Kafka配置文件server.properties（0.X版本到2.X版本）

前言

其實每個版本都有些許改動，只不過改動大小而已，但是網上的教程都真的太老了，其實更新一下也費不了多少時間

 0.9.0

# 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.
# 節點的ID，必須與其它節點不同
broker.id=0

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

listeners=PLAINTEXT://:9092

# The port the socket server listens on
# 監聽端口
#port=9092

# Hostname the broker will bind to. If not set, the server will bind to all interfaces
# 節點需要綁定的主機名稱。如果沒有設置，服務器會綁定到所有接口
#host.name=localhost

# Hostname the broker will advertise to producers and consumers. If not set, it uses the
# value for "host.name" if configured.  Otherwise, it will use the value returned from
# java.net.InetAddress.getCanonicalHostName().
# 節點的主機名會通知給生產者和消費者。如果沒有設置，它將會使用"host.name"的值（前提是設置了host.name）。
# 否則他會使用java.net.InetAddress.getCanonicalHostName()的返回值
#advertised.host.name=<hostname routable by clients>

# The port to publish to ZooKeeper for clients to use. If this is not set,
# it will publish the same port that the broker binds to.
# 這個端口將暴露給Zookeeper以供客戶端來使用。如果沒有設置，將會暴露節點綁定的端口
#advertised.port=<port accessible by clients>

# The number of threads handling network requests
# 接受網絡請求的線程數
num.network.threads=3

# The number of threads doing disk I/O、
# 進行磁盤IO的線程數
num.io.threads=8

# The send buffer (SO_SNDBUF) used by the socket server
# 套接字服務器使用的發送緩沖區大小
socket.send.buffer.bytes=102400

# The receive buffer (SO_RCVBUF) used by the socket server
# 套接字服務器使用的接收緩沖區大小
socket.receive.buffer.bytes=102400

# The maximum size of a request that the socket server will accept (protection against OOM)
# 單個請求最大能接收的數據量
socket.request.max.bytes=104857600


############################# Log Basics #############################

# A comma seperated list of directories under which to store log files
# 一個逗號分隔的目錄列表，用來存儲日志文件
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.
# 每個主題的日志分區的默認數量。更多的分區允許更大的並行操作，但是它會導致節點產生更多的文件
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.
# 每個數據目錄中的線程數，用於在啟動時日志恢復，並在關閉時刷新。
num.recovery.threads.per.data.dir=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.
# 消息直接被寫入文件系統，但是默認情況下我們僅僅調用fsync()以延遲的同步系統緩存
# There are a few important trade-offs here:
# 這些有一些重要的權衡
#    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.
#    1. 持久性:如果不使用復制，未刷新的數據可能會丟失。
#    2. 延遲:非常大的刷新間隔可能會在刷新時導致延遲，因為將會有大量數據刷新。
#    3. 吞吐量:刷新通常是最昂貴的操作，而一個小的刷新間隔可能會導致過多的搜索。
# 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.
# 下面的設置允許你去配置刷新策略，每隔一段時間刷新或者一次N個消息（或者兩個都配置）。這可以在全局范圍內完成，並在每個主題的基礎上重寫。

# The number of messages to accept before forcing a flush of data to disk
# 在強制刷新數據到磁盤執勤啊允許接收消息的數量
#log.flush.interval.messages=10000

# The maximum amount of time a message can sit in a log before we force a flush
# 在強制刷新之前，消息可以在日志中停留的最長時間
#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.
# 以下的配置控制了日志段的處理。策略可以配置為每隔一段時間刪除片段或者到達一定大小之后。
# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
# from the end of the log.
# 當滿足這些條件時，將會刪除一個片段。刪除總是發生在日志的末尾。

# The minimum age of a log file to be eligible for deletion
# 一個日志的最小存活時間，可以被刪除
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.
# 一個基於大小的日志保留策略。段將被從日志中刪除只要剩下的部分段不低於log.retention.bytes。
#log.retention.bytes=1073741824

# The maximum size of a log segment file. When this size is reached a new log segment will be created.
# 每一個日志段大小的最大值。當到達這個大小時，會生成一個新的片段。
log.segment.bytes=1073741824

