一、基础配置文件（14个）
1.1、connect-console-sink.properties
name=local-console-sink
connector.class=org.apache.kafka.connect.file.FileStreamSinkConnector
tasks.max=1
topics=connect-test
1.2、connect-console-source.properties
name=local-console-source
connector.class=org.apache.kafka.connect.file.FileStreamSourceConnector
tasks.max=1
topic=connect-test
1.3、onnect-distributed.properties
# This file contains some of the configurations for the Kafka Connect distributed worker. This file is intended
# to be used with the examples, and some settings may differ from those used in a production system, especially
# the `bootstrap.servers` and those specifying replication factors.
# A list of host/port pairs to use for establishing the initial connection to the Kafka cluster.
bootstrap.servers=localhost:9092
# unique name for the cluster, used in forming the Connect cluster group. Note that this must not conflict with consumer group IDs
group.id=connect-cluster
# The converters specify the format of data in Kafka and how to translate it into Connect data. Every Connect user will
# need to configure these based on the format they want their data in when loaded from or stored into Kafka
key.converter=org.apache.kafka.connect.json.JsonConverter
value.converter=org.apache.kafka.connect.json.JsonConverter
# Converter-specific settings can be passed in by prefixing the Converter's setting with the converter we want to apply
# it to
key.converter.schemas.enable=true
value.converter.schemas.enable=true
# Topic to use for storing offsets. This topic should have many partitions and be replicated and compacted.
# Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
# the topic before starting Kafka Connect if a specific topic configuration is needed.
# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
offset.storage.topic=connect-offsets
offset.storage.replication.factor=1
#offset.storage.partitions=25
# Topic to use for storing connector and task configurations; note that this should be a single partition, highly replicated,
# and compacted topic. Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
# the topic before starting Kafka Connect if a specific topic configuration is needed.
# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
config.storage.topic=connect-configs
config.storage.replication.factor=1
# Topic to use for storing statuses. This topic can have multiple partitions and should be replicated and compacted.
# Kafka Connect will attempt to create the topic automatically when needed, but you can always manually create
# the topic before starting Kafka Connect if a specific topic configuration is needed.
# Most users will want to use the built-in default replication factor of 3 or in some cases even specify a larger value.
# Since this means there must be at least as many brokers as the maximum replication factor used, we'd like to be able
# to run this example on a single-broker cluster and so here we instead set the replication factor to 1.
status.storage.topic=connect-status
status.storage.replication.factor=1
#status.storage.partitions=5
# Flush much faster than normal, which is useful for testing/debugging
offset.flush.interval.ms=10000
# These are provided to inform the user about the presence of the REST host and port configs
# Hostname & Port for the REST API to listen on. If this is set, it will bind to the interface used to listen to requests.
#rest.host.name=
#rest.port=8083
# The Hostname & Port that will be given out to other workers to connect to i.e. URLs that are routable from other servers.
#rest.advertised.host.name=
#rest.advertised.port=
# Set to a list of filesystem paths separated by commas (,) to enable class loading isolation for plugins
# (connectors, converters, transformations). The list should consist of top level directories that include
# any combination of:
# a) directories immediately containing jars with plugins and their dependencies
# b) uber-jars with plugins and their dependencies
# c) directories immediately containing the package directory structure of classes of plugins and their dependencies
# Examples:
# plugin.path=/usr/local/share/java,/usr/local/share/kafka/plugins,/opt/connectors,
#plugin.path=
1.4、connect-file-sink.properties
name=local-file-sink
connector.class=FileStreamSink
tasks.max=1
file=test.sink.txt
topics=connect-test
1.5、connect-file-source.properties
name=local-file-source
connector.class=FileStreamSource
tasks.max=1
file=test.txt
topic=connect-test
1.6、connect-log4j.properties
log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
#
# The `%X{connector.context}` parameter in the layout includes connector-specific and task-specific information
# in the log message, where appropriate. This makes it easier to identify those log messages that apply to a
# specific connector. Simply add this parameter to the log layout configuration below to include the contextual information.
