kafka配置文件记录

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

# 每一个broker在集群中的唯一表示，要求是正数。当该服务器的IP地址发生改变时，broker.id没有变化，则不会影响consumers的消息情况
broker.id=0

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

listeners=PLAINTEXT://:9092

# The port the socket server listens on
#port=9092

# Hostname the broker will bind to. If not set, the server will bind to all interfaces
#host.name=master

# 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().
#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.
#advertised.port=<port accessible by clients>

# broker处理消息的最大线程数，一般情况下不需要去修改
num.network.threads=3

# broker处理磁盘IO的线程数，数值应该大于你的硬盘数
num.io.threads=8

# socket的发送缓冲区，socket的调优参数SO_SNDBUFF
socket.send.buffer.bytes=102400

# socket的接受缓冲区，socket的调优参数SO_RCVBUFF
socket.receive.buffer.bytes=102400

# socket请求的最大数值，防止serverOOM，message.max.bytes必然要小于socket.request.max.bytes，会被topic创建时的指定参数覆盖
socket.request.max.bytes=104857600


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

# kafka数据的存放地址，多个地址的话用逗号分割 /data/kafka-logs-1，/data/kafka-logs-2
log.dirs=/tmp/kafka-logs

#每个topic的分区个数，若是在topic创建时候没有指定的话会被topic创建时的指定参数覆盖
num.partitions=2

# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
# 每个数据目录用来日志恢复的线程数目
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. 
# 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.

# 数据存储的最大时间保24*7 7 天
log.retention.hours=168

# 每个topic下每个partition保存数据的总量；注意，这是每个partitions的上限，因此这个数值乘以partitions的个数就是每个topic保存的数据总量。同时注意：如果log.retention.hours和log.retention.bytes都设置了，则超过了任何一个限制都会造成删除一个段文件。
#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

# 检查日志分段文件的间隔时间，以确定是否文件属性是否到达删除要求。
log.retention.check.interval.ms=300000

#当这个属性设置为false时，一旦日志的保存时间或者大小达到上限时，就会被删除；如果设置为true，则当保存属性达到上限时，就会进行log compaction。
log.cleaner.enable=false

############################# 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=6000

Here is our server production server configuration:
# Replication configurations
num.replica.fetchers=4
replica.fetch.max.bytes=1048576
replica.fetch.wait.max.ms=500
replica.high.watermark.checkpoint.interval.ms=5000
replica.socket.timeout.ms=30000
replica.socket.receive.buffer.bytes=65536
replica.lag.time.max.ms=10000

controller.socket.timeout.ms=30000
controller.message.queue.size=10

# Log configuration
num.partitions=8
message.max.bytes=1000000
auto.create.topics.enable=true
log.index.interval.bytes=4096
log.index.size.max.bytes=10485760
log.retention.hours=168
log.flush.interval.ms=10000
log.flush.interval.messages=20000
log.flush.scheduler.interval.ms=2000
log.roll.hours=168
log.retention.check.interval.ms=300000
log.segment.bytes=1073741824

# ZK configuration
zookeeper.connection.timeout.ms=6000
zookeeper.sync.time.ms=2000

# Socket server configuration
num.io.threads=8
num.network.threads=8
socket.request.max.bytes=104857600
socket.receive.buffer.bytes=1048576
socket.send.buffer.bytes=1048576
queued.max.requests=16
fetch.purgatory.purge.interval.requests=100
producer.purgatory.purge.interval.requests=100