# The interval at which log segments are checked to see if they can be deleted according
# to the retention policies
# 檢查日志段的時間間隔，看是否可以根據保留策略刪除它們
log.retention.check.interval.ms=300000

############################# Zookeeper #############################

# Zookeeper connection string (see zookeeper docs for details).
# Zookeeper連接字符串（具體見Zookeeper文檔）
# This is a comma separated host:port pairs, each corresponding to a zk
# 這是一個以逗號為分割的部分，每一個都匹配一個Zookeeper
# 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.
# 您還可以將一個可選的chroot字符串附加到url，以指定所有kafka znode的根目錄。
zookeeper.connect=localhost:2181

# Timeout in ms for connecting to zookeeper
# 連接到Zookeeper的超時時間
zookeeper.connection.timeout.ms=6000

 

 0.10.1

# 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.
# 節點的ID，必須與其它節點不同
broker.id=0

# Switch to enable topic deletion or not, default value is false
# 選擇啟用刪除主題功能，默認false
#delete.topic.enable=true

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

# The address the socket server listens on. It will get the value returned from 
# java.net.InetAddress.getCanonicalHostName() if not configured.
# 套接字服務器堅挺的地址。如果沒有配置，就使用java.net.InetAddress.getCanonicalHostName()的返回值
#   FORMAT:格式：
#     listeners = security_protocol://host_name:port
#   EXAMPLE:例子：
#     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().
# 節點的主機名會通知給生產者和消費者。如果沒有設置，如果配置了"listeners"就使用"listeners"的值。
# 否則就使用java.net.InetAddress.getCanonicalHostName()的返回值
#advertised.listeners=PLAINTEXT://your.host.name:9092

# The number of threads handling network requests
# 接受網絡請求的線程數
num.network.threads=3

# The number of threads doing disk I/O
# 進行磁盤IO的線程數
num.io.threads=8

# The send buffer (SO_SNDBUF) used by the socket server
# 套接字服務器使用的發送緩沖區大小
socket.send.buffer.bytes=102400

# The receive buffer (SO_RCVBUF) used by the socket server
# 套接字服務器使用的接收緩沖區大小
socket.receive.buffer.bytes=102400

# The maximum size of a request that the socket server will accept (protection against OOM)
# 單個請求最大能接收的數據量
socket.request.max.bytes=104857600


############################# Log Basics #############################

# A comma seperated list of directories under which to store log files
# 一個逗號分隔的目錄列表，用來存儲日志文件
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.
# 每個主題的日志分區的默認數量。更多的分區允許更大的並行操作，但是它會導致節點產生更多的文件
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.
# 每個數據目錄中的線程數，用於在啟動時日志恢復，並在關閉時刷新。
num.recovery.threads.per.data.dir=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.
# 消息直接被寫入文件系統，但是默認情況下我們僅僅調用fsync()以延遲的同步系統緩存
# There are a few important trade-offs here:
# 這些有一些重要的權衡
#    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.
#    1. 持久性:如果不使用復制，未刷新的數據可能會丟失。
#    2. 延遲:非常大的刷新間隔可能會在刷新時導致延遲，因為將會有大量數據刷新。
#    3. 吞吐量:刷新通常是最昂貴的操作，而一個小的刷新間隔可能會導致過多的搜索。
# 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.
# 下面的設置允許你去配置刷新策略，每隔一段時間刷新或者一次N個消息（或者兩個都配置）。這可以在全局范圍內完成，並在每個主題的基礎上重寫。

# The number of messages to accept before forcing a flush of data to disk
# 在強制刷新數據到磁盤之前允許接收消息的數量
#log.flush.interval.messages=10000

# The maximum amount of time a message can sit in a log before we force a flush
# 在強制刷新之前，消息可以在日志中停留的最長時間
#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.
# 以下的配置控制了日志段的處理。策略可以配置為每隔一段時間刪除片段或者到達一定大小之后。
# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
# from the end of the log.
# 當滿足這些條件時，將會刪除一個片段。刪除總是發生在日志的末尾。

# The minimum age of a log file to be eligible for deletion
# 一個日志的最小存活時間，可以被刪除
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.
# 一個基於大小的日志保留策略。段將被從日志中刪除只要剩下的部分段不低於log.retention.bytes。
#log.retention.bytes=1073741824

