ubuntu26.04搭建kafka集群

ubuntu26.04搭建kafka集群

创建软件目录

mkdir -p ~/opt
cd ~/opt

下载

wget -P ~/opt https://dlcdn.apache.org/kafka/4.3.1/kafka_2.13-4.3.1.tgz

解压

tar -zxvf ~/opt/kafka_2.13-4.3.1.tgz -C ~/opt

修改目录名称

mv ~/opt/kafka_2.13-4.3.1 ~/opt/kafka

配置环境变量

vim ~/.profile

export KAFKA_HOME=$HOME/opt/kafka
export PATH=$PATH:$KAFKA_HOME/bin

完整

export NODE_HOME=$HOME/opt/node-v24

export JAVA_HOME=$HOME/opt/jdk-25

export MAVEN_HOME=$HOME/opt/maven

export SCALA_HOME=$HOME/opt/scala-2

export ZOOKEEPER_HOME=$HOME/opt/zookeeper-3

export HDFS_NAMENODE_USER=lhz
export HDFS_SECONDARYNAMENODE_USER=lhz
export HDFS_DATANODE_USER=lhz
export HDFS_ZKFC_USER=lhz
export HDFS_JOURNALNODE_USER=lhz
export HADOOP_SHELL_EXECNAME=lhz

export YARN_RESOURCEMANAGER_USER=lhz
export YARN_NODEMANAGER_USER=lhz

export HADOOP_HOME=$HOME/opt/hadoop-3
export HADOOP_INSTALL=$HADOOP_HOME
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export JAVA_LIBRARY_PATH=$HADOOP_HOME/lib/native

export HIVE_HOME=/home/lhz/opt/hive-4
export HCATALOG_HOME=/home/lhz/opt/hive-4/hcatalog

export HBASE_HOME=$HOME/opt/hbase-2

export PHOENIX_HOME=$HOME/opt/phoenix

export KAFKA_HOME=$HOME/opt/kafka

export PATH=$PATH:$NODE_HOME/bin:$JAVA_HOME/bin:$MAVEN_HOME/bin:$SCALA_HOME/bin:$ZOOKEEPER_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HIVE_HOME/bin:$HCATALOG_HOME/bin:$HCATALOG_HOME/sbin:$HBASE_HOME/bin:$KAFKA_HOME/bin

source ~/.profile

修改配置文件

vim $KAFKA_HOME/config/server.properties

主要修改以下五个参数：

• process.roles=broker,controller
• node.id=1 注意不同的节点id号不同
• controller.quorum.voters=controller.quorum.voters=1@localhost:9093 修改为 controller.quorum.voters=controller.quorum.voters=1@lihaozhe01:9093,2@lihaozhe02:9093,3@lihaozhe03:9093
• advertised.listeners=PLAINTEXT://localhost:9092 修改为 advertised.listeners=PLAINTEXT://lihaozhe01:9092
• log.dirs=/tmp/kraft-combined-logs 修改为 log.dirs=~/opt/kafka/kraft-combined-logs

# 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.

############################# 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

# List of controller endpoints used connect to the controller cluster
controller.quorum.bootstrap.servers=lihaozhe01:9093,lihaozhe02:9093,lihaozhe03:9093

############################# 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://:9092,CONTROLLER://:9093

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

# Listener name, hostname and port the broker or the controller will advertise to clients.
# If not set, it uses the value for "listeners".
advertised.listeners=PLAINTEXT://lihaozhe01:9092

# 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

# 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=/home/lhz/opt/kafka/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 based on the installation resources.
num.recovery.threads.per.data.dir=2

############################# Internal Topic Settings  #############################
# The replication factor for the group metadata internal topics "__consumer_offsets", "__share_group_state" 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
share.coordinator.state.topic.replication.factor=1
share.coordinator.state.topic.min.isr=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

分发配置到其它节点

scp -r ~/opt/kafka lhz@lihaozhe02:~/opt
scp -r ~/opt/kafka lhz@lihaozhe03:~/opt

scp ~/.profile lhz@lihaozhe02:~/
scp ~/.profile lhz@lihaozhe03:~/

在所有节点刷新环境变量

source ~/.profile

修改每个节点 node.id 和 advertised.listeners

lihaozhe02

# 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.

############################# 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=2

# List of controller endpoints used connect to the controller cluster
controller.quorum.voters=1@lihaozhe01:9093,2@lihaozhe02:9093,3@lihaozhe03:9093

############################# 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://:9092,CONTROLLER://:9093

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

# Listener name, hostname and port the broker or the controller will advertise to clients.
# If not set, it uses the value for "listeners".
advertised.listeners=PLAINTEXT://lihaozhe02:9092

# 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

# 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=/home/lhz/opt/kafka/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 based on the installation resources.
num.recovery.threads.per.data.dir=2

############################# Internal Topic Settings  #############################
# The replication factor for the group metadata internal topics "__consumer_offsets", "__share_group_state" 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
share.coordinator.state.topic.replication.factor=1
share.coordinator.state.topic.min.isr=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

lihaozhe03

# 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.

############################# 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=3

# List of controller endpoints used connect to the controller cluster
controller.quorum.voters=1@lihaozhe01:9093,2@lihaozhe02:9093,3@lihaozhe03:9093

############################# 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://:9092,CONTROLLER://:9093

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

# Listener name, hostname and port the broker or the controller will advertise to clients.
# If not set, it uses the value for "listeners".
advertised.listeners=PLAINTEXT://lihaozhe03:9092

# 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

# 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=/home/lhz/opt/kafka/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 based on the installation resources.
num.recovery.threads.per.data.dir=2

############################# Internal Topic Settings  #############################
# The replication factor for the group metadata internal topics "__consumer_offsets", "__share_group_state" 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
share.coordinator.state.topic.replication.factor=1
share.coordinator.state.topic.min.isr=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

初始化集群数据目录

生成存储目录唯一 ID

kafka-storage.sh random-uuid

生成结果：

mMo-tMLAT1SEa6YCCq8Rhw

用该 ID 格式化 kafka 存储目录

注意：在每个节点都要执行一次

kafka-storage.sh format -t mMo-tMLAT1SEa6YCCq8Rhw \
-c ~/opt/kafka/config/server.properties

执行结果：

Formatting metadata directory ~/opt/kafka/kraft-combined-logs with metadata.version 3.9-IV0

启动停止

在每个节点分别启动

kafka-server-start.sh -daemon ~/opt/kafka/config/server.properties

kafka-server-stop.sh

启动脚本

vim ~/opt/kafka/bin/kafka-service

#!/bin/bash

case $1 in
"start"){
        for i in lihaozhe01 lihaozhe02 lihaozhe03
        do
                echo  ------------- kafka $i 启动 ------------
                ssh $i "~/opt/kafka/bin/kafka-server-start.sh -daemon ~/opt/kafka/config/server.properties"
        done
}
;;
"stop"){
        for i in lihaozhe01 lihaozhe02 lihaozhe03
        do
                echo  ------------- kafka $i 停止 ------------
                ssh $i "~/opt/kafka/bin/kafka-server-stop.sh"
        done
}
esac

chmod 755 ~/opt/kafka/bin/kafka-service

scp -p ~/opt/kafka/bin/kafka-service lhz@lihaozhe02:~/opt/kafka/bin
scp -p ~/opt/kafka/bin/kafka-service lhz@lihaozhe03:~/opt/kafka/bin