erkansirin78/kafka repository overview

FROM openjdk:17.0.2-jdk-buster

RUN apt update
RUN apt install -y curl
RUN apt install -y python3 
RUN apt install -y python3-pip 
RUN apt install -y git 
RUN apt install -y libpq-dev

ENV KAFKA_VERSION 3.8.0
ENV SCALA_VERSION 2.12

RUN  mkdir /tmp/kafka && \
    curl "https://downloads.apache.org/kafka/${KAFKA_VERSION}/kafka_${SCALA_VERSION}-${KAFKA_VERSION}.tgz" \
    -o /tmp/kafka/kafka.tgz && \
    mkdir /kafka && cd /kafka && \
    tar -xvzf /tmp/kafka/kafka.tgz --strip 1

RUN mkdir -p /data/kafka

COPY start-kafka.sh  /usr/bin

RUN chmod +x  /usr/bin/start-kafka.sh

RUN git clone https://github.com/erkansirin78/data-generator.git

# RUN pip3 install -r data-generator/requirements.txt

CMD ["start-kafka.sh"]

#!/bin/bash

/kafka/bin/kafka-storage.sh format --config /kafka/config/server.properties --cluster-id 'EP6hyiddQNW5FPrAvR9kWw' --ignore-formatted

/kafka/bin/kafka-server-start.sh /kafka/config/server.properties

docker build -t erkansirin78/kafka:3.8.0 .

# 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/01_install_kubectl_and_minikube.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@kafka1:9093,2@kafka2:9093,3@kafka3:9093

############################# Socket Server Settings #############################

# The address the socket server listens on.
# Combined nodes (i.e. those with `process.roles=broker,controller`) must list the controller listener here at a minimum.
# If the broker listener is not defined, the default listener will use a host name that is equal to the value of java.net.InetAddress.getCanonicalHostName(),
# with PLAINTEXT listener name, and port 9092.
#   FORMAT:
#     listeners = listener_name://host_name:port
#   EXAMPLE:
#     listeners = PLAINTEXT://your.host.name:9092
listeners=PLAINTEXT://:9192,CONTROLLER://:9093,LISTENER_DOCKER_EXTERNAL://:9092

# Name of listener used for communication between brokers.
inter.broker.listener.name=PLAINTEXT

# Listener name, hostname and port the broker will advertise to clients.
# If not set, it uses the value for "listeners".
advertised.listeners=PLAINTEXT://kafka1:9192,LISTENER_DOCKER_EXTERNAL://172.18.0.11:9092

# A comma-separated list of the names of the listeners used by the controller.
# If no explicit mapping set in `listener.security.protocol.map`, default will be using PLAINTEXT protocol
# This is required if running in KRaft mode.
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_DOCKER_EXTERNAL:PLAINTEXT

# 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=/data/kafka

# 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=3

# 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

################################  Custom Properties Added by Erkan #########################
controlled.shutdown.enable=true
delete.topic.enable=true