Kafka環境搭建

下載下傳Kafka的release包

http://kafka.apache.org/downloads

kafka/config/zookeeper.properties配置檔案注意

# 注意此處的dataDir和dataLogDir都需要配置（否則可能會出現znode節點寫入錯誤問題）

dataDir=/Users/zhangsan/Documents/zookeeper-3.4.8/data

dataLogDir=/Users/xusijun/Documents/zookeeper-3.4.8/logs

# 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

kafka/config/server.properties配置檔案注意

broker.id=0

# 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

# A comma separated list of directories under which to store log files

log.dirs=/tmp/kafka-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 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 for to ensure availability such as 3.

offsets.topic.replication.factor=1

transaction.state.log.replication.factor=1

transaction.state.log.min.isr=1

# 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 connection string (see zookeeper docs for details).

zookeeper.connect=localhost:2181

# Timeout in ms for connecting to zookeeper

zookeeper.connection.timeout.ms=6000

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

啟動指令

> cd kafka/bin

> ./zookeeper-server-start.sh ../config/zookeeper.properties &

> ./kafka-server-start.sh ../config/server.properties &

建立topic

./kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic example