Kafka 配置解读

# see kafka.server.KafkaConfig for additional details and defaults
############################# Server Basics #############################
broker.id=0 #集群唯一
# 是否允许topic删除的开关,默认false
#delete.topic.enable=true
############################# Socket Server Settings #############################
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 handling network requests
num.network.threads=3
# The number of threads doing 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 seperated list of directories under which to store log files
# 存放日志片段,如果指定了多个路径[逗号分隔],broker会根据最少使用原则
# 把同一个分区的日志片段保存到同一路径下,broker会往拥有最少
# 数目分区的路径新增分区,而不是最小磁盘空间
log.dirs=/usr/local/ww/kafka_2.11-0.10.2.1/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.
# 新创建的主题的分区数,可以增加主题的分区个数,但不能减少,因此,如果需要
# 主题的分区数小于num.partitions的值,需要手动创建该主题
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.
# 每个日志目录使用的线程数量[默认1],总的线程数量= N * log.dirs的数量
# 服务器正常启动-打开日志片段,
# 服务器崩溃后重启-用于检查和截断每个分区的日志片段
# 服务器正常关闭-关闭日志片段
num.recovery.threads.per.data.dir=4
############################# 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 exceessive 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
# 数据保留默认一周[hours/minutes/ms],
# 通过检查磁盘上日志片段文件的最后修改时间[日志片段关闭时间]来实现
log.retention.hours=168
# A size-based retention policy for logs. Segments are pruned from the log as long as the remaining
# segments don't drop below log.retention.bytes. Functions independently of log.retention.hours.
# 通过保留的消息的字节数[默认1GB]判断消息是否过期,作用在分区上
# 如果一个主题包含2个分区,那么该主题最多可以保持2GB的数据
# 如果增加该主题的分区,那么该主题可以保留的数据也随之增加
log.retention.bytes=1073741824
# The maximum size of a log segment file. When this size is reached a new log segment will be created.
# 消息到达broker时,他们被追加到分区的当前日志片段上,当日志片段
# 达到log.segment.bytes的上限时,当前日志片段就会被关闭,一个新的
# 日志片段被打开,如果一个日志片段被关闭,就开始等待过期
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=master:2181,slave1:2181,slave2:2181/chroot
# Timeout in ms for connecting to zookeeper
zookeeper.connection.timeout.ms=6000