# The maximum size of a log segment file. When this size is reached a new log segment will be created.
# 每一個日志段大小的最大值。當到達這個大小時，會生成一個新的片段。
log.segment.bytes=1073741824

# The interval at which log segments are checked to see if they can be deleted according
# to the retention policies
# 檢查日志段的時間間隔，看是否可以根據保留策略刪除它們
log.retention.check.interval.ms=300000

############################# Zookeeper #############################

# Zookeeper connection string (see zookeeper docs for details).
# Zookeeper連接字符串（具體見Zookeeper文檔）
# This is a comma separated host:port pairs, each corresponding to a zk
# 這是一個以逗號為分割的部分，每一個都匹配一個Zookeeper
# 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.
# 您還可以將一個可選的chroot字符串附加到url，以指定所有kafka znode的根目錄。
zookeeper.connect=localhost:2181

# Timeout in ms for connecting to zookeeper
# 連接到Zookeeper的超時時間
zookeeper.connection.timeout.ms=6000

 

0.11.0

 

# 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.
# 節點的ID，必須與其它節點不同
broker.id=0

# Switch to enable topic deletion or not, default value is false
# 選擇啟用刪除主題功能，默認false
#delete.topic.enable=true

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

# The address the socket server listens on. It will get the value returned from 
# java.net.InetAddress.getCanonicalHostName() if not configured.
# 套接字服務器堅挺的地址。如果沒有配置，就使用java.net.InetAddress.getCanonicalHostName()的返回值
#   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().
# 節點的主機名會通知給生產者和消費者。如果沒有設置，如果配置了"listeners"就使用"listeners"的值。
# 否則就使用java.net.InetAddress.getCanonicalHostName()的返回值
#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
# 將偵聽器的名稱映射到安全協議，默認情況下它們是相同的。有關詳細信息，請參閱配置文檔
#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
# 服務器用來接受請求或者發送響應的線程數
num.network.threads=3

# The number of threads that the server uses for processing requests, which may include disk I/O
# 服務器用來處理請求的線程數，可能包括磁盤IO
num.io.threads=8

# The send buffer (SO_SNDBUF) used by the socket server
# 套接字服務器使用的發送緩沖區大小
socket.send.buffer.bytes=102400

# The receive buffer (SO_RCVBUF) used by the socket server
# 套接字服務器使用的接收緩沖區大小
socket.receive.buffer.bytes=102400

# The maximum size of a request that the socket server will accept (protection against OOM)
# 單個請求最大能接收的數據量
socket.request.max.bytes=104857600


############################# Log Basics #############################

# A comma seperated list of directories under which to store log files
# 一個逗號分隔的目錄列表，用來存儲日志文件
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.
# 每個主題的日志分區的默認數量。更多的分區允許更大的並行操作，但是它會導致節點產生更多的文件
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.
# 每個數據目錄中的線程數，用於在啟動時日志恢復，並在關閉時刷新。
num.recovery.threads.per.data.dir=1

############################# Internal Topic Settings  #############################
# 內部主題設置
# 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.
# 對於除了開發測試之外的其他任何東西，group元數據內部主題的復制因子“__consumer_offsets”和“__transaction_state”，建議值大於1，以確保可用性(如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.
# 消息直接被寫入文件系統，但是默認情況下我們僅僅調用fsync()以延遲的同步系統緩存
# There are a few important trade-offs here:
# 這些有一些重要的權衡
#    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.
#    1. 持久性:如果不使用復制，未刷新的數據可能會丟失。
#    2. 延遲:非常大的刷新間隔可能會在刷新時導致延遲，因為將會有大量數據刷新。
#    3. 吞吐量:刷新通常是最昂貴的操作，而一個小的刷新間隔可能會導致過多的搜索。
# 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.
# 下面的設置允許你去配置刷新策略，每隔一段時間刷新或者一次N個消息（或者兩個都配置）。這可以在全局范圍內完成，並在每個主題的基礎上重寫。

# The number of messages to accept before forcing a flush of data to disk
# 在強制刷新數據到磁盤之前允許接收消息的數量
#log.flush.interval.messages=10000

