mansu · February 4, 2022 23:21
diff --git a/kafka-server.properties b/kafka-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=0

 # Switch to enable topic deletion or not, default value is false.
 # Topics can now only be deleted via
 delete.topic.enable=false

 # As our clusters grow in size, we would like to have more control of topic allocation and broker placement. Enabling automatic topic  creation takes away this control. Further, topics are also 
 # created during metadata fetch requests. So, a fat fingered script can accientally create topics and cause issues. So, we should disable it in our clusters. 
 auto.create.topics.enable=false

 # The default replication factor for automatically created topics.
 default.replication.factor=3

 # Number of threads used to replicate messages from leaders.
 # Increasing this value can increase the degree of I/O parallelism in the follower broker.
 num.replica.fetchers=4

 # Minimum bytes expected for each fetch response. If not enough bytes, wait up to replicaMaxWaitTimeMs
 # Default 1
 replica.fetch.min.bytes=65536

 # The socket receive buffer for network requests.
 # Default 65536
 replica.socket.receive.buffer.bytes=1048576

 # max wait time for each fetcher request issued by follower replicas.
 # This value should always be less than the replica.lag.time.max.ms at all times
 # to prevent frequent shrinking of ISR for low throughput topics.
 # Default 500
 replica.fetch.wait.max.ms=5000

 # If a follower hasn't sent any fetch requests or hasn't consumed up to the leaders log end offset 
 # for at least this time, the leader will remove the follower from isr.
 # Default 10000
 replica.lag.time.max.ms=10000

 # The socket timeout for network requests. Its value should be at least replica.fetch.wait.max.ms.
 # Default 30000
 replica.socket.timeout.ms=30000

 # The largest record batch size allowed by Kafka.
 # If this is increased and there are consumers older than 0.10.2,
 # the consumers' fetch size must also be increased so that the they can fetch record batches this large.
 message.max.bytes = 1000000

 # migrate any partitions the server is the leader for to other replicas prior to shutting down
 controlled.shutdown.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.
 #   FORMAT:
 #     listeners = listener_name://host_name:port
 #   EXAMPLE:
 #     listeners = PLAINTEXT://your.host.name:9092
 listeners=PLAINTEXT://0.0.0.0:9092

 # 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=3

 # The number of threads that the server uses for processing requests, which may include disk I/O
 num.io.threads=8

 # The send buffer (SO_SNDBUF) used by the socket server
 socket.send.buffer.bytes=1048576

 # The receive buffer (SO_RCVBUF) used by the socket server
 socket.receive.buffer.bytes=1048576

 # 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
 log.dirs=/your/kafka/partitions

 # 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=8

 # 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=6

 ############################# 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 for to ensure availability such as 3.
 offsets.topic.replication.factor=3
 # TODO: these are for only-once semantics; factor of 1 is for dev environment
 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 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
 log.retention.hours=48

 # 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.
 #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

 # 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=zkhost1:2181,zkhost2:2181,zkhost3:2181,zkhost4:2181,zkhost5:2181

 # Timeout in ms for connecting to zookeeper
 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=3000

 metric.reporters=com.linkedin.kafka.cruisecontrol.metricsreporter.CruiseControlMetricsReporter

 # The rack awareness feature spreads replicas of the same partition across different racks.
 # This extends the guarantees Kafka provides for broker-failure to cover rack-failure,
 # limiting the risk of data loss should all the brokers on a rack fail at once.
 broker.rack=<we partition by availability zone>

 # Enables auto leader balancing. A background thread checks and triggers leader balance if required at regular intervals
 auto.leader.rebalance.enable=false

 # this is a very controversial setting, events and jq are OK with this, but it can lead to data losss
 # This flag was turned on in previous versions of Kafka since we ran with Replication factor of 2. 
 # In Kafka 2.0, we want to run the cluster with RF=3.
 # So, this flag should be turned off.
 # This flag should only be turned on when the Kafka cluster is being brought up form an inconsistent state.
 unclean.leader.election.enable=false


 # Leader imbalance settings
 # The ratio of leader imbalance allowed per broker. The controller would trigger a leader balance if it goes above this value per broker. The value is specified in percentage.	
 leader.imbalance.per.broker.percentage=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.
	#broker.id=0

