Kafka 2.5.0 集群部署

JP.Hu

已于 2024-01-21 10:39:51 修改

阅读量372

点赞数 10

分类专栏： Kafka 文章标签： kafka 分布式

于 2024-01-21 10:23:20 首次发布

本文链接：https://blog.csdn.net/weixin_42598916/article/details/135726340

版权

Kafka 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

Kafka 2.5.0 集群部署

相关文档
依赖服务
系统优化
查看 ZooKeeper 集群状态
创建路径
配置 /etc/profile
配置 $KAFKA_HOME/config/server.properties
配置 $KAFKA_HOME/bin/kafka-run-class.sh
分发配置
调整 $KAFKA_HOME/config/server.properties
启动 Kafka
验证 Kafka

依赖服务

JDK 1.8.0_333
ZooKeeper 3.5.10：https://blog.csdn.net/weixin_42598916/article/details/135726572?spm=1001.2014.3001.5502

系统优化

每个节点都需进行如下优化

# 按需求更改主机名
hostname hadoop1

# 关闭 SELinux
# 将 SELINUX 值更改为 disabled
vi /etc/selinux/config
SELINUX=disabled

# 需要重启后才可生效
# 查看 SELinux 状态
getenforce

# 关闭防火墙
systemctl stop firewalld && systemctl disable firewalld && systemctl status firewalld

# 安装 Chrony 服务
yum install chrony -y

# 配置 Chrony 服务
# 注释默认的 NTP 服务地址
# 配置所需的 NTP 服务地址
vi /etc/chonry.conf
server hadoop1 iburst

# 重启 Chrony 服务并配置开机自启
systemctl enable chronyd --now

# 查看 Chrony 服务状态
chronyc sources -v
210 Number of sources = 1
.-- Source mode  '^' = server, '=' = peer, '#' = local clock.
/ .- Source state '*' = current synced, '+' = combined , '-' = not combined,
| /   '?' = unreachable, 'x' = time may be in error, '~' = time too variable.
||                                                 .- xxxx [ yyyy ] +/- zzzz
||      Reachability register (octal) -.           |  xxxx = adjusted offset,
||      Log2(Polling interval) --.      |          |  yyyy = measured offset,
||                                \     |          |  zzzz = estimated error.
||                                 |    |       
MS Name/IP address         Stratum Poll Reach LastRx Last sample
====================================================================================================================
^* hadoop1                        4   6   377    12    -28us[  -45us] +/-   75ms

# 配置免密登录
# 所有节点生成 id_rsa.pub
ssh-keygen -t rsa

# 将每个节点的 id_rsa.pub 信息，分别放入所有节点的 authorized_keys 文件内
cat id_rsa.pub >> hadoop1:/root/.ssh/authorized_keys
cat id_rsa.pub >> hadoop2:/root/.ssh/authorized_keys
cat id_rsa.pub >> hadoop3:/root/.ssh/authorized_keys

# 最终效果
cat /root/.ssh/authorized_keys
# redis-nodes
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDwuKw9LdfDO3Ln+ViNtQEqZtH/RvoFymKkexBXRUK/2XcczKHPv967KHH71L/5vPOQPUXZLZg3TPERlRTIW9MvCh0LmceGAiQHrxczx56RnYh8nESknd2jbHBToGwqgoB8xsB2IQuhze0CqvRs7A0nrbyBvnUpg/DvePTOSSgii4z9kishBCbrCPamQm20drXVDK3gQ9Q+/YJLKa3+mxzI67xfk/jby0A0DD9XKL7fflRgMK0GXEtYsJ04tKc5Bo+w6Zc8gHyryFrKD4wpeoPakqmrdzaTVYI1x5WvrAPrQplxAP8iNfBqRJSHvlDBXVeXgSxz2I4HBshsStkKp root@redis1
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDkspWeTwWoWyr6biMnefOYT4kh+7gPAboHAWe7p67IR9pfu+Rkk/vxLFDbi7X6Td9AhIXEZH6fY5BhihBzhRO/VtjE24QqnXdOLDHV1i0rSEYh6GOAbnVl/93lKidQF/2wvnQET31m1iwls3ul6aWw8/pOcxWy6kB+6MRiOExhu+0erE3jBFLcl+e0IJLKp/nLjCof/qWh3hLGVyhgMn/WmGhf7OyUbedXFqAwwS83/M60jSL1nB1lnIOoHrNSdnrN/GJVXmmwJjJAG4g4hbAg2zNind2rz6p4mq5k7iBbDUFghFwKKYsGeV0Onm7SKErFlHCJNFSOgfVNpaUYJ root@redis2
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQC+DGKAYw3tbdmv2GDsz3HEOdoKk8JVCEvDFczap2g3DoaqwEBkRag2l9IQ3RZL/WtpKe0f2vZzcm5t3d7e6YhyfEXRn1fjOmynTcykB13xAVrlRfJ6Sayur0OiPzWBktpNj8qaTKjwH+lyHGBwa5duqKiVEglEH2mX5grcOa/mH2Mo+IWsCYeCldKjfdBy2drlAim1fYvJwvtg0uDe8sfDUdDonG4phNOVaWB2u79SxKlGnGewGNuOrifIzkbc0mH9kNgrlw/xdSIqaFA738Yn/4n/kSe3BgceJ0wBowLzorgW2ogyGOdQp6MzBRlg/hxn4EDLJisrC9mSCMOOl root@redis3

# hadoop-nodes
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQCvWawSJqu4/Adnu6TjvV8rVDAqTU2CGNaSBOTDjcytHHOaY8UiwUMKvXUJugBmRkyhtWhQPHrVSmOH6+qMnHk5XQcWBmce8qCQqDoz49WwyZH95ciY/ynKR9dzAJwXN5fvJEoKxBhSJLk27SDsgRUX05IAjTN5Wx05GCNC36CRGHr6bwsC5iK+nv1ZllkRPyqoICJcvVVoJFDe+svNwLJS8bEpTUS/3C6w1RdfEgGVK0/NLnmANz6VIu5LAZqOpwFcB8Zed3wgnoHUfDCSXLEUQbcgRxDvba7lcvOqbiNh4Tr6WctSHw0UD9PSK6AXdS0jAAyjZ1J5kbWaI+vmZ root@hadoop1
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQCwCqgQWDgw7sSqNer1oONzsFhoCWBmLqdWOQCcC7RYhD6kiVzdAEP7qZwWKRwoe/E++xP0+slgxsIsXGVoObGrlT3n+g/2xsgTCaBT/6sGV7k28UOozh76GlyfJjzavbwWE9Q2yR2mkb3/ILGE6CUNCkqqLuYEDTG4DxNupGhsGSYChAcjclzYFrMxDARiOJ8cahDjVlmGzFWxNhzJ36pFC1Rdyeu4CrtZ8tkuqQagGZqB63bVmvTiOM2fY8Wp8TNv0Zz2XmFmv7IUhpDXlPZdFCviwLYLLoJ9LTG32rO/jY0U78LFdDpsYdebthztNakKMZEhCqVIR+k1VMPtp root@hadoop2
ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDHmj5qT64jSc3LCR2EBKB+12C1XxhFlc44X8zdf3mL8gbepG+ndMgBV4eombLg7QjZshCsjhk9d8esofAlrPk5tX/nWWHg3p5jYTh5/6V+iU7VDpWmMVN/87dsjBbmM9P6jTNiwqk4rdSXDKXkmrVygGHnEj95eP35Nq1JKg+GS7RjWWB0+loGQ4eYKO1nj2nYNOlNBi28CKh1uMWf42bDtcfKP3Z4gEOtPBD5rVPiU2Tq6jgtAs/VvaYGv5FHO4MB0lBE1ik8zp/4trfGU5hie/1PzCRAIvsqPEBSzeUs9nhHODj6vZYwgQupK9Qv5jEbQgh6pCGEfFZlfsC03 root@hadoop3

