KTable not updating (immediately) when new messages are put on input stream - apache-kafka

I have a kafka topic of Strings with an arbitrary key. I want to create a topic of characters in string : value pairs, e.g:
input("key","value") -> outputs (["v","value"],["a","value"],...)
To keep it simple, my input topic has a single partition, and thus the KTable code should be receiving all messages to a single instance.
I have created the following sandbox code, which builds the new table just fine , but doesn't update when a new item is put into the original topic:
import java.util.LinkedHashSet;
import java.util.Properties;
import java.util.Set;
import java.util.concurrent.TimeUnit;
import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerConfig;
import org.apache.kafka.clients.producer.ProducerRecord;
import org.apache.kafka.common.serialization.Serdes;
import org.apache.kafka.common.serialization.StringSerializer;
import org.apache.kafka.common.utils.Bytes;
import org.apache.kafka.streams.KafkaStreams;
import org.apache.kafka.streams.KeyValue;
import org.apache.kafka.streams.StoreQueryParameters;
import org.apache.kafka.streams.StreamsBuilder;
import org.apache.kafka.streams.StreamsConfig;
import org.apache.kafka.streams.kstream.Consumed;
import org.apache.kafka.streams.kstream.Grouped;
import org.apache.kafka.streams.kstream.Materialized;
import org.apache.kafka.streams.state.KeyValueIterator;
import org.apache.kafka.streams.state.KeyValueStore;
import org.apache.kafka.streams.state.QueryableStoreTypes;
import org.apache.kafka.streams.state.ReadOnlyKeyValueStore;
public class Sandbox
{
private final static String kafkaBootstrapServers = "192.168.1.254:9092";
private final static String kafkaGlobalTablesDirectory = "C:\\Kafka\\tmp\\kafka-streams-global-tables\\";
private final static String topic = "sandbox";
private static KafkaStreams streams;
public static void main(String[] args)
{
// 1. set up the test data
Properties producerProperties = new Properties();
producerProperties.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, kafkaBootstrapServers);
producerProperties.put(ProducerConfig.CLIENT_ID_CONFIG, Sandbox.class.getName() + "_testProducer");
producerProperties.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class.getName());
producerProperties.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class.getName());
Producer<String, String> sandboxProducer = new KafkaProducer<>(producerProperties);
sandboxProducer.send(new ProducerRecord<String, String>(topic,"uvw","uvw"));
// 2. read the test data and check it's working
ReadOnlyKeyValueStore<String, String> store = getStore();
printStore(store.all());
System.out.println("-------------ADDING NEW VALUE----------------");
sandboxProducer.send(new ProducerRecord<String, String>(topic,"xyz","xyz"));
System.out.println("-------------ADDED NEW VALUE----------------");
printStore(store.all());
sandboxProducer.close();
streams.close();
}
private static void printStore(KeyValueIterator<String, String> i)
{
System.out.println("-------------PRINT START----------------");
while (i.hasNext())
{
KeyValue<String, String> n = i.next();
System.out.println(n.key + ":" + String.join(",", n.value));
}
System.out.println("-------------PRINT END----------------");
}
private static ReadOnlyKeyValueStore<String, String> getStore()
{
ReadOnlyKeyValueStore<String, String> store = null;
String storeString = "sandbox_store";
StreamsBuilder builder = new StreamsBuilder();
builder.stream(topic
, Consumed.with(Serdes.String(),Serdes.String()))
.filter((k,v)->v!=null)
.flatMap((k,v)->{
Set<KeyValue<String, String>> results = new LinkedHashSet<>();
if (v != null)
{
for (char subChar : v.toCharArray())
{
results.add(KeyValue.<String, String>pair(new String(new char[] {subChar}), v));
}
}
return results;
})
.groupByKey(Grouped.with(Serdes.String(), Serdes.String()))
.aggregate(()->new String()
, (key, value, agg) -> {
agg = agg + value;
return agg;
}
,Materialized.<String, String, KeyValueStore<Bytes, byte[]>>as(storeString)
.withKeySerde(Serdes.String())
.withValueSerde(Serdes.String()));
final Properties streamsConfiguration = new Properties();
streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, "sandbox");
streamsConfiguration.put(StreamsConfig.CLIENT_ID_CONFIG, Sandbox.class.getName());
streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, kafkaBootstrapServers);
streamsConfiguration.put(StreamsConfig.STATE_DIR_CONFIG, kafkaGlobalTablesDirectory + "Sandbox");
streamsConfiguration.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
streams = new KafkaStreams(builder.build(), streamsConfiguration);
streams.setUncaughtExceptionHandler((Thread thread, Throwable throwable) -> {
System.out.println("Exception on thread " + thread.getName() + ":" + throwable.getLocalizedMessage());
});
Runtime.getRuntime().addShutdownHook(new Thread(streams::close));
streams.cleanUp(); // clear any old streams data - forces a rebuild of the local caches.
streams.start(); // hangs until the global table is built
StoreQueryParameters<ReadOnlyKeyValueStore<String, String>> storeSqp
= StoreQueryParameters.fromNameAndType(storeString
,QueryableStoreTypes.<String, String>keyValueStore());
// this while loop gives time for Kafka Streams to start up properly before creating the store
while (store == null)
{
try {
TimeUnit.SECONDS.sleep(1);
store = streams.store(storeSqp);
System.out.println("Store " + storeString + " Created successfully.");
} catch (InterruptedException e) {
}
catch (Exception e) {
System.out.println("Exception creating store " + storeString + ". Will try again in 1 second. Message: " + e.getLocalizedMessage());
}
}
return store;
}
}
The output I am getting is as follows:
Store sandbox_store Created successfully.
-------------PRINT START----------------
u:uvw
v:uvw
w:uvw
-------------PRINT END----------------
-------------ADDING NEW VALUE----------------
-------------ADDED NEW VALUE----------------
-------------PRINT START----------------
u:uvw
v:uvw
w:uvw
-------------PRINT END----------------
Note that the xyz I added has gone missing!
(p.s. I know I could use reduce instead of aggregate, but in practise the new value would be a different type, not a string, so it wouldn't work for my actual use-case)
Now, if I add a 10 second pause before printing the second time; or if I then restart the Sandbox class without clearing the topic, the first xyz shows up then. So it's clearly that there's a time delay somewhere in the system. And in practise I'm dealing with 300mb+ of messages all going onto the input topic at once, once an hour; and so the delay is even longer than just a few seconds.
How can I help speed things up?

