kafka配置详解

# 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.

#
# This configuration file is intended for use in ZK-based mode, where Apache ZooKeeper is required.
# 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.
# 服务器标识必须为每个代理设置一个唯一的整数
broker.id=0

############################# Socket Server Settings #############################

# 套接字服务器配置
# The address the socket server listens on. If not configured, the host name will be equal to the value of
# java.net.InetAddress.getCanonicalHostName(), with PLAINTEXT listener name, and port 9092.
#   FORMAT:
#     listeners = listener_name://host_name:port
#   EXAMPLE:
#     listeners = PLAINTEXT://your.host.name:9092
#listeners=PLAINTEXT://:9092

# Listener name, hostname and port the broker will advertise to clients.
# If not set, it uses the value for "listeners".
#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
# 服务器用于接收来自网络的请求并向网络发送响应的线程数
num.network.threads=3

# The number of threads that the server uses for processing requests, which may include disk I/O
# 服务器用于处理请求的线程数，可能包括磁盘I / O.  默认是 8
num.io.threads=8

# The send buffer (SO_SNDBUF) used by the socket server
# 套接字服务器使用的发送缓冲区（SO_SNDBUF）
socket.send.buffer.bytes=102400

# The receive buffer (SO_RCVBUF) used by the socket server
# 套接字服务器使用的接收缓冲区（SO_SNDBUF）
socket.receive.buffer.bytes=102400

# The maximum size of a request that the socket server will accept (protection against OOM)
# 套接字服务器将接受的请求的最大大小（防止OOM）
socket.request.max.bytes=104857600


#############################  Log Basics  #############################
############################# 日志基础配置 #############################
# A comma separated list of directories under which to store log files
# 逗号分隔的目录列表，用于存储日志文件
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.
# 每个主题的默认日志分区数。更多分区允许更大，但这也会导致更多的文件，默认几个broker几个分区
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.
# 在启动时用于日志恢复和在关闭时刷新的每个数据目录的线程数。
# 对于数据目录位于RAID阵列中的安装，建议增加此值。
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=1
transaction.state.log.replication.factor=1
transaction.state.log.min.isr=1

############################# 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.
# 消息立即写入文件系统，但默认情况下我们只有fsync（）才能同步
# 懒惰的操作系统缓存。以下配置控制将数据刷新到磁盘。
# 这里有一些重要的权衡：
# 1.持久性：如果您不使用复制，则可能会丢失未刷新的数据。
# 2.延迟：当刷新确实发生时，非常大的刷新间隔可能会导致延迟峰值，因为会有大量数据需要刷新。
# 3.吞吐量：冲洗通常是最昂贵的操作，并且小的冲洗间隔可能导致过多的搜索。
# 以下设置允许配置刷新策略以在一段时间后刷新数据或
# 每N条消息（或两者）。这可以在全局范围内完成，并在每个主题的基础上进行覆盖。

# 强制刷新数据到磁盘之前要接受的消息数
#log.flush.interval.messages=10000

# The maximum amount of time a message can sit in a log before we force a flush
# 强制刷新之前消息可以在日志中停留的最长时间
#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
# segment文件保留的最长时间，默认保留7天（168小时），
# 超时将被删除，也就是说7天之前的数据将被清理掉。
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.
# 日志文件中每个segment的大小，默认为1G
log.segment.bytes=1073741824

# The interval at which log segments are checked to see if they can be deleted according
# to the retention policies
#上面的参数设置了每一个segment文件的大小是1G，那么就需要有一个东西去定期检查segment文件有没有达到1G，多长时间去检查一次，就需要设置一个周期性检查文件大小的时间（单位是毫秒）
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

# 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