# 配置 OracleJDK
# 下载 Oracle JDK 并存放至指定路径内
# 配置 /etc/profile 文件
cat > /etc/profile << EOF

# Oracle JDK 1.8.0_333
export JAVA_HOME=/data/service/jdk/jdk1.8.0_333
export CLASSPATH=$:CLASSPATH:$JAVA_HOME/lib/
export PATH=$PATH:$JAVA_HOME/bin
EOF

# 刷新配置
source /etc/profile

# 查看 JDK 状态
java -version
java version "1.8.0_333"
Java(TM) SE Runtime Environment (build 1.8.0_333-b02)
Java HotSpot(TM) 64-Bit Server VM (build 25.333-b02, mixed mode)

# 配置 HOSTS 文件
cat > /etc/hosts << EOF
# redis-nodes
10.10.10.21 redis1
10.10.10.22 redis2
10.10.10.23 redis3

# hadoop-nodes
10.10.10.131 hadoop1
10.10.10.132 hadoop2
10.10.10.133 hadoop3
EOF

# 关闭 swap
swapoff -a

# 注销 swap 分区挂载
vi /etc/fstab

# 配置 vm.swapiness
echo "vm.swappiness = 0" >> /etc/sysctl.conf

# 刷新配置
sysctl -p

# 配置 transparent_hugepage
# 临时生效
echo never > /sys/kernel/mm/transparent_hugepage/enabled && echo never > /sys/kernel/mm/transparent_hugepage/defrag

# 永久生效
echo "echo never > /sys/kernel/mm/transparent_hugepage/enabled" >> /etc/rc.local && echo "echo never > /sys/kernel/mm/transparent_hugepage/defrag" >> /etc/rc.local

# 配置 最大连接数
# CentOS6 的文件名为 90-nproc.conf
# CentOS7 的文件名为 20-nproc.conf
vi /etc/security/limits.d/20-nproc.conf
* - nofile 655350
* - nproc 655350

查看 ZooKeeper 集群状态

$ZK_HOME/bin/zkCli.sh -server hadoop1:2181,hadoop2:2181,hadoop3:2181
[zk: hadoop1:2181,hadoop2:2181,hadoop3:2181(CONNECTED) 0] ls /
[admin, brokers, cluster, config, consumers, controller, controller_epoch, hadoop-ha, hbase, isr_change_notification, latest_producer_id_block, log_dir_event_notification, rmstore, spark, yarn-leader-election, zookeeper]

创建路径

所有节点都需进行创建

mkdir -p /data/service/kafka/{kafka-data,kafka-logs}

配置 /etc/profile

所有节点都需进行部署

# Kafka 2.5.0
export KAFKA_HOME=/data/service/kafka/kafka_2.12-2.5.0
export PATH=$PATH:$KAFKA_HOME/bin:$KAFKA_HOME/sbin:$KAFKA_HOME/lib

