Kafka Linux集群搭建及容灾演练

下载tar包，版本kafka2.12-2.6.0，放入/usr/local/share文件夹解压缩

cd /usr/local/share
#下载kafka（官网也有）
wget https://apache.osuosl.org/kafka/2.6.0/kafka_2.12-2.6.0.tgz
#解压
tar -zxvf kafka_2.12-2.6.0.tgz
cd kafka_2.12-2.6.0
#将bin目录加入PATH
echo 'export PATH=$PATH:/usr/local/share/kafka_2.12-2.6.0/bin' >> /etc/profile
#加载
source /etc/profile
#进入conf目录配置三个conf（单机单kafka则不需要这样直接配置server.properties），由于在单机所以开三个配置文件，从三个配置文件启动三个kafka
cd /usr/local/share/kafka_2.12-2.6.0/config
#先复制一个配置，等下配置好这个之后再复制两份
cp server.properties server1.properties
#编辑配置（内容在下面文本）保存退出
vi server1.properties
#讲几个重要的
#broker.id=1   Broker代理的ID 1 2 3 
#listeners=PLAINTEXT://:9092  绑定到哪个端口进行通信
#log.dirs=/tmp/kafka-logs1 日志路径
#offsets.topic.replication.factor  副本数量，建议多少个节点就多少
#zookeeper.connect=localhost:2181,localhost:2182,localhost:2183 zookeeper集群的各个节点地址（这里用一台电脑模拟三个zookeeper所以都在本地）
#再复制两份
cp server1.properties server2.properties
cp server1.properties server3.properties
#然后把复制出来的两份分别修改掉broker id，listener,log.dirs保存
#依次启动三个kafka broker
nohup kafka-server-start.sh server1.properties 1>/dev/null 2>&1 &
nohup kafka-server-start.sh server2.properties 1>/dev/null 2>&1 &
nohup kafka-server-start.sh server3.properties 1>/dev/null 2>&1 &
#创建一个topic  三份副本  
kafka-topics.sh --create --zookeeper localhost:2181,localhost:2182,localhost:2183 --replication-factor 3 --partitions 1 --topic test 
#查看一下topic
kafka-topics.sh --describe --zookeeper localhost:2181,localhost:2182,localhost:2183 --topic test
#使用kafka_test nodejs来做生产者消费者测试（见博客https://blog.csdn.net/HumorChen99/article/details/109745711）
let client=await generateKafkaConnection("192.168.108.129:9092,192.168.108.129:9093,192.168.108.129:9094")
#topic用test
#然后启动生产者消费者
#然后挂掉一个kafka，服务依然在稳定运行,demo成功

# 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.

# see kafka.server.KafkaConfig for additional details and defaults

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

# The id of the broker. This must be set to a unique integer for each broker.
broker.id=1

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

# 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://your.host.name: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=/tmp/kafka-logs1

# 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=3
transaction.state.log.replication.factor=3
transaction.state.log.min.isr=3

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

############################# 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=localhost:2181,localhost:2182,localhost:2183

# 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