Related

Kafka Java Producer API unable to serialize key as Long or Int

Here is the Java code for producing data in Kafka:
import org.apache.kafka.clients.producer.*;
import org.apache.kafka.common.serialization.LongSerializer;
import org.apache.kafka.common.serialization.StringSerializer;
import java.util.Properties;
public class ExampleClass {
private final static String TOPIC = "my-example-topic";
private final static String BOOTSTRAP_SERVERS = "confbroker:9092";
private static Producer<Long, String> createProducer() {
Properties props = new Properties();
props.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, BOOTSTRAP_SERVERS);
props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, LongSerializer.class.getName());
props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class.getName());
return new KafkaProducer<>(props);
}
private static void runProducer() throws Exception {
final Producer<Long, String> producer = createProducer();
long sensorId = 1001L;
try {
for (long index = sensorId; index < sensorId + 5; index++) {
final ProducerRecord<Long, String> record = new ProducerRecord<>(TOPIC, index, "This is sensor no: " + index);
RecordMetadata metadata = producer.send(record).get();
System.out.printf("sent record(key=%s value=%s) " + "meta(partition=%d, offset=%d)\n", record.key(),
record.value(), metadata.partition(), metadata.offset());
}
} finally {
producer.flush();
producer.close();
}
}
public static void main(String... args) throws Exception {
runProducer();
}
}
When running console consumer in Confluent 5.4.0, I am getting result as:
The key is gibberish.
How can I produce Key of either Int or Long type.
PS:
=> Same result in Confluent 5.5 also.
=> Same result with IntegerSerializer.
The console consumer uses StringDeserialisers as default for the key and the value. If you want to deserialise the key as Long you have to explicitly mention that in your console-consumer command:
--property key.deserializer org.apache.kafka.common.serialization.LongDeserializer

