对比下config/connect-distributed.properties和config/connect-standalone.properties
cat config/connect-distributed.properties |grep -v "^#" |grep -v "^$" && \
echo "#############################" && \
cat config/connect-standalone.properties |grep -v "^#" |grep -v "^$"
bootstrap.servers=localhost:9092
group.id=connect-cluster
key.converter=org.apache.kafka.connect.json.JsonConverter
value.converter=org.apache.kafka.connect.json.JsonConverter
key.converter.schemas.enable=true
value.converter.schemas.enable=true
offset.storage.topic=connect-offsets
offset.storage.replication.factor=1
config.storage.topic=connect-configs
config.storage.replication.factor=1
status.storage.topic=connect-status
status.storage.replication.factor=1
offset.flush.interval.ms=10000
#############################
bootstrap.servers=localhost:9092
key.converter=org.apache.kafka.connect.json.JsonConverter
value.converter=org.apache.kafka.connect.json.JsonConverter
key.converter.schemas.enable=true
value.converter.schemas.enable=true
offset.storage.file.filename=/tmp/connect.offsets
offset.flush.interval.ms=10000
connect-distributed三个topic
# 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
手工创建connect-distributed三个topic
(
./bin/kafka-topics.sh --create --topic connect-offsets --bootstrap-server 192.168.6.222:9092 --config cleanup.policy=compact --partitions 10 --replication-factor 3
./bin/kafka-topics.sh --create --topic connect-configs --bootstrap-server 192.168.6.222:9092 --config cleanup.policy=compact --partitions 1 --replication-factor 3
./bin/kafka-topics.sh --create --topic connect-status --bootstrap-server 192.168.6.222:9092 --config cleanup.policy=compact --partitions 10 --replication-factor 3
)
ref
使用 Kafka Connect 将数据从 Apache Kafka 引入 Azure Cosmos DB for Apache Cassandra