# The maximum amount of time a message can sit in a log before we force a flush
# 在強制刷新之前，消息可以在日志中停留的最長時間
#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.
# 以下的配置控制了日志段的處理。策略可以配置為每隔一段時間刪除片段或者到達一定大小之后。
# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
# from the end of the log.
# 當滿足這些條件時，將會刪除一個片段。刪除總是發生在日志的末尾。

# The minimum age of a log file to be eligible for deletion
# 一個日志的最小存活時間，可以被刪除
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.
# 一個基於大小的日志保留策略。段將被從日志中刪除只要剩下的部分段不低於log.retention.bytes。
#log.retention.bytes=1073741824

# The maximum size of a log segment file. When this size is reached a new log segment will be created.
# 每一個日志段大小的最大值。當到達這個大小時，會生成一個新的片段。
log.segment.bytes=1073741824

# The interval at which log segments are checked to see if they can be deleted according
# to the retention policies
# 檢查日志段的時間間隔，看是否可以根據保留策略刪除它們
log.retention.check.interval.ms=300000

############################# Zookeeper #############################

# Zookeeper connection string (see zookeeper docs for details).
# Zookeeper連接字符串（具體見Zookeeper文檔）
# This is a comma separated host:port pairs, each corresponding to a zk
# 這是一個以逗號為分割的部分，每一個都匹配一個Zookeeper
# 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.
# 您還可以將一個可選的chroot字符串附加到url，以指定所有kafka znode的根目錄。
zookeeper.connect=localhost:2181

# Timeout in ms for connecting to zookeeper
# 連接到Zookeeper的超時時間
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

 

小結

可以看出，目前最新版本的配置文件沒有了

#port=9092

#host.name=localhost

#advertised.host.name=<hostname routable by clients>

#advertised.port=<port accessible by clients>

 

取而代之的是

#listeners=PLAINTEXT://:9092

#advertised.listeners=PLAINTEXT://your.host.name:9092

 

並且新增了一些配置，以及有些地方注釋的說明更詳細。

=====================2020.4.15更新=====================

1.1.1、2.0.0、2.1.1、2.2.0、2.3.0、2.4.1

# 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. # 節點的ID，必須與其它節點不同
broker.id=0

############################# 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 # 套接字服務器監聽的地址。如果沒有配置，就使用java.net.InetAddress.getCanonicalHostName()的返回值
#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 # 接受網絡請求的線程數
num.network.threads=3

# The number of threads that the server uses for processing requests, which may include disk I/O # 進行磁盤IO的線程數
num.io.threads=8 # The send buffer (SO_SNDBUF) used by the socket server # 套接字服務器使用的發送緩沖區大小
socket.send.buffer.bytes=102400 # The receive buffer (SO_RCVBUF) used by the socket server # 套接字服務器使用的接收緩沖區大小
socket.receive.buffer.bytes=102400 # The maximum size of a request that the socket server will accept (protection against OOM) # 單個請求最大能接收的數據量
socket.request.max.bytes=104857600 ############################# Log Basics ############################# # A comma separated list of directories under which to store log files # 一個逗號分隔的目錄列表，用來存儲日志文件
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. # 每個主題的日志分區的默認數量。更多的分區允許更大的並行操作，但是它會導致節點產生更多的文件
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. # 每個數據目錄中的線程數，用於在啟動時日志恢復，並在關閉時刷新。
num.recovery.threads.per.data.dir=1

