作者：尹正杰
版权声明：原创作品，谢绝转载！否则将追究法律责任。
一.默认kafka配置文件内容（[yinzhengjie@s101 ~]$ more /soft/kafka/config/server.properties ）
[yinzhengjie@s101 ~]$ more /soft/kafka/config/server.properties
# 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= ############################# 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://s101:9092 # 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= # The number of threads that the server uses for processing requests, which may include disk I/O
num.io.threads= # The send buffer (SO_SNDBUF) used by the socket server
socket.send.buffer.bytes= # The receive buffer (SO_RCVBUF) used by the socket server
socket.receive.buffer.bytes= # The maximum size of a request that the socket server will accept (protection against OOM)
socket.request.max.bytes= ############################# Log Basics ############################# # A comma separated list of directories under which to store log files
log.dirs=/home/yinzhengjie/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= # 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= ############################# 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 is recommended for to ensure availability such as .
offsets.topic.replication.factor=
transaction.state.log.replication.factor=
transaction.state.log.min.isr= ############################# 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:
# . Durability: Unflushed data may be lost if you are not using replication.
# . 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.
# . 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= # The maximum amount of time a message can sit in a log before we force a flush
#log.flush.interval.ms= ############################# 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= # 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= # The maximum size of a log segment file. When this size is reached a new log segment will be created.
log.segment.bytes= # 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= ############################# 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=s102:,s103:,s104: # Timeout in ms for connecting to zookeeper
zookeeper.connection.timeout.ms= ############################# 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 seconds.
# We override this to here as it makes for a better out-of-the-box experience for development and testing.
# However, in production environments the default value of seconds is more suitable as this will help to avoid unnecessary, and potentially expensive, rebalances during application st
artup.
group.initial.rebalance.delay.ms=
[yinzhengjie@s101 ~]$
二.Kafka常用参数
1>.broker.id
答：是Kafka节点服务的唯一身份标识（和zookeeper的myid类似），，如果多台kafka节点的broker.id重复的话，那仅有一个节点可以正常提供服务。
2>.listeners=PLAINTEXT://s101:9092
答：listeners 表示监听端口，PLAINTEXT表示纯文本（也就是说，不管你发送什么数据类型都以纯文本的方式接收，包括图片，视频等等，只不过接收过来再打开的话可能会是乱码！），s101:9092表示的主机名和端口号。
3>.num.network.threads=3
答：默认的网络线程数是3。
4>.num.io.threads=8
答：默认的I/O线程是8。
5>.socket.send.buffer.bytes=102400
答：默认的套接字发送缓冲是100K。
6>.socket.receive.buffer.bytes=102400
答：默认的tao-jiezi接受缓冲是100k。
7>.socket.request.max.bytes=104857600
答：默认接收到的最大字节数是100M。
8>.log.dirs=/home/yinzhengjie/kafka/logs
答：指定存放kafka的真实数据。我这里把真实的数据存在“/home/yinzhengjie/kafka/logs”。
9>.num.partitions=1
答：默认的分区数是1。
10>.num.recovery.threads.per.data.dir=1
答：每一个文件夹默认的恢复线程是1。
11>.log.retention.hours=168
答：默认数据保存时间是168小时，即一个星期（7天）。
12>.log.segment.bytes=1073741824
答：指定每个数据日志保存最大数据为1G，当超过这个值时，会自动进行日志滚动。
13>.log.retention.check.interval.ms=300000
答：每隔300秒（即5分钟）检查日志是否过期，如果数据超过了存货日期（默认7天），就会在删除log中对应的数据。
14>.zookeeper.connect=s102:2181,s103:2181,s104:2181
答：指定zookeeper服务器，如果有多个，需要用逗号分隔。
15>.zookeeper.connection.timeout.ms=6000
答：设置zookeeper的连接超时时间（默认为6秒），如果到达这个指定时间仍然连接不上的话就默认该节点已经挂掉！
16>.
三.