#
#log4j.appender.stdout.layout.ConversionPattern=[%d] %p %X{connector.context}%m (%c:%L)%n
log4j.appender.stdout.layout.ConversionPattern=[%d] %p %m (%c:%L)%n
log4j.logger.org.apache.zookeeper=ERROR
log4j.logger.org.I0Itec.zkclient=ERROR
log4j.logger.org.reflections=ERROR
1.7、connect-standalone.properties
# These are defaults. This file just demonstrates how to override some settings.
bootstrap.servers=localhost:9092
# The converters specify the format of data in Kafka and how to translate it into Connect data. Every Connect user will
# need to configure these based on the format they want their data in when loaded from or stored into Kafka
key.converter=org.apache.kafka.connect.json.JsonConverter
value.converter=org.apache.kafka.connect.json.JsonConverter
# Converter-specific settings can be passed in by prefixing the Converter's setting with the converter we want to apply
# it to
key.converter.schemas.enable=true
value.converter.schemas.enable=true
offset.storage.file.filename=/tmp/connect.offsets
# Flush much faster than normal, which is useful for testing/debugging
offset.flush.interval.ms=10000
# Set to a list of filesystem paths separated by commas (,) to enable class loading isolation for plugins
# (connectors, converters, transformations). The list should consist of top level directories that include
# any combination of:
# a) directories immediately containing jars with plugins and their dependencies
# b) uber-jars with plugins and their dependencies
# c) directories immediately containing the package directory structure of classes of plugins and their dependencies
# Note: symlinks will be followed to discover dependencies or plugins.
# Examples:
# plugin.path=/usr/local/share/java,/usr/local/share/kafka/plugins,/opt/connectors,
#plugin.path=
1.8、consumer.properties
# list of brokers used for bootstrapping knowledge about the rest of the cluster
# format: host1:port1,host2:port2 ...
bootstrap.servers=localhost:9092
# consumer group id
group.id=test-consumer-group
# What to do when there is no initial offset in Kafka or if the current
# offset does not exist any more on the server: latest, earliest, none
#auto.offset.reset=
1.9、log4j.properties
name=local-console-sink
connector.class=org.apache.kafka.connect.file.FileStreamSinkConnector
tasks.max=1
topics=connect-test
1.10、producer.properties
############################# Producer Basics #############################
# list of brokers used for bootstrapping knowledge about the rest of the cluster
# format: host1:port1,host2:port2 ...
bootstrap.servers=localhost:9092
# specify the compression codec for all data generated: none, gzip, snappy, lz4, zstd
compression.type=none
# name of the partitioner class for partitioning events; default partition spreads data randomly
#partitioner.class=
# the maximum amount of time the client will wait for the response of a request
#request.timeout.ms=
# how long `KafkaProducer.send` and `KafkaProducer.partitionsFor` will block for
#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
#linger.ms=
# the maximum size of a request in bytes
#max.request.size=
# the default batch size in bytes when batching multiple records sent to a partition
#batch.size=
# the total bytes of memory the producer can use to buffer records waiting to be sent to the server
#buffer.memory=
1.11、server.properties
############################# Server Basics #############################
# The id of the broker. This must be set to a unique integer for each broker.
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
#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
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=102400
# The receive buffer (SO_RCVBUF) used by the socket server
socket.receive.buffer.bytes=102400
# The maximum size of a request that the socket server will accept (protection against OOM)
socket.request.max.bytes=104857600
############################# Log Basics #############################
# A comma separated list of directories under which to store log files
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.
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.
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 for 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.
# 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=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.
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=localhost: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=0
1.12、tools-log4j.properties
log4j.rootLogger=WARN, stderr
log4j.appender.stderr=org.apache.log4j.ConsoleAppender
log4j.appender.stderr.layout=org.apache.log4j.PatternLayout
log4j.appender.stderr.layout.ConversionPattern=[%d] %p %m (%c)%n
log4j.appender.stderr.Target=System.err
1.13、trogdor.conf
{
"_comment": [
"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."
],
"platform": "org.apache.kafka.trogdor.basic.BasicPlatform", "nodes": {
"node0": {
"hostname": "localhost",
"trogdor.agent.port": 8888,
"trogdor.coordinator.port": 8889
}
}
}
1.14、zookeeper.properties
# the directory where the snapshot is stored.
dataDir=/tmp/zookeeper
# the port at which the clients will connect
clientPort=2181
# disable the per-ip limit on the number of connections since this is a non-production config
maxClientCnxns=0
二、客户端操作和常用API
三、常见问题及解决方案
