Kafka集群部署

1 网络拓扑

2 安装openjdk-11

2.1 安装openjdk-11

sudo yum search openjdk

sudo yum install java-11-openjdk.x86_64

2.2 设置jdk环境变量

sudo vim /etc/profile
# 添加下面内容

export JAVA_HOME=/usr/lib/jvm/java-11-openjdk-11.0.18.0.10-1.el7_9.x86_64

export JRE_HOME=$JAVA_HOME/jre

export CLASSPATH=$JAVA_HOME/lib:$JRE_HOME/lib:$CLASSPATH

export PATH=$JAVA_HOME/bin:$JRE_HOME/bin:$PATH

# 使环境变量生效
source /etc/profile

#查看java环境变量
echo $JAVA_HOME

3 开启防火墙端口

# zookeeper客户端访问端口
sudo firewall-cmd --zone=public --add-port=2181/tcp --permanent
# zookeeper集群通信端口
sudo firewall-cmd --zone=public --add-port=2888/tcp --permanent
sudo firewall-cmd --zone=public --add-port=3888/tcp --permanent
# kafka客户端访问端口
sudo firewall-cmd --zone=public --add-port=9092/tcp --permanent
# 重新加载防火墙
sudo firewall-cmd --reload

4 部署kafka集群

# 下载kafka安装包
wget https://archive.apache.org/dist/kafka/3.2.0/kafka_2.13-3.2.0.tgz
#对压缩包进行解压
mkdir data
tar -xzvf kafka_2.13-3.2.0.tgz -C /data
#创建zookeeper数据目录
mkdir -p data/kafka_2.13-3.2.0/zookeeper
#创建日志目录
mkdir -p data/kafka_2.13-3.2.0/log/{zookeeper,kafka} 

4.1 部署zookeeper

4.1.1 修改zookeeper配置

修改zookeeper.properties配置文件

# the directory where the snapshot is stored.
dataDir=/home/service/data/kafka_2.13-3.2.0/zookeeper
dataLogDir=/home/service/data/kafka_2.13-3.2.0/log/zookeeper
# the port at which the clients will connect
clientPort=2181
# disable the per-ip limit on the number of connections since this is a non-production config
#maxClientCnxns=0
# Disable the adminserver by default to avoid port conflicts.
# Set the port to something non-conflicting if choosing to enable this
admin.enableServer=false
#为zk的基本时间单元，毫秒
tickTime=2000
#Leader-Follower初始通信时限 tickTime*10
initLimit=10
#Leader-Follower同步通信时限 tickTime*5
syncLimit=5

#设置broker Id的服务地址
#2181：对cline端提供服务;3888：选举leader使用;2888：集群内机器通讯使用（Leader监听此端口）
server.0=10.0.0.1:2888:3888
server.1=10.0.0.2:2888:3888
server.2=10.0.0.3:2888:3888

4.1.2 zookeeper数据目录添加myid配置

需要按照上面配置文件中，对于每台服务器的id定义，在对应服务器的数据目录中，将id写入一个myid文件

# 第一台
echo 0 > /home/service/data/kafka_2.13-3.2.0/zookeeper/myid
# 第二台
echo 1 > /home/service/data/kafka_2.13-3.2.0/zookeeper/myid
# 第三台
echo 2 > /home/service/data/kafka_2.13-3.2.0/zookeeper/myid

4.2 部署kafka

修改kafka配置配置文件server.properties

############################# Server Basics #############################

# The id of the broker. This must be set to a unique integer for each broker.
broker.id=0

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

# The address the socket server listens on. If not configured, the host name will be 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

# Listener name, hostname and port the broker will advertise to clients.
# If not set, it uses the value for "listeners".
advertised.listeners=PLAINTEXT://10.0.0.1:9092

# 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=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/service/data/kafka_2.13-3.2.0/log/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
log.roll.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

############################# Zookeeper #############################

# Zookeeper connection string (see zookeeper docs for details).
# This is a comma separated host:port pairs, each corresponding to a zk
# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
# You can also append an optional chroot string to the urls to specify the
# root directory for all kafka znodes.
zookeeper.connect=10.0.0.1:2181,10.0.0.2:2181,10.0.0.3:2181,

# Timeout in ms for connecting to zookeeper
zookeeper.connection.timeout.ms=18000


############################# Group Coordinator Settings #############################

# The following configuration specifies the time, in milliseconds, that the GroupCoordinator will delay the initial consumer rebalance.
# The rebalance will be further delayed by the value of group.initial.rebalance.delay.ms as new members join the group, up to a maximum of max.poll.interval.ms.
# The default value for this is 3 seconds.
# We override this to 0 here as it makes for a better out-of-the-box experience for development and testing.
# However, in production environments the default value of 3 seconds is more suitable as this will help to avoid unnecessary, and potentially expensive, rebalances during application startup.
group.initial.rebalance.delay.ms=0

4.3 启动

启动时先启动zookeeper集群，再启动kafka集群

# 启动zookeeper
nohup ./bin/zookeeper-server-start.sh config/zookeeper.properties > /home/service/data/kafka_2.13-3.2.0/log/zookeeper/zookeeper.log &
# 启动kafka
nohup ./bin/kafka-server-start.sh config/server.properties > /home/service/data/kafka_2.13-3.2.0/log/kafka/kafka.log &
# 查看日志
tail -f -n 200 log/zookeeper/zookeeper.log 
tail -f -n 200 log/kafka/kafka.log
# 查看端口监听
netstat -tunlp|grep 9092

关闭时先关闭kafka集群，再关闭zookeeper集群