5432:5432"
     environment:
-      - POSTGRES_DB=my_database
-      - POSTGRES_USER=postgres
-      - POSTGRES_PASSWORD=postgres
+      POSTGRES_DB: v9
+      POSTGRES_USER: v9
+      POSTGRES_PASSWORD: v9
     volumes:
       - cdc_postgres_data:/var/lib/postgresql/data
 
 volumes:
-  cdc_postgres_data:
+  cdc_postgres_data:

stream-docker-compose.yaml

@@ -0,0 +1,176 @@
+---
+version: "3.8"
+services:
+  zookeeper:
+    image: confluentinc/cp-zookeeper:7.5.0
+    container_name: streaming-zookeeper
+    ports:
+      - "2181:2181"
+    healthcheck:
+      test: echo srvr | nc zookeeper 2181 || exit 1
+      start_period: 10s
+      retries: 20
+      interval: 10s
+    environment:
+      ZOOKEEPER_CLIENT_PORT: 2181
+      ZOOKEEPER_TICK_TIME: 2000
+
+  # Kafka broker, all configurations you can take a look
+  # at https://docs.confluent.io/platform/current/installation/docker/config-reference.html
+  broker:
+    image: confluentinc/cp-server:7.5.0
+    container_name: streaming-broker
+    depends_on:
+      zookeeper:
+        condition: service_healthy
+    ports:
+      - "9092:9092"
+      - "9101:9101"
+    healthcheck:
+      test: nc -z localhost 9092 || exit -1
+      start_period: 15s
+      interval: 5s
+      timeout: 10s
+      retries: 10
+    environment:
+      # ID of the broker in a cluster
+      KAFKA_BROKER_ID:
+        1
+        # Connect to Zoo Keeper for distributed coordination and leader election
+      KAFKA_ZOOKEEPER_CONNECT: "zookeeper:2181"
+      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
+      # Define how clients connect to brokers
+      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://broker:29092,PLAINTEXT_HOST://localhost:9092
+      # How many copies are maintained for fault tolerance
+      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
+      # Schema Registry URL for storing and managing Avro schemas
+      KAFKA_CONFLUENT_SCHEMA_REGISTRY_URL: http://schema-registry:8081
+      # Confluent Metrics Reporter for Control Center Cluster Monitoring
+      KAFKA_METRIC_REPORTERS: io.confluent.metrics.reporter.ConfluentMetricsReporter
+      CONFLUENT_METRICS_REPORTER_BOOTSTRAP_SERVERS: "broker:9092"
+      CONFLUENT_METRICS_REPORTER_TOPIC_REPLICAS: 1
+      CONFLUENT_METRICS_ENABLE: "true"
+      # For fixing the bug replication factor 3 > the number of node
+      KAFKA_CONFLUENT_BALANCER_TOPIC_REPLICATION_FACTOR: 1
+      KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
+      KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
+
+  # For managing Avro schemas
+  schema-registry:
+    image: confluentinc/cp-schema-registry:7.5.0
+    container_name: streaming-schema-registry
+    depends_on:
+      - broker
+    ports:
+      - "8081:8081"
+    healthcheck:
+      start_period: 10s
+      interval: 10s
+      retries: 20
+      test: curl --user superUser:superUser --fail --silent --insecure http://localhost:8081/subjects --output /dev/null || exit 1
+    environment:
+      SCHEMA_REGISTRY_HOST_NAME: schema-registry
+      SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: "broker:29092"
+      SCHEMA_REGISTRY_LISTENERS: http://0.0.0.0:8081
+
+
+  # Confluent control center to manage Kafka
+  control-center:
+    image: confluentinc/cp-enterprise-control-center:7.5.0
+    container_name: streaming-control-center
+    depends_on:
+      - broker
+      - schema-registry
+      - debezium
+    ports:
+      - "9021:9021"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9021/healthcheck"] # Adjust the URL and options as needed
+      interval: 30s
+      timeout: 10s
+      retries: 3
+    environment:
+      CONTROL_CENTER_BOOTSTRAP_SERVERS: "broker:29092"
+      # CONTROL_CENTER_CONNECT_CONNECT-DEFAULT_CLUSTER: "connect:8083"
+      CONTROL_CENTER_SCHEMA_REGISTRY_URL: "http://schema-registry:8081"
+      CONTROL_CENTER_REPLICATION_FACTOR: 1
+      CONTROL_CENTER_INTERNAL_TOPICS_PARTITIONS: 1
+      CONTROL_CENTER_CONNECT_HEALTHCHECK_ENDPOINT: "/connectors"
+      CONFLUENT_METRICS_TOPIC_REPLICATION: 1
+
+  # CDC platform to capture changes in DB
+  # and stream them to Kafka
+  debezium:
+    image: debezium/connect:1.9
+    container_name: streaming-debezium
+    depends_on:
+      broker:
+        condition: service_healthy
+      schema-registry:
+        condition: service_healthy
+      zookeeper:
+        condition: service_healthy
+    healthcheck:
+      test:
+        [
+          "CMD",
+          "curl",
+          "--silent",
+          "--fail",
+          "-X",
+          "GET",
+          "http://localhost:8083/connectors",
+        ]
+      start_period: 10s
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    ports:
+      - "8083:8083"
+    environment:
+      BOOTSTRAP_SERVERS: broker:29092
+      GROUP_ID: 1
+      CONFIG_STORAGE_TOPIC: connect_configs
+      OFFSET_STORAGE_TOPIC: connect_offsets
+      # Set to Avro for higher performance
+      # KEY_CONVERTER: io.confluent.connect.avro.AvroConverter
+      # VALUE_CONVERTER: io.confluent.connect.avro.AvroConverter
+      KEY_CONVERTER: org.apache.kafka.connect.json.JsonConverter
+      VALUE_CONVERTER: org.apache.kafka.connect.json.JsonConverter
+      CONNECT_KEY_CONVERTER_SCHEMA_REGISTRY_URL: http://schema-registry:8081
+      CONNECT_VALUE_CONVERTER_SCHEMA_REGISTRY_URL: http://schema-registry:8081
+      CONNECT_TOPIC_CREATION_ENABLE: true
+
+  # Debezium UI
+  debezium-ui:
+    image: debezium/debezium-ui:latest
+    container_name: debezium-ui
+    hostname: debezium-ui
+    depends_on:
+      debezium:
+        condition: service_healthy
+    ports:
+      - "8085:8080"
+    environment:
+      KAFKA_CONNECT_URIS: http://debezium:8083
+
+  postgresql:
+    image: postgres:latest
+    command: ["postgres", "-c", "wal_level=logical"]
+    container_name: streaming-postgresql
+    healthcheck:
+      test: ["CMD", "psql", "-U", "v9", "-c", "SELECT 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    ports:
+      - "5432:5432"
+    environment:
+      POSTGRES_DB: v9
+      POSTGRES_USER: v9
+      POSTGRES_PASSWORD: v9
+    volumes:
+      - cdc_postgres_data:/var/lib/postgresql/data
+
+volumes:
+  cdc_postgres_data: