# Develop KCL 2.x Consumers
**Important**
Amazon Kinesis Client Library (KCL) versions 1.x and 2.x are outdated. KCL 1.x will reach end-of-support on January 30, 2026. We **strongly recommend** that you migrate your KCL applications using version 1.x to the latest KCL version before January 30, 2026. To find the latest KCL version, see [Amazon Kinesis Client Library page on GitHub](https://github.com/awslabs/amazon-kinesis-client). For information about the latest KCL versions, see [Use Kinesis Client Library](kcl.md). For information about migrating from KCL 1.x to KCL 3.x, see [Migrating from KCL 1.x to KCL 3.x](kcl-migration-1-3.md).
This topic shows you how to use version 2.0 of the Kinesis Client Library (KCL).
For more information about the KCL, see the overview provided in [Developing Consumers Using the Kinesis Client Library 1.x](https://docs.aws.amazon.com/streams/latest/dev/developing-consumers-with-kcl.html).
Choose from the following topics depending on the option you want to use.
**Topics**
+ [Develop a Kinesis Client Library consumer in Java](kcl2-standard-consumer-java-example.md)
+ [Develop a Kinesis Client Library consumer in Python](kcl2-standard-consumer-python-example.md)
+ [Develop enhanced fan-out consumers with KCL 2.x](building-enhanced-consumers-kcl-retired.md)
# Develop a Kinesis Client Library consumer in Java
**Important**
Amazon Kinesis Client Library (KCL) versions 1.x and 2.x are outdated. KCL 1.x will reach end-of-support on January 30, 2026. We **strongly recommend** that you migrate your KCL applications using version 1.x to the latest KCL version before January 30, 2026. To find the latest KCL version, see [Amazon Kinesis Client Library page on GitHub](https://github.com/awslabs/amazon-kinesis-client). For information about the latest KCL versions, see [Use Kinesis Client Library](kcl.md). For information about migrating from KCL 1.x to KCL 3.x, see [Migrating from KCL 1.x to KCL 3.x](kcl-migration-1-3.md).
The following code shows an example implementation in Java of `ProcessorFactory` and `RecordProcessor`. If you want to take advantage of the enhanced fan-out feature, see [Using Consumers with Enhanced Fan-Out ](https://docs.aws.amazon.com/streams/latest/dev/building-enhanced-consumers-kcl-java.html).
```
/*
* Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Amazon Software License (the "License").
* You may not use this file except in compliance with the License.
* A copy of the License is located at
*
* http://aws.amazon.com/asl/
*
* or in the "license" file accompanying this file. This file 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.
*/
/*
* Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License").
* You may not use this file except in compliance with the License.
* A copy of the License is located at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* or in the "license" file accompanying this file. This file 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.
*/
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.UUID;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.Executors;
import java.util.concurrent.Future;
import java.util.concurrent.ScheduledExecutorService;
import java.util.concurrent.ScheduledFuture;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import org.apache.commons.lang3.ObjectUtils;
import org.apache.commons.lang3.RandomStringUtils;
import org.apache.commons.lang3.RandomUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.slf4j.MDC;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.cloudwatch.CloudWatchAsyncClient;
import software.amazon.awssdk.services.dynamodb.DynamoDbAsyncClient;
import software.amazon.awssdk.services.kinesis.KinesisAsyncClient;
import software.amazon.awssdk.services.kinesis.model.PutRecordRequest;
import software.amazon.kinesis.common.ConfigsBuilder;
import software.amazon.kinesis.common.KinesisClientUtil;
import software.amazon.kinesis.coordinator.Scheduler;
import software.amazon.kinesis.exceptions.InvalidStateException;
import software.amazon.kinesis.exceptions.ShutdownException;
import software.amazon.kinesis.lifecycle.events.InitializationInput;
import software.amazon.kinesis.lifecycle.events.LeaseLostInput;
import software.amazon.kinesis.lifecycle.events.ProcessRecordsInput;
import software.amazon.kinesis.lifecycle.events.ShardEndedInput;
import software.amazon.kinesis.lifecycle.events.ShutdownRequestedInput;
import software.amazon.kinesis.processor.ShardRecordProcessor;
import software.amazon.kinesis.processor.ShardRecordProcessorFactory;
import software.amazon.kinesis.retrieval.polling.PollingConfig;
/**
* This class will run a simple app that uses the KCL to read data and uses the AWS SDK to publish data.
* Before running this program you must first create a Kinesis stream through the AWS console or AWS SDK.
*/
public class SampleSingle {
private static final Logger log = LoggerFactory.getLogger(SampleSingle.class);
/**
* Invoke the main method with 2 args: the stream name and (optionally) the region.
* Verifies valid inputs and then starts running the app.
*/
public static void main(String... args) {
if (args.length < 1) {
log.error("At a minimum, the stream name is required as the first argument. The Region may be specified as the second argument.");
System.exit(1);
}
String streamName = args[0];
String region = null;
if (args.length > 1) {
region = args[1];
}
new SampleSingle(streamName, region).run();
}
private final String streamName;
private final Region region;
private final KinesisAsyncClient kinesisClient;
/**
* Constructor sets streamName and region. It also creates a KinesisClient object to send data to Kinesis.
* This KinesisClient is used to send dummy data so that the consumer has something to read; it is also used
* indirectly by the KCL to handle the consumption of the data.
*/
private SampleSingle(String streamName, String region) {
this.streamName = streamName;
this.region = Region.of(ObjectUtils.firstNonNull(region, "us-east-2"));
this.kinesisClient = KinesisClientUtil.createKinesisAsyncClient(KinesisAsyncClient.builder().region(this.region));
}
private void run() {
/**
* Sends dummy data to Kinesis. Not relevant to consuming the data with the KCL
*/
ScheduledExecutorService producerExecutor = Executors.newSingleThreadScheduledExecutor();
ScheduledFuture producerFuture = producerExecutor.scheduleAtFixedRate(this::publishRecord, 10, 1, TimeUnit.SECONDS);
/**
* Sets up configuration for the KCL, including DynamoDB and CloudWatch dependencies. The final argument, a
* ShardRecordProcessorFactory, is where the logic for record processing lives, and is located in a private
* class below.
*/
DynamoDbAsyncClient dynamoClient = DynamoDbAsyncClient.builder().region(region).build();
CloudWatchAsyncClient cloudWatchClient = CloudWatchAsyncClient.builder().region(region).build();
ConfigsBuilder configsBuilder = new ConfigsBuilder(streamName, streamName, kinesisClient, dynamoClient, cloudWatchClient, UUID.randomUUID().toString(), new SampleRecordProcessorFactory());
/**
* The Scheduler (also called Worker in earlier versions of the KCL) is the entry point to the KCL. This
* instance is configured with defaults provided by the ConfigsBuilder.
*/
Scheduler scheduler = new Scheduler(
configsBuilder.checkpointConfig(),
configsBuilder.coordinatorConfig(),
configsBuilder.leaseManagementConfig(),
configsBuilder.lifecycleConfig(),
configsBuilder.metricsConfig(),
configsBuilder.processorConfig(),
configsBuilder.retrievalConfig().retrievalSpecificConfig(new PollingConfig(streamName, kinesisClient))
);
/**
* Kickoff the Scheduler. Record processing of the stream of dummy data will continue indefinitely
* until an exit is triggered.
*/
Thread schedulerThread = new Thread(scheduler);
schedulerThread.setDaemon(true);
schedulerThread.start();
/**
* Allows termination of app by pressing Enter.
*/
System.out.println("Press enter to shutdown");
BufferedReader reader = new BufferedReader(new InputStreamReader(System.in));
try {
reader.readLine();
} catch (IOException ioex) {
log.error("Caught exception while waiting for confirm. Shutting down.", ioex);
}
/**
* Stops sending dummy data.
*/
log.info("Cancelling producer and shutting down executor.");
producerFuture.cancel(true);
producerExecutor.shutdownNow();
/**
* Stops consuming data. Finishes processing the current batch of data already received from Kinesis
* before shutting down.
*/
Future gracefulShutdownFuture = scheduler.startGracefulShutdown();
log.info("Waiting up to 20 seconds for shutdown to complete.");
try {
gracefulShutdownFuture.get(20, TimeUnit.SECONDS);
} catch (InterruptedException e) {
log.info("Interrupted while waiting for graceful shutdown. Continuing.");
} catch (ExecutionException e) {
log.error("Exception while executing graceful shutdown.", e);
} catch (TimeoutException e) {
log.error("Timeout while waiting for shutdown. Scheduler may not have exited.");
}
log.info("Completed, shutting down now.");
}
/**
* Sends a single record of dummy data to Kinesis.
*/
private void publishRecord() {
PutRecordRequest request = PutRecordRequest.builder()
.partitionKey(RandomStringUtils.randomAlphabetic(5, 20))
.streamName(streamName)
.data(SdkBytes.fromByteArray(RandomUtils.nextBytes(10)))
.build();
try {
kinesisClient.putRecord(request).get();
} catch (InterruptedException e) {
log.info("Interrupted, assuming shutdown.");
} catch (ExecutionException e) {
log.error("Exception while sending data to Kinesis. Will try again next cycle.", e);
}
}
private static class SampleRecordProcessorFactory implements ShardRecordProcessorFactory {
public ShardRecordProcessor shardRecordProcessor() {
return new SampleRecordProcessor();
}
}
/**
* The implementation of the ShardRecordProcessor interface is where the heart of the record processing logic lives.
* In this example all we do to 'process' is log info about the records.
*/
private static class SampleRecordProcessor implements ShardRecordProcessor {
private static final String SHARD_ID_MDC_KEY = "ShardId";
private static final Logger log = LoggerFactory.getLogger(SampleRecordProcessor.class);
private String shardId;
/**
* Invoked by the KCL before data records are delivered to the ShardRecordProcessor instance (via
* processRecords). In this example we do nothing except some logging.
*
* @param initializationInput Provides information related to initialization.
*/
public void initialize(InitializationInput initializationInput) {
shardId = initializationInput.shardId();
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Initializing @ Sequence: {}", initializationInput.extendedSequenceNumber());
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
/**
* Handles record processing logic. The Amazon Kinesis Client Library will invoke this method to deliver
* data records to the application. In this example we simply log our records.
*
* @param processRecordsInput Provides the records to be processed as well as information and capabilities
* related to them (e.g. checkpointing).
*/
public void processRecords(ProcessRecordsInput processRecordsInput) {
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Processing {} record(s)", processRecordsInput.records().size());
processRecordsInput.records().forEach(r -> log.info("Processing record pk: {} -- Seq: {}", r.partitionKey(), r.sequenceNumber()));
} catch (Throwable t) {
log.error("Caught throwable while processing records. Aborting.");
Runtime.getRuntime().halt(1);
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
/** Called when the lease tied to this record processor has been lost. Once the lease has been lost,
* the record processor can no longer checkpoint.
*
* @param leaseLostInput Provides access to functions and data related to the loss of the lease.
*/
public void leaseLost(LeaseLostInput leaseLostInput) {
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Lost lease, so terminating.");
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
/**
* Called when all data on this shard has been processed. Checkpointing must occur in the method for record
* processing to be considered complete; an exception will be thrown otherwise.
*
* @param shardEndedInput Provides access to a checkpointer method for completing processing of the shard.
*/
public void shardEnded(ShardEndedInput shardEndedInput) {
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Reached shard end checkpointing.");
shardEndedInput.checkpointer().checkpoint();
} catch (ShutdownException | InvalidStateException e) {
log.error("Exception while checkpointing at shard end. Giving up.", e);
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
/**
* Invoked when Scheduler has been requested to shut down (i.e. we decide to stop running the app by pressing
* Enter). Checkpoints and logs the data a final time.
*
* @param shutdownRequestedInput Provides access to a checkpointer, allowing a record processor to checkpoint
* before the shutdown is completed.
*/
public void shutdownRequested(ShutdownRequestedInput shutdownRequestedInput) {
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Scheduler is shutting down, checkpointing.");
shutdownRequestedInput.checkpointer().checkpoint();
} catch (ShutdownException | InvalidStateException e) {
log.error("Exception while checkpointing at requested shutdown. Giving up.", e);
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
}
}
```
# Develop a Kinesis Client Library consumer in Python
**Important**
Amazon Kinesis Client Library (KCL) versions 1.x and 2.x are outdated. KCL 1.x will reach end-of-support on January 30, 2026. We **strongly recommend** that you migrate your KCL applications using version 1.x to the latest KCL version before January 30, 2026. To find the latest KCL version, see [Amazon Kinesis Client Library page on GitHub](https://github.com/awslabs/amazon-kinesis-client). For information about the latest KCL versions, see [Use Kinesis Client Library](kcl.md). For information about migrating from KCL 1.x to KCL 3.x, see [Migrating from KCL 1.x to KCL 3.x](kcl-migration-1-3.md).
You can use the Kinesis Client Library (KCL) to build applications that process data from your Kinesis data streams. The Kinesis Client Library is available in multiple languages. This topic discusses Python.
The KCL is a Java library; support for languages other than Java is provided using a multi-language interface called the *MultiLangDaemon*. This daemon is Java-based and runs in the background when you are using a KCL language other than Java. Therefore, if you install the KCL for Python and write your consumer app entirely in Python, you still need Java installed on your system because of the MultiLangDaemon. Further, MultiLangDaemon has some default settings you may need to customize for your use case, for example, the AWS Region that it connects to. For more information about the MultiLangDaemon on GitHub, go to the [KCL MultiLangDaemon project](https://github.com/awslabs/amazon-kinesis-client/tree/v1.x/src/main/java/com/amazonaws/services/kinesis/multilang) page.
To download the Python KCL from GitHub, go to [Kinesis Client Library (Python)](https://github.com/awslabs/amazon-kinesis-client-python). To download sample code for a Python KCL consumer application, go to the [KCL for Python sample project](https://github.com/awslabs/amazon-kinesis-client-python/tree/master/samples) page on GitHub.
You must complete the following tasks when implementing a KCL consumer application in Python:
**Topics**
+ [Implement the RecordProcessor class methods](#kinesis-record-processor-implementation-interface-py)
+ [Modify the configuration properties](#kinesis-record-processor-initialization-py)
## Implement the RecordProcessor class methods
The `RecordProcess` class must extend the `RecordProcessorBase` class to implement the following methods:
```
initialize
process_records
shutdown_requested
```
This sample provides implementations that you can use as a starting point.
```
#!/usr/bin/env python
# Copyright 2014-2015 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Amazon Software License (the "License").
# You may not use this file except in compliance with the License.
# A copy of the License is located at
#
# http://aws.amazon.com/asl/
#
# or in the "license" file accompanying this file. This file 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.
from __future__ import print_function
import sys
import time
from amazon_kclpy import kcl
from amazon_kclpy.v3 import processor
class RecordProcessor(processor.RecordProcessorBase):
"""
A RecordProcessor processes data from a shard in a stream. Its methods will be called with this pattern:
* initialize will be called once
* process_records will be called zero or more times
* shutdown will be called if this MultiLangDaemon instance loses the lease to this shard, or the shard ends due
a scaling change.
"""
def __init__(self):
self._SLEEP_SECONDS = 5
self._CHECKPOINT_RETRIES = 5
self._CHECKPOINT_FREQ_SECONDS = 60
self._largest_seq = (None, None)
self._largest_sub_seq = None
self._last_checkpoint_time = None
def log(self, message):
sys.stderr.write(message)
def initialize(self, initialize_input):
"""
Called once by a KCLProcess before any calls to process_records
:param amazon_kclpy.messages.InitializeInput initialize_input: Information about the lease that this record
processor has been assigned.
"""
self._largest_seq = (None, None)
self._last_checkpoint_time = time.time()
def checkpoint(self, checkpointer, sequence_number=None, sub_sequence_number=None):
"""
Checkpoints with retries on retryable exceptions.
:param amazon_kclpy.kcl.Checkpointer checkpointer: the checkpointer provided to either process_records
or shutdown
:param str or None sequence_number: the sequence number to checkpoint at.
:param int or None sub_sequence_number: the sub sequence number to checkpoint at.
"""
for n in range(0, self._CHECKPOINT_RETRIES):
try:
checkpointer.checkpoint(sequence_number, sub_sequence_number)
return
except kcl.CheckpointError as e:
if 'ShutdownException' == e.value:
#
# A ShutdownException indicates that this record processor should be shutdown. This is due to
# some failover event, e.g. another MultiLangDaemon has taken the lease for this shard.
#
print('Encountered shutdown exception, skipping checkpoint')
return
elif 'ThrottlingException' == e.value:
#
# A ThrottlingException indicates that one of our dependencies is is over burdened, e.g. too many
# dynamo writes. We will sleep temporarily to let it recover.
#
if self._CHECKPOINT_RETRIES - 1 == n:
sys.stderr.write('Failed to checkpoint after {n} attempts, giving up.\n'.format(n=n))
return
else:
print('Was throttled while checkpointing, will attempt again in {s} seconds'
.format(s=self._SLEEP_SECONDS))
elif 'InvalidStateException' == e.value:
sys.stderr.write('MultiLangDaemon reported an invalid state while checkpointing.\n')
else: # Some other error
sys.stderr.write('Encountered an error while checkpointing, error was {e}.\n'.format(e=e))
time.sleep(self._SLEEP_SECONDS)
def process_record(self, data, partition_key, sequence_number, sub_sequence_number):
"""
Called for each record that is passed to process_records.
:param str data: The blob of data that was contained in the record.
:param str partition_key: The key associated with this recod.
:param int sequence_number: The sequence number associated with this record.
:param int sub_sequence_number: the sub sequence number associated with this record.
"""
####################################
# Insert your processing logic here
####################################
self.log("Record (Partition Key: {pk}, Sequence Number: {seq}, Subsequence Number: {sseq}, Data Size: {ds}"
.format(pk=partition_key, seq=sequence_number, sseq=sub_sequence_number, ds=len(data)))
def should_update_sequence(self, sequence_number, sub_sequence_number):
"""
Determines whether a new larger sequence number is available
:param int sequence_number: the sequence number from the current record
:param int sub_sequence_number: the sub sequence number from the current record
:return boolean: true if the largest sequence should be updated, false otherwise
"""
return self._largest_seq == (None, None) or sequence_number > self._largest_seq[0] or \
(sequence_number == self._largest_seq[0] and sub_sequence_number > self._largest_seq[1])
def process_records(self, process_records_input):
"""
Called by a KCLProcess with a list of records to be processed and a checkpointer which accepts sequence numbers
from the records to indicate where in the stream to checkpoint.
:param amazon_kclpy.messages.ProcessRecordsInput process_records_input: the records, and metadata about the
records.
"""
try:
for record in process_records_input.records:
data = record.binary_data
seq = int(record.sequence_number)
sub_seq = record.sub_sequence_number
key = record.partition_key
self.process_record(data, key, seq, sub_seq)
if self.should_update_sequence(seq, sub_seq):
self._largest_seq = (seq, sub_seq)
#
# Checkpoints every self._CHECKPOINT_FREQ_SECONDS seconds
#
if time.time() - self._last_checkpoint_time > self._CHECKPOINT_FREQ_SECONDS:
self.checkpoint(process_records_input.checkpointer, str(self._largest_seq[0]), self._largest_seq[1])
self._last_checkpoint_time = time.time()
except Exception as e:
self.log("Encountered an exception while processing records. Exception was {e}\n".format(e=e))
def lease_lost(self, lease_lost_input):
self.log("Lease has been lost")
def shard_ended(self, shard_ended_input):
self.log("Shard has ended checkpointing")
shard_ended_input.checkpointer.checkpoint()
def shutdown_requested(self, shutdown_requested_input):
self.log("Shutdown has been requested, checkpointing.")
shutdown_requested_input.checkpointer.checkpoint()
if __name__ == "__main__":
kcl_process = kcl.KCLProcess(RecordProcessor())
kcl_process.run()
```
## Modify the configuration properties
The sample provides default values for the configuration properties, as shown in the following script. You can override any of these properties with your own values.
```
# The script that abides by the multi-language protocol. This script will
# be executed by the MultiLangDaemon, which will communicate with this script
# over STDIN and STDOUT according to the multi-language protocol.
executableName = sample_kclpy_app.py
# The name of an Amazon Kinesis stream to process.
streamName = words
# Used by the KCL as the name of this application. Will be used as the name
# of an Amazon DynamoDB table which will store the lease and checkpoint
# information for workers with this application name
applicationName = PythonKCLSample
# Users can change the credentials provider the KCL will use to retrieve credentials.
# The DefaultAWSCredentialsProviderChain checks several other providers, which is
# described here:
# http://docs.aws.amazon.com/AWSJavaSDK/latest/javadoc/com/amazonaws/auth/DefaultAWSCredentialsProviderChain.html
AWSCredentialsProvider = DefaultAWSCredentialsProviderChain
# Appended to the user agent of the KCL. Does not impact the functionality of the
# KCL in any other way.
processingLanguage = python/2.7
# Valid options at TRIM_HORIZON or LATEST.
# See http://docs.aws.amazon.com/kinesis/latest/APIReference/API_GetShardIterator.html#API_GetShardIterator_RequestSyntax
initialPositionInStream = TRIM_HORIZON
# The following properties are also available for configuring the KCL Worker that is created
# by the MultiLangDaemon.
# The KCL defaults to us-east-1
#regionName = us-east-1
# Fail over time in milliseconds. A worker which does not renew it's lease within this time interval
# will be regarded as having problems and it's shards will be assigned to other workers.
# For applications that have a large number of shards, this msy be set to a higher number to reduce
# the number of DynamoDB IOPS required for tracking leases
#failoverTimeMillis = 10000
# A worker id that uniquely identifies this worker among all workers using the same applicationName
# If this isn't provided a MultiLangDaemon instance will assign a unique workerId to itself.
#workerId =
# Shard sync interval in milliseconds - e.g. wait for this long between shard sync tasks.
#shardSyncIntervalMillis = 60000
# Max records to fetch from Kinesis in a single GetRecords call.
#maxRecords = 10000
# Idle time between record reads in milliseconds.
#idleTimeBetweenReadsInMillis = 1000
# Enables applications flush/checkpoint (if they have some data "in progress", but don't get new data for while)
#callProcessRecordsEvenForEmptyRecordList = false
# Interval in milliseconds between polling to check for parent shard completion.
# Polling frequently will take up more DynamoDB IOPS (when there are leases for shards waiting on
# completion of parent shards).
#parentShardPollIntervalMillis = 10000
# Cleanup leases upon shards completion (don't wait until they expire in Kinesis).
# Keeping leases takes some tracking/resources (e.g. they need to be renewed, assigned), so by default we try
# to delete the ones we don't need any longer.
#cleanupLeasesUponShardCompletion = true
# Backoff time in milliseconds for Amazon Kinesis Client Library tasks (in the event of failures).
#taskBackoffTimeMillis = 500
# Buffer metrics for at most this long before publishing to CloudWatch.
#metricsBufferTimeMillis = 10000
# Buffer at most this many metrics before publishing to CloudWatch.
#metricsMaxQueueSize = 10000
# KCL will validate client provided sequence numbers with a call to Amazon Kinesis before checkpointing for calls
# to RecordProcessorCheckpointer#checkpoint(String) by default.
#validateSequenceNumberBeforeCheckpointing = true
# The maximum number of active threads for the MultiLangDaemon to permit.
# If a value is provided then a FixedThreadPool is used with the maximum
# active threads set to the provided value. If a non-positive integer or no
# value is provided a CachedThreadPool is used.
#maxActiveThreads = 0
```
### Application name
The KCL requires an application name that is unique among your applications and among Amazon DynamoDB tables in the same Region. It uses the application name configuration value in the following ways:
+ All workers that are associated with this application name are assumed to be working together on the same stream. These workers can be distributed across multiple instances. If you run an additional instance of the same application code, but with a different application name, the KCL treats the second instance as an entirely separate application that is also operating on the same stream.
+ The KCL creates a DynamoDB table with the application name and uses the table to maintain state information (such as checkpoints and worker-shard mapping) for the application. Each application has its own DynamoDB table. For more information, see [Use a lease table to track the shards processed by the KCL consumer application](shared-throughput-kcl-consumers.md#shared-throughput-kcl-consumers-leasetable).
### Credentials
You must make your AWS credentials available to one of the credential providers in the [default credential providers chain](https://docs.aws.amazon.com/sdk-for-java/latest/reference/com/amazonaws/auth/DefaultAWSCredentialsProviderChain.html). You can you use the `AWSCredentialsProvider` property to set a credentials provider. If you run your consumer application on an Amazon EC2 instance, we recommend that you configure the instance with an IAM role. AWS credentials that reflect the permissions associated with this IAM role are made available to applications on the instance through its instance metadata. This is the most secure way to manage credentials for a consumer application running on an EC2 instance.
# Develop enhanced fan-out consumers with KCL 2.x
**Important**
Amazon Kinesis Client Library (KCL) versions 1.x and 2.x are outdated. KCL 1.x will reach end-of-support on January 30, 2026. We **strongly recommend** that you migrate your KCL applications using version 1.x to the latest KCL version before January 30, 2026. To find the latest KCL version, see [Amazon Kinesis Client Library page on GitHub](https://github.com/awslabs/amazon-kinesis-client). For information about the latest KCL versions, see [Use Kinesis Client Library](kcl.md). For information about migrating from KCL 1.x to KCL 3.x, see [Migrating from KCL 1.x to KCL 3.x](kcl-migration-1-3.md).
Consumers that use *enhanced fan-out* in Amazon Kinesis Data Streams can receive records from a data stream with dedicated throughput of up to 2 MB of data per second per shard. This type of consumer doesn't have to contend with other consumers that are receiving data from the stream. For more information, see [Develop enhanced fan-out consumers with dedicated throughput](enhanced-consumers.md).
You can use version 2.0 or later of the Kinesis Client Library (KCL) to develop applications that use enhanced fan-out to receive data from streams. The KCL automatically subscribes your application to all the shards of a stream, and ensures that your consumer application can read with a throughput value of 2 MB/sec per shard. If you want to use the KCL without turning on enhanced fan-out, see [Developing Consumers Using the Kinesis Client Library 2.0](https://docs.aws.amazon.com/streams/latest/dev/developing-consumers-with-kcl-v2.html).
**Topics**
+ [Develop enhanced fan-out consumers using KCL 2.x in Java](building-enhanced-consumers-kcl-java.md)
# Develop enhanced fan-out consumers using KCL 2.x in Java
**Important**
Amazon Kinesis Client Library (KCL) versions 1.x and 2.x are outdated. KCL 1.x will reach end-of-support on January 30, 2026. We **strongly recommend** that you migrate your KCL applications using version 1.x to the latest KCL version before January 30, 2026. To find the latest KCL version, see [Amazon Kinesis Client Library page on GitHub](https://github.com/awslabs/amazon-kinesis-client). For information about the latest KCL versions, see [Use Kinesis Client Library](kcl.md). For information about migrating from KCL 1.x to KCL 3.x, see [Migrating from KCL 1.x to KCL 3.x](kcl-migration-1-3.md).
You can use version 2.0 or later of the Kinesis Client Library (KCL) to develop applications in Amazon Kinesis Data Streams to receive data from streams using enhanced fan-out. The following code shows an example implementation in Java of `ProcessorFactory` and `RecordProcessor`.
It is recommended that you use `KinesisClientUtil` to create `KinesisAsyncClient` and to configure `maxConcurrency` in `KinesisAsyncClient`.
**Important**
The Amazon Kinesis Client might see significantly increased latency, unless you configure `KinesisAsyncClient` to have a `maxConcurrency` high enough to allow all leases plus additional usages of `KinesisAsyncClient`.
```
/*
* Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Amazon Software License (the "License").
* You may not use this file except in compliance with the License.
* A copy of the License is located at
*
* http://aws.amazon.com/asl/
*
* or in the "license" file accompanying this file. This file 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.
*/
/*
* Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License").
* You may not use this file except in compliance with the License.
* A copy of the License is located at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* or in the "license" file accompanying this file. This file 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.
*/
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.UUID;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.Executors;
import java.util.concurrent.Future;
import java.util.concurrent.ScheduledExecutorService;
import java.util.concurrent.ScheduledFuture;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import org.apache.commons.lang3.ObjectUtils;
import org.apache.commons.lang3.RandomStringUtils;
import org.apache.commons.lang3.RandomUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.slf4j.MDC;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.cloudwatch.CloudWatchAsyncClient;
import software.amazon.awssdk.services.dynamodb.DynamoDbAsyncClient;
import software.amazon.awssdk.services.kinesis.KinesisAsyncClient;
import software.amazon.awssdk.services.kinesis.model.PutRecordRequest;
import software.amazon.kinesis.common.ConfigsBuilder;
import software.amazon.kinesis.common.KinesisClientUtil;
import software.amazon.kinesis.coordinator.Scheduler;
import software.amazon.kinesis.exceptions.InvalidStateException;
import software.amazon.kinesis.exceptions.ShutdownException;
import software.amazon.kinesis.lifecycle.events.InitializationInput;
import software.amazon.kinesis.lifecycle.events.LeaseLostInput;
import software.amazon.kinesis.lifecycle.events.ProcessRecordsInput;
import software.amazon.kinesis.lifecycle.events.ShardEndedInput;
import software.amazon.kinesis.lifecycle.events.ShutdownRequestedInput;
import software.amazon.kinesis.processor.ShardRecordProcessor;
import software.amazon.kinesis.processor.ShardRecordProcessorFactory;
public class SampleSingle {
private static final Logger log = LoggerFactory.getLogger(SampleSingle.class);
public static void main(String... args) {
if (args.length < 1) {
log.error("At a minimum, the stream name is required as the first argument. The Region may be specified as the second argument.");
System.exit(1);
}
String streamName = args[0];
String region = null;
if (args.length > 1) {
region = args[1];
}
new SampleSingle(streamName, region).run();
}
private final String streamName;
private final Region region;
private final KinesisAsyncClient kinesisClient;
private SampleSingle(String streamName, String region) {
this.streamName = streamName;
this.region = Region.of(ObjectUtils.firstNonNull(region, "us-east-2"));
this.kinesisClient = KinesisClientUtil.createKinesisAsyncClient(KinesisAsyncClient.builder().region(this.region));
}
private void run() {
ScheduledExecutorService producerExecutor = Executors.newSingleThreadScheduledExecutor();
ScheduledFuture producerFuture = producerExecutor.scheduleAtFixedRate(this::publishRecord, 10, 1, TimeUnit.SECONDS);
DynamoDbAsyncClient dynamoClient = DynamoDbAsyncClient.builder().region(region).build();
CloudWatchAsyncClient cloudWatchClient = CloudWatchAsyncClient.builder().region(region).build();
ConfigsBuilder configsBuilder = new ConfigsBuilder(streamName, streamName, kinesisClient, dynamoClient, cloudWatchClient, UUID.randomUUID().toString(), new SampleRecordProcessorFactory());
Scheduler scheduler = new Scheduler(
configsBuilder.checkpointConfig(),
configsBuilder.coordinatorConfig(),
configsBuilder.leaseManagementConfig(),
configsBuilder.lifecycleConfig(),
configsBuilder.metricsConfig(),
configsBuilder.processorConfig(),
configsBuilder.retrievalConfig()
);
Thread schedulerThread = new Thread(scheduler);
schedulerThread.setDaemon(true);
schedulerThread.start();
System.out.println("Press enter to shutdown");
BufferedReader reader = new BufferedReader(new InputStreamReader(System.in));
try {
reader.readLine();
} catch (IOException ioex) {
log.error("Caught exception while waiting for confirm. Shutting down.", ioex);
}
log.info("Cancelling producer, and shutting down executor.");
producerFuture.cancel(true);
producerExecutor.shutdownNow();
Future gracefulShutdownFuture = scheduler.startGracefulShutdown();
log.info("Waiting up to 20 seconds for shutdown to complete.");
try {
gracefulShutdownFuture.get(20, TimeUnit.SECONDS);
} catch (InterruptedException e) {
log.info("Interrupted while waiting for graceful shutdown. Continuing.");
} catch (ExecutionException e) {
log.error("Exception while executing graceful shutdown.", e);
} catch (TimeoutException e) {
log.error("Timeout while waiting for shutdown. Scheduler may not have exited.");
}
log.info("Completed, shutting down now.");
}
private void publishRecord() {
PutRecordRequest request = PutRecordRequest.builder()
.partitionKey(RandomStringUtils.randomAlphabetic(5, 20))
.streamName(streamName)
.data(SdkBytes.fromByteArray(RandomUtils.nextBytes(10)))
.build();
try {
kinesisClient.putRecord(request).get();
} catch (InterruptedException e) {
log.info("Interrupted, assuming shutdown.");
} catch (ExecutionException e) {
log.error("Exception while sending data to Kinesis. Will try again next cycle.", e);
}
}
private static class SampleRecordProcessorFactory implements ShardRecordProcessorFactory {
public ShardRecordProcessor shardRecordProcessor() {
return new SampleRecordProcessor();
}
}
private static class SampleRecordProcessor implements ShardRecordProcessor {
private static final String SHARD_ID_MDC_KEY = "ShardId";
private static final Logger log = LoggerFactory.getLogger(SampleRecordProcessor.class);
private String shardId;
public void initialize(InitializationInput initializationInput) {
shardId = initializationInput.shardId();
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Initializing @ Sequence: {}", initializationInput.extendedSequenceNumber());
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
public void processRecords(ProcessRecordsInput processRecordsInput) {
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Processing {} record(s)", processRecordsInput.records().size());
processRecordsInput.records().forEach(r -> log.info("Processing record pk: {} -- Seq: {}", r.partitionKey(), r.sequenceNumber()));
} catch (Throwable t) {
log.error("Caught throwable while processing records. Aborting.");
Runtime.getRuntime().halt(1);
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
public void leaseLost(LeaseLostInput leaseLostInput) {
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Lost lease, so terminating.");
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
public void shardEnded(ShardEndedInput shardEndedInput) {
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Reached shard end checkpointing.");
shardEndedInput.checkpointer().checkpoint();
} catch (ShutdownException | InvalidStateException e) {
log.error("Exception while checkpointing at shard end. Giving up.", e);
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
public void shutdownRequested(ShutdownRequestedInput shutdownRequestedInput) {
MDC.put(SHARD_ID_MDC_KEY, shardId);
try {
log.info("Scheduler is shutting down, checkpointing.");
shutdownRequestedInput.checkpointer().checkpoint();
} catch (ShutdownException | InvalidStateException e) {
log.error("Exception while checkpointing at requested shutdown. Giving up.", e);
} finally {
MDC.remove(SHARD_ID_MDC_KEY);
}
}
}
}
```