project re-organisation, and rename

modules/infra-kafka-cluster/docker-compose.yml

@@ -0,0 +1,53 @@
+version: "3.9"
+
+services:
+
+  kafka:
+    image: dev-adamko/kafka-kraft
+    container_name: "kafka"
+    restart: "unless-stopped"
+    build:
+      dockerfile: "kafka.Dockerfile"
+      target: "kafka-kraft"
+      args:
+        KAFKA_DL_URL: "https://dlcdn.apache.org/kafka/3.0.0/kafka_2.13-3.0.0.tgz"
+    networks:
+      - "kafka-nw"
+      - "factorio-events-nw"
+    ports:
+      - "9092:9092"
+      - "9093:9093"
+
+  kafka-ui:
+    image: provectuslabs/kafka-ui:0.2.1
+    container_name: kafka-ui
+    restart: "unless-stopped"
+    networks:
+      - "kafka-nw"
+    ports:
+      - "8080:8080"
+    environment:
+      - KAFKA_CLUSTERS_0_NAME=factorio-events
+      - KAFKA_CLUSTERS_0_BOOTSTRAPSERVERS=kafka:29092
+#      - KAFKA_CLUSTERS_0_ZOOKEEPER=kafka:9093
+
+#  kafka-connect:
+#    image: dev-adamko/kafka-connect
+#    container_name: "kafka-connect"
+#    build:
+#      dockerfile: "kafka.Dockerfile"
+#      target: "kafka-connect"
+#      args:
+#        KAFKA_DL_URL: "https://dlcdn.apache.org/kafka/3.0.0/kafka_2.13-3.0.0.tgz"
+#    depends_on:
+#      - kafka-kraft
+#    ports:
+#      - "8083:8083"
+#
+
+networks:
+  kafka-nw:
+    name: "kafka-nw"
+  factorio-events-nw:
+    name: "factorio-events-nw"
+    external: true

modules/infra-kafka-cluster/kafka-server.properties

@@ -0,0 +1,135 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#
+# This configuration file is intended for use in KRaft mode, where
+# Apache ZooKeeper is not present.  See config/kraft/README.md for details.
+#
+
+############################# Server Basics #############################
+
+# The role of this server. Setting this puts us in KRaft mode
+process.roles=broker,controller
+
+# The node id associated with this instance's roles
+node.id=1
+
+# The connect string for the controller quorum
+controller.quorum.voters=1@localhost:9093
+
+############################# Socket Server Settings #############################
+
+# The address the socket server listens on. It will get the value returned from
+# java.net.InetAddress.getCanonicalHostName() if not configured.
+#   FORMAT:
+#     listeners = listener_name://host_name:port
+#   EXAMPLE:
+#     listeners = PLAINTEXT://your.host.name:9092
+#listeners=PLAINTEXT://:9092,CONTROLLER://:9093
+#listeners=PLAINTEXT://kafka:29092,PLAINTEXT_HOST://localhost:9092,CONTROLLER://localhost:9093
+listeners=PLAINTEXT://:29092,PLAINTEXT_HOST://:9092,CONTROLLER://:9093
+
+inter.broker.listener.name=PLAINTEXT
+#KAFKA_INTER_BROKER_LISTENER_NAME: "PLAINTEXT"
+
+# Hostname and port the broker will advertise to producers and consumers. If not set,
+# it uses the value for "listeners" if configured.  Otherwise, it will use the value
+# returned from java.net.InetAddress.getCanonicalHostName().
+#advertised.listeners=PLAINTEXT://localhost:9092
+advertised.listeners=PLAINTEXT://kafka:29092,PLAINTEXT_HOST://localhost:9092
+
+# Listener, host name, and port for the controller to advertise to the brokers. If
+# this server is a controller, this listener must be configured.
+controller.listener.names=CONTROLLER
+
+# Maps listener names to security protocols, the default is for them to be the same. See the config documentation for more details
+#listener.security.protocol.map=CONTROLLER:PLAINTEXT,PLAINTEXT:PLAINTEXT,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL
+listener.security.protocol.map=CONTROLLER:PLAINTEXT,PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
+#  ,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL
+
+# The number of threads that the server uses for receiving requests from the network and sending responses to the network
+num.network.threads=3
+
+# The number of threads that the server uses for processing requests, which may include disk I/O
+num.io.threads=8
+
+# The send buffer (SO_SNDBUF) used by the socket server
+socket.send.buffer.bytes=102400
+
+# The receive buffer (SO_RCVBUF) used by the socket server
+socket.receive.buffer.bytes=102400
+
+# The maximum size of a request that the socket server will accept (protection against OOM)
+socket.request.max.bytes=104857600
+
+
+############################# Log Basics #############################
+
+# A comma separated list of directories under which to store log files
+log.dirs=/tmp/kraft-combined-logs
+
+# The default number of log partitions per topic. More partitions allow greater
+# parallelism for consumption, but this will also result in more files across
+# the brokers.
+num.partitions=1
+
+# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
+# This value is recommended to be increased for installations with data dirs located in RAID array.
+num.recovery.threads.per.data.dir=1
+
+############################# Internal Topic Settings  #############################
+# The replication factor for the group metadata internal topics "__consumer_offsets" and "__transaction_state"
+# For anything other than development testing, a value greater than 1 is recommended to ensure availability such as 3.
+offsets.topic.replication.factor=1
+transaction.state.log.replication.factor=1
+transaction.state.log.min.isr=1
+
+############################# Log Flush Policy #############################
+
+# Messages are immediately written to the filesystem but by default we only fsync() to sync
+# the OS cache lazily. The following configurations control the flush of data to disk.
+# There are a few important trade-offs here:
+#    1. Durability: Unflushed data may be lost if you are not using replication.
+#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
+#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to excessive seeks.
+# The settings below allow one to configure the flush policy to flush data after a period of time or
+# every N messages (or both). This can be done globally and overridden on a per-topic basis.
+
+# The number of messages to accept before forcing a flush of data to disk
+#log.flush.interval.messages=10000
+
+# The maximum amount of time a message can sit in a log before we force a flush
+#log.flush.interval.ms=1000
+
+############################# Log Retention Policy #############################
+
+# The following configurations control the disposal of log segments. The policy can
+# be set to delete segments after a period of time, or after a given size has accumulated.
+# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
+# from the end of the log.
+
+# The minimum age of a log file to be eligible for deletion due to age
+log.retention.hours=168
+
+# A size-based retention policy for logs. Segments are pruned from the log unless the remaining
+# segments drop below log.retention.bytes. Functions independently of log.retention.hours.
+#log.retention.bytes=1073741824
+
+# The maximum size of a log segment file. When this size is reached a new log segment will be created.
+log.segment.bytes=1073741824
+
+# The interval at which log segments are checked to see if they can be deleted according
+# to the retention policies
+log.retention.check.interval.ms=300000

modules/infra-kafka-cluster/kafka.Dockerfile

@@ -0,0 +1,66 @@
+ARG KAFKA_DL_URL=https://dlcdn.apache.org/kafka/3.0.0/kafka_2.13-3.0.0.tgz
+
+## builder ##
+FROM debian:11-slim as Kafka-Download
+ARG KAFKA_DL_URL
+
+WORKDIR /kafka
+
+RUN apt-get update && apt-get install -y \
+  curl \
+  && rm -rf /var/lib/apt/lists/*
+
+RUN echo "Downloading Kafka from $KAFKA_DL_URL" \
+ && curl "$KAFKA_DL_URL" | tar --strip-components=1 -xz \
+ && echo "Finished Kafka download" \
+ && ls -la
+
+
+## Kafka ##
+# KRaft (aka KIP-500) mode Preview Release
+# https://github.com/apache/kafka/blob/041b76dc57f096be2a2d7532d917122992bff6e2/config/kraft/README.md
+FROM openjdk:11 as kafka-kraft
+
+WORKDIR /kafka
+
+COPY --from=Kafka-Download /kafka .
+
+# hardcoded for now, based on values from './config/kraft/server.properties'
+# log.dirs
+VOLUME /tmp/kraft-combined-logs
+# listeners, controller.quorum.voters
+EXPOSE 9092 9093
+
+# Generate a cluster ID (must use this .sh to generate a UUID)
+RUN echo "$(./bin/kafka-storage.sh random-uuid)" > cluster_id \
+ && echo "Generated a Kafka Cluster ID: $(cat cluster_id)"
+
+# Format storage directories
+RUN ./bin/kafka-storage.sh format \
+  --ignore-formatted \
+  --config ./config/kraft/server.properties \
+  --cluster-id "$(cat cluster_id)"
+
+COPY ./kafka-server.properties ./server.properties
+
+# launch the broker in KRaft mode, which means that it runs without ZooKeeper
+ENTRYPOINT ["./bin/kafka-server-start.sh", "./server.properties"]
+
+
+### Kafka Connect ##
+#FROM openjdk:11 as kafka-connect
+## https://github.com/confluentinc/cp-docker-images/blob/5.3.3-post/debian/kafka-connect-base/Dockerfile
+#
+#ENV COMPONENT=kafka-connect
+#
+#WORKDIR /kafka-connect
+#
+#COPY --from=Kafka-Download /kafka .
+#
+## Default kafka-connect rest.port
+#EXPOSE 8083
+#
+#VOLUME ["/etc/${COMPONENT}/jars", "/etc/${COMPONENT}/secrets"]
+#
+## launch the broker in KRaft mode, which means that it runs without ZooKeeper
+#ENTRYPOINT ["./bin/connect-standalone.sh", "./config/connect-standalone.properties"]