	# Switch to enable topic deletion or not, default value is false.
	# Topics can now only be deleted via
	delete.topic.enable=false

	# As our clusters grow in size, we would like to have more control of topic allocation and broker placement. Enabling automatic topic creation takes away this control. Further, topics are also
	# created during metadata fetch requests. So, a fat fingered script can accientally create topics and cause issues. So, we should disable it in our clusters.
	auto.create.topics.enable=false

	# The default replication factor for automatically created topics.
	default.replication.factor=3

	# Number of threads used to replicate messages from leaders.
	# Increasing this value can increase the degree of I/O parallelism in the follower broker.
	num.replica.fetchers=4

	# Minimum bytes expected for each fetch response. If not enough bytes, wait up to replicaMaxWaitTimeMs
	# Default 1
	replica.fetch.min.bytes=65536

	# The socket receive buffer for network requests.
	# Default 65536
	replica.socket.receive.buffer.bytes=1048576

	# max wait time for each fetcher request issued by follower replicas.
	# This value should always be less than the replica.lag.time.max.ms at all times
	# to prevent frequent shrinking of ISR for low throughput topics.
	# Default 500
	replica.fetch.wait.max.ms=5000

	# If a follower hasn't sent any fetch requests or hasn't consumed up to the leaders log end offset
	# for at least this time, the leader will remove the follower from isr.
	# Default 10000
	replica.lag.time.max.ms=10000

	# The socket timeout for network requests. Its value should be at least replica.fetch.wait.max.ms.
	# Default 30000
	replica.socket.timeout.ms=30000

	# The largest record batch size allowed by Kafka.
	# If this is increased and there are consumers older than 0.10.2,
	# the consumers' fetch size must also be increased so that the they can fetch record batches this large.
	message.max.bytes = 1000000

	# migrate any partitions the server is the leader for to other replicas prior to shutting down
	controlled.shutdown.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.
	# FORMAT:
	# listeners = listener_name://host_name:port
	# EXAMPLE:
	# listeners = PLAINTEXT://your.host.name:9092
	listeners=PLAINTEXT://0.0.0.0:9092

	# 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=3

	# The number of threads that the server uses for processing requests, which may include disk I/O
	num.io.threads=8

	# The send buffer (SO_SNDBUF) used by the socket server
	socket.send.buffer.bytes=1048576

	# The receive buffer (SO_RCVBUF) used by the socket server
	socket.receive.buffer.bytes=1048576

	# 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
	log.dirs=/your/kafka/partitions

	# 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=8

	# 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=6

	############################# 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 for to ensure availability such as 3.
	offsets.topic.replication.factor=3
	# TODO: these are for only-once semantics; factor of 1 is for dev environment
	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 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
	log.retention.hours=48

	# 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.
	#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

	# 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=zkhost1:2181,zkhost2:2181,zkhost3:2181,zkhost4:2181,zkhost5:2181

	# Timeout in ms for connecting to zookeeper
	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=3000

	metric.reporters=com.linkedin.kafka.cruisecontrol.metricsreporter.CruiseControlMetricsReporter

	# The rack awareness feature spreads replicas of the same partition across different racks.
	# This extends the guarantees Kafka provides for broker-failure to cover rack-failure,
	# limiting the risk of data loss should all the brokers on a rack fail at once.
	broker.rack=<we partition by availability zone>

	# Enables auto leader balancing. A background thread checks and triggers leader balance if required at regular intervals
	auto.leader.rebalance.enable=false

	# this is a very controversial setting, events and jq are OK with this, but it can lead to data losss
	# This flag was turned on in previous versions of Kafka since we ran with Replication factor of 2.
	# In Kafka 2.0, we want to run the cluster with RF=3.
	# So, this flag should be turned off.
	# This flag should only be turned on when the Kafka cluster is being brought up form an inconsistent state.
	unclean.leader.election.enable=false


	# Leader imbalance settings
	# The ratio of leader imbalance allowed per broker. The controller would trigger a leader balance if it goes above this value per broker. The value is specified in percentage.
	leader.imbalance.per.broker.percentage=0