配置 $KAFKA_HOME/config/server.properties

只需在某一个节点上部署即可
配置测试成功后，推送到所有其余节点

# Kafka Broker 的唯一标识
broker.id=0

# 指定 Kafka Broker 所绑定的 IP 地址和端口号
# 默认端口号为 9092
listeners=PLAINTEXT://10.10.10.131:9092

# Kafka 数据存放路径
log.dirs=/data/service/kafka/kafka-data

# 开启删除 topic 权限
delete.topic.enable=true

# 允许非 ISR 的副本成为 Leader
unclean.leader.election.enable=true

# 指定所连接的 ZooKeeper 集群
zookeeper.connect=localhost:hadoop1:2181,hadoop2:2181,hadoop3:2181

# 指定 JVM 配置
export KAFKA_OPTS="-XX:+UseG1GC -Xmx1g -Xms1g"

# 指定处理网络请求的线程数
num.network.threads=3

# 指定处理磁盘 I/O 的线程数
num.io.threads=8

# 指定发送数据时的套接字发送缓冲区大小，单位是 byte
socket.send.buffer.bytes=102400

# 指定接收数据时的套接字接收缓冲区大小，单位是 byte
socket.receive.buffer.bytes=102400

# 指定单个请求允许的最大字节数
socket.request.max.bytes=104857600

# 指定每个主题的初始分区数
num.partitions=1

# 指定每个数据目录用于日志恢复的线程数
num.recovery.threads.per.data.dir=1

# 指定存储消费者偏移量的主题的复制因子
offsets.topic.replication.factor=1

# 指定存储事务状态的日志的复制因子
transaction.state.log.replication.factor=1

# 指定事务状态日志的最小同步副本数
transaction.state.log.min.isr=1

# 日志文件的保留时间，单位是小时
log.retention.hours=168

# 检查过期日志的频率，单位是毫秒
log.retention.check.interval.ms=300000

# 指定与 ZooKeeper 建立连接的超时时间，单位是毫秒
zookeeper.connection.timeout.ms=18000

# 指定消费者组初始平衡的延迟时间，单位是毫秒
group.initial.rebalance.delay.ms=0

配置 $KAFKA_HOME/bin/kafka-run-class.sh

调整 Kafka Log 路径

# Log directory to use
if [ "x$LOG_DIR" = "x" ]; then
  LOG_DIR="/data/service/kafka/kafka-logs"
fi

调整 Kafka JVM 路径
- 若不希望使用节点的 JDK 的版本或无法进行节点 JDK 的更新，则可以通过调整如下部分的内容，写死 JDK 路径，起到指定 JDK 版本的效果

if [ -z "$JAVA_HOME" ]; then
  JAVA="java"
else
  JAVA="$JAVA_HOME/bin/java"
fi

分发配置

scp -r /data/service/kafka root@hadoop2:/data/service/
scp -r /data/service/kafka root@hadoop3:/data/service/

调整 $KAFKA_HOME/config/server.properties

# 10.10.10.132
broker.id=1
listeners=PLAINTEXT://10.10.10.132:9092

# 10.10.10.133
broker.id=2
listeners=PLAINTEXT://10.10.10.133:9092

启动 Kafka

# 10.10.10.131
$KAFKA_HOME/bin/kafka-server-start.sh -daemon $KAFKA_HOME/config/server.properties

# 10.10.10.132
$KAFKA_HOME/bin/kafka-server-start.sh -daemon $KAFKA_HOME/config/server.properties

# 10.10.10.133
$KAFKA_HOME/bin/kafka-server-start.sh -daemon $KAFKA_HOME/config/server.properties

验证 Kafka

# 10.10.10.131
$KAFKA_HOME/bin/kafka-topics.sh --bootstrap-server hadoop1:9092 --list

# 创建 Topic test
# --topic 指定 topic 名称
# --bootstrap-server 指定 Kafka broker 节点
# --partitions 指定 topic 分区数量
# --replication-factor 指定 topic 复制因子
$KAFKA_HOME/bin/kafka-topics.sh --create --topic test --bootstrap-server hadoop1:9092 --partitions 3 --replication-factor 2

# 查看 Topic test
$KAFKA_HOME/bin/kafka-topics.sh --bootstrap-server hadoop1:9092 --describe --topic test

# 生产 Topic test 数据
# 如下命令是进入生产的交互界面，输入所需生产的数据后，按回车键完成输入
$KAFKA_HOME/bin/kafka-console-producer.sh --topic test --bootstrap-server hadoop1:9092
> a = 1

# 消费 Topic test 数据
$KAFKA_HOME/bin/kafka-console-consumer.sh --topic test --bootstrap-server hadoop1:9092 --from-beginning