############################# Internal Topic Settings  #############################
# The replication factor for the group metadata internal topics "__consumer_offsets" and "__transaction_state"
# 內部主題“_consumer_offsets”和“_transaction_state”的復制因子
# For anything other than development testing, a value greater than 1 is recommended for to ensure availability such as 3. # 對於開發測試以外的任何情況，建議使用大於1的值來確保可用性，比如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.
# 消息直接被寫入文件系統，但是默認情況下我們僅僅調用fsync()以延遲的同步系統緩存
# There are a few important trade-offs here:
# 這些有一些重要的權衡
#    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.
#    1. 持久性:如果不使用復制，未刷新的數據可能會丟失。
#    2. 延遲:非常大的刷新間隔可能會在刷新時導致延遲，因為將會有大量數據刷新。
#    3. 吞吐量:刷新通常是最昂貴的操作，而一個小的刷新間隔可能會導致過多的搜索。 # 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. # 下面的設置允許你去配置刷新策略，每隔一段時間刷新或者一次N個消息（或者兩個都配置）。這可以在全局范圍內完成，並在每個主題的基礎上重寫。 # The number of messages to accept before forcing a flush of data to disk # 在強制刷新數據到磁盤之前允許接收消息的數量
#log.flush.interval.messages=10000 # The maximum amount of time a message can sit in a log before we force a flush # 在強制刷新之前，消息可以在日志中停留的最長時間
#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. # 以下的配置控制了日志段的處理。策略可以配置為每隔一段時間刪除片段或者到達一定大小之后。 # A segment will be deleted whenever *either* of these criteria are met. Deletion always happens # from the end of the log. # 當滿足這些條件時，將會刪除一個片段。刪除總是發生在日志的末尾。 # The minimum age of a log file to be eligible for deletion due to age # 一個日志的最小存活時間
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. # 一個基於大小的日志保留策略。只要剩下的部分不低於log.retention.bytes，段將從日志中刪除。
#log.retention.bytes=1073741824 # The maximum size of a log segment file. When this size is reached a new log segment will be created. # 每一個日志段大小的最大值。當到達這個大小時，會生成一個新的片段。
log.segment.bytes=1073741824 # The interval at which log segments are checked to see if they can be deleted according # to the retention policies # 檢查日志段的時間間隔，看是否可以根據保留策略刪除它們
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.
# 配置zookeeper地址，多個以逗號分隔，還可以在最后指定kafka存儲的namespace：eg："127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002/kafka"
zookeeper.connect=localhost:2181 # Timeout in ms for connecting to zookeeper # 連接到Zookeeper的超時時間
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.
# 指定GroupCoordinator延遲初始消費者再平衡的時間(以毫秒為單位)
# 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.
# 默認值是3秒
# 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. # 在生產環境中，3秒的默認值更合適
group.initial.rebalance.delay.ms=0

更多詳細配置見官網：http://kafka.apache.org/documentation/#configuration

 

生產端配置

# 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 org.apache.kafka.clients.producer.ProducerConfig for more details

############################# Producer Basics #############################

# list of brokers used for bootstrapping knowledge about the rest of the cluster
# format: host1:port1,host2:port2 ...
bootstrap.servers=localhost:9092 # 指定數據壓縮格式：none、gzip、snappy、lz4、zstd
compression.type=none

# name of the partitioner class for partitioning events; default partition spreads data randomly
# 分區策略，默認隨機
#partitioner.class= # the maximum amount of time the client will wait for the response of a request # 客戶端等待請求響應的最大時間，即在向 producer 發送 ack 之前，broker允許等待的最大時間
#request.timeout.ms= # how long `KafkaProducer.send` and `KafkaProducer.partitionsFor` will block for # `KafkaProducer.send` and `KafkaProducer.partitionsFor`阻塞的時間
#max.block.ms= # the producer will wait for up to the given delay to allow other records to be sent so that the sends can be batched together # 生產者將等待一個延遲，以便和其他的消息組合成一個批次發出，減少發送的請求數
#linger.ms= # the maximum size of a request in bytes # 請求的最大字節數
#max.request.size= # the default batch size in bytes when batching multiple records sent to a partition # 在批處理消息發送到一個分區的多個記錄時的批處理大小，默認16k
#batch.size= # the total bytes of memory the producer can use to buffer records waiting to be sent to the server # 生產者可以用來緩存消息的緩沖區大小
#buffer.memory= # 以下是默認配置文件沒有的：更多 http://kafka.apache.org/documentation/#producerconfigs

# 在請求完成之前，生產者要求leader已收到確認消息的數量。 # 0：生產者不會等待服務器的ack響應，不保證服務器收到消息，返回的偏移量總是-1
# 1：leader將消息寫入本地日志，但不會管其他follower是否寫入。
# all：leader和所有的follower都成功同步消息才會返回ack，保證消息不會丟失。all等價於-1.
acks=