How to read all the records in a Kafka topic

I am using kafka : kafka_2.12-2.1.0, spring kafka on client side and have got stuck with an issue.
I need to load an in-memory map by reading all the existing messages within a kafka topic. I did this by starting a new consumer (with a unique consumer group id and setting the offset to earliest). Then I iterate over the consumer (poll method) to get all messages and stop when the consumer records become empty.
But I noticed that, when I start polling, the first few iterations return consumer records as empty and then it starts returning the actual records. Now this breaks my logic as our code thinks there are no records in the topic.
I have tried few other ways (like using offsets number) but haven't been able to come up with any solution, apart from keeping another record somewhere which tells me how many messages there are in the topic which needs to be read before I stop.
Any idea's please ?
To my understanding, what you are trying to achieve is to have a map constructed in your application based on the values that are already in a specific Topic.
For this task, instead of manually polling the topic, you can use Ktable in Kafka Streams DSL which will automatically construct a readable key-value store which is fault tolerant, replication enabled and automatically filled with new values.
You can do this simply by calling groupByKey on a stream and then using the aggregate.
KStreamBuilder builder = new KStreamBuilder();
KStream<String, Long> myKStream = builder.stream(Serdes.String(), Serdes.Long(), "topic_name");
KTable<String, Long> totalCount = myKStream.groupByKey().aggregate(this::initializer, this::aggregator);
(The actual code may vary depending on the kafka version, your configurations, etc..)
Read more about Kafka Stream concepts here
Then I iterate over the consumer (poll method) to get all messages and stop when the consumer records become empty
Kafka is a message streaming platform. Any data you stream is being updated continuously and you probably should not use it in a way that you expect the consuming to stop after a certain number of messages. How will you handle if a new message comes in after you stop the consumer?
Also the reason you are getting null records maybe probably related to records being in different partitions, etc..
What is your specific use case here?, There might be a good way to do it with the Kafka semantics itself.
You have to use 2 consumers one to load the offsets and another one to read all the records.
import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.kafka.common.PartitionInfo;
import org.apache.kafka.common.TopicPartition;
import org.apache.kafka.common.serialization.ByteArrayDeserializer;
import java.time.Duration;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Objects;
import java.util.Properties;
import java.util.Set;
import java.util.stream.Collectors;
public class KafkaRecordReader {
static final Map<String, Object> props = new HashMap<>();
static {
props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "localhost:9092");
props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, ByteArrayDeserializer.class);
props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, ByteArrayDeserializer.class);
props.put(ConsumerConfig.CLIENT_ID_CONFIG, "sample-client");
}
public static void main(String[] args) {
final Map<TopicPartition, OffsetInfo> partitionOffsetInfos = getOffsets(Arrays.asList("world, sample"));
final List<ConsumerRecord<byte[], byte[]>> records = readRecords(partitionOffsetInfos);
System.out.println(partitionOffsetInfos);
System.out.println("Read : " + records.size() + " records");
}
private static List<ConsumerRecord<byte[], byte[]>> readRecords(final Map<TopicPartition, OffsetInfo> offsetInfos) {
final Properties readerProps = new Properties();
readerProps.putAll(props);
readerProps.put(ConsumerConfig.CLIENT_ID_CONFIG, "record-reader");
final Map<TopicPartition, Boolean> partitionToReadStatusMap = new HashMap<>();
offsetInfos.forEach((tp, offsetInfo) -> {
partitionToReadStatusMap.put(tp, offsetInfo.beginOffset == offsetInfo.endOffset);
});
final List<ConsumerRecord<byte[], byte[]>> cachedRecords = new ArrayList<>();
try (final KafkaConsumer<byte[], byte[]> consumer = new KafkaConsumer<>(readerProps)) {
consumer.assign(offsetInfos.keySet());
for (final Map.Entry<TopicPartition, OffsetInfo> entry : offsetInfos.entrySet()) {
consumer.seek(entry.getKey(), entry.getValue().beginOffset);
}
boolean close = false;
while (!close) {
final ConsumerRecords<byte[], byte[]> consumerRecords = consumer.poll(Duration.ofMillis(100));
for (final ConsumerRecord<byte[], byte[]> record : consumerRecords) {
cachedRecords.add(record);
final TopicPartition currentTp = new TopicPartition(record.topic(), record.partition());
if (record.offset() + 1 == offsetInfos.get(currentTp).endOffset) {
partitionToReadStatusMap.put(currentTp, true);
}
}
boolean done = true;
for (final Map.Entry<TopicPartition, Boolean> entry : partitionToReadStatusMap.entrySet()) {
done &= entry.getValue();
}
close = done;
}
}
return cachedRecords;
}
private static Map<TopicPartition, OffsetInfo> getOffsets(final List<String> topics) {
final Properties offsetReaderProps = new Properties();
offsetReaderProps.putAll(props);
offsetReaderProps.put(ConsumerConfig.CLIENT_ID_CONFIG, "offset-reader");
final Map<TopicPartition, OffsetInfo> partitionOffsetInfo = new HashMap<>();
try (final KafkaConsumer<byte[], byte[]> consumer = new KafkaConsumer<>(offsetReaderProps)) {
final List<PartitionInfo> partitionInfos = new ArrayList<>();
topics.forEach(topic -> partitionInfos.addAll(consumer.partitionsFor("sample")));
final Set<TopicPartition> topicPartitions = partitionInfos
.stream()
.map(x -> new TopicPartition(x.topic(), x.partition()))
.collect(Collectors.toSet());
consumer.assign(topicPartitions);
final Map<TopicPartition, Long> beginningOffsets = consumer.beginningOffsets(topicPartitions);
final Map<TopicPartition, Long> endOffsets = consumer.endOffsets(topicPartitions);
for (final TopicPartition tp : topicPartitions) {
partitionOffsetInfo.put(tp, new OffsetInfo(beginningOffsets.get(tp), endOffsets.get(tp)));
}
}
return partitionOffsetInfo;
}
private static class OffsetInfo {
private final long beginOffset;
private final long endOffset;
private OffsetInfo(long beginOffset, long endOffset) {
this.beginOffset = beginOffset;
this.endOffset = endOffset;
}
#Override
public String toString() {
return "OffsetInfo{" +
"beginOffset=" + beginOffset +
", endOffset=" + endOffset +
'}';
}
#Override
public boolean equals(Object o) {
if (this == o) return true;
if (o == null || getClass() != o.getClass()) return false;
OffsetInfo that = (OffsetInfo) o;
return beginOffset == that.beginOffset &&
endOffset == that.endOffset;
}
#Override
public int hashCode() {
return Objects.hash(beginOffset, endOffset);
}
}
}
Adding to the above answer from #arshad, the reason you are not getting the records is because you have already read them. See this answer here using earliest or latest does not matter on the consumer after you have a committed offset for the partition
I would use a seek to the beginning or the particular offset if you knew the starting offset.

Write in Topic in Kafka through Java Code

i am trying to write in Kafka Topic through JAVA, as i have created the Topic, but want to insert some data in that topic.
Thanks in advance.
Here's an example of a synchronous producer. It should work with Kafka 0.11 (and a few prior releases too):
import org.apache.kafka.clients.producer.*;
import org.apache.kafka.common.serialization.LongSerializer;
import org.apache.kafka.common.serialization.StringSerializer;
import java.util.Properties;
public class MyKafkaProducer {
private final static String TOPIC = "my-example-topic";
private final static String BOOTSTRAP_SERVERS = "localhost:9092,localhost:9093,localhost:9094";
private static Producer<Long, String> createProducer() {
Properties props = new Properties();
props.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, BOOTSTRAP_SERVERS);
props.put(ProducerConfig.CLIENT_ID_CONFIG, "MyKafkaProducer");
props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, LongSerializer.class.getName());
props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class.getName());
return new KafkaProducer<>(props);
}
static void runProducer(final int sendMessageCount) throws Exception {
final Producer<Long, String> producer = createProducer();
try {
for (long index = 1; index <= sendMessageCount; index++) {
final ProducerRecord<Long, String> record = new ProducerRecord<>(TOPIC, index, "Message " + index);
RecordMetadata metadata = producer.send(record).get();
System.out.printf("sent record(key=%s value='%s')" + " metadata(partition=%d, offset=%d)\n",
record.key(), record.value(), metadata.partition(), metadata.offset());
}
} finally {
producer.flush();
producer.close();
}
}
public static void main(String[] args) throws Exception {
if (args.length == 0) {
runProducer(5);
} else {
runProducer(Integer.parseInt(args[0]));
}
}
}
You may need to modify some of the hard-coded settings.
Reference: http://cloudurable.com/blog/kafka-tutorial-kafka-producer/index.html

kafka customet partioner error

i wrote custom partitioner program,both class in same project but not sure why i am getting below error.Please help me on this.Below program is a kafka producer program.When i run the program i am getting error as SensorPartitioner class not found.
error:
Exception in thread "main" org.apache.kafka.common.config.ConfigException: Invalid value SensorPartitioner for configuration partitioner.class: Class SensorPartitioner could not be found.
at org.apache.kafka.common.config.ConfigDef.parseType(ConfigDef.java:671)
at org.apache.kafka.common.config.ConfigDef.parse(ConfigDef.java:418)
at org.apache.kafka.common.config.AbstractConfig.<init>(AbstractConfig.java:56)
at org.apache.kafka.common.config.AbstractConfig.<init>(AbstractConfig.java:63)
at org.apache.kafka.clients.producer.ProducerConfig.<init>(ProducerConfig.java:338)
at org.apache.kafka.clients.producer.KafkaProducer.<init>(KafkaProducer.java:188)
at kafka.test.main(test.java:19)
package kafka;
import org.apache.kafka.clients.producer.*;
import java.io.BufferedReader;
import java.io.FileReader;
import java.util.Properties;
public class test {
public static void main(String[] args) throws Exception{
System.out.println("new");
String topicName = "partitionTopic";
String sCurrentLine;
Properties props = new Properties();
props.put("bootstrap.servers", "localhost:9092,localhost:9093");
props.put("key.serializer","org.apache.kafka.common.serialization.StringSerializer");
props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
props.put("partitioner.class", "SensorPartitioner");
props.put("speed.sensor.name", "core");
Producer<String, String> producer = new KafkaProducer <String, String>(props);
try{
BufferedReader br = null;
br = new BufferedReader(new FileReader("datagen_10.txt"));
//String arr1=" ";
while ((sCurrentLine = br.readLine()) != null) {
System.out.println(sCurrentLine);
String[] arr11 = sCurrentLine.split(",");
String key=arr11[0];
ProducerRecord<String, String> record = new ProducerRecord<String, String>(topicName,key,sCurrentLine);
RecordMetadata metadata = producer.send(record).get();
System.out.println("Message is sent to Partition no " + metadata.partition() + " and offset " + metadata.offset());
System.out.println("SynchronousProducer Completed with success.");
}
br.close();
}catch (Exception e) {
e.printStackTrace();
System.out.println("SynchronousProducer failed with an exception");
}finally{
producer.close();
}
}
}
below program is custom partitioner program.
package kafka;
import java.util.*;
import org.apache.kafka.clients.producer.*;
import org.apache.kafka.common.*;
import org.apache.kafka.common.utils.*;
import org.apache.kafka.common.record.*;
public class SensorPartitioner implements Partitioner {
private String speedSensorName;
public void configure(Map<String, ?> configs) {
speedSensorName = configs.get("speed.sensor.name").toString();
}
public int partition(String topic, Object key, byte[] keyBytes, Object value, byte[] valueBytes, Cluster cluster) {
List<PartitionInfo> partitions = cluster.partitionsForTopic(topic);
int numPartitions = partitions.size();
int sp = (int)Math.abs(numPartitions*0.3);
int p=0;
if ( (keyBytes == null) || (!(key instanceof String)) )
throw new InvalidRecordException("All messages must have sensor name as key");
if ( ((String)key).equals(speedSensorName) )
p = Utils.toPositive(Utils.murmur2(valueBytes)) % sp;
else
p = Utils.toPositive(Utils.murmur2(keyBytes)) % (numPartitions-sp) + sp ;
System.out.println("Key = " + (String)key + " Partition = " + p );
return p;
}
public void close() {}
}
I also met the same problem, but I found the SensorPartitioner instead of a Kafka class, actually is another class in the tutorial. You create the SensorPartitioner class, then the problem would be solved.
The class:
https://github.com/LearningJournal/ApacheKafkaTutorials/blob/master/ProducerExamples/SensorPartitioner.java
vivman I had the same problem with IDEA devTools.And I fixed it by set fullPath to partitioner.class like this props.put("partitioner.class", "xx.xxx.x.SensorPartitioner"); in you program you can try to modify like this props.put("partitioner.class", "kafka.SensorPartitioner");
hope this helps.
Use absolute path to SensorPartitioner class as below:
props.put("partitioner.class", "com.subpackage.subsubpackage.SensorPartitioner");

apache kafka throwing an exception for scala

I am trying to compile and run a simple kafka code that is a sample from Aapche.When compiling I am getting the following exception, even after adding all the lib files for scala (i guess).
Exception in thread "main" java.lang.NullPointerException
at scala.Predef$.Integer2int(Predef.scala:303)
at kafka.client.ClientUtils$$anonfun$parseBrokerList$1.apply(ClientUtils.scala:103)
at kafka.client.ClientUtils$$anonfun$parseBrokerList$1.apply(ClientUtils.scala:102)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:194)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:194)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:60)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:44)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:194)
at scala.collection.mutable.ArrayBuffer.map(ArrayBuffer.scala:44)
at kafka.client.ClientUtils$.parseBrokerList(ClientUtils.scala:102)
at kafka.producer.BrokerPartitionInfo.<init>(BrokerPartitionInfo.scala:32)
at kafka.producer.async.DefaultEventHandler.<init>(DefaultEventHandler.scala:41)
at kafka.producer.Producer.<init>(Producer.scala:60)
at kafka.javaapi.producer.Producer.<init>(Producer.scala:26)
at kafkaTest.TestProducer.main(TestProducer.java:23)
This is my program:
package kafkaTest;
import java.util.*;
import kafka.javaapi.producer.Producer;
import kafka.producer.KeyedMessage;
import kafka.producer.ProducerConfig;
public class TestProducer {
public static void main(String[] args) {
// long events = Long.parseLong(args[0]);
long events = 10l;
Random rnd = new Random();
Properties props = new Properties();
props.put("metadata.broker.list", "broker1:9092,broker2:9092 ");
props.put("serializer.class", "kafka.serializer.StringEncoder");
***![props.put("partitioner.class", "kafkaTest.SimplePartitioner");][1]***//this is line no 23
props.put("request.required.acks", "1");
ProducerConfig config = new ProducerConfig(props);
Producer<String, String> producer = new Producer<String, String>(config);
for (long nEvents = 0; nEvents < events; nEvents++) { long runtime =
new Date().getTime(); String ip = "192.168.2.1" + rnd.nextInt(255);
String msg = runtime + ",www.example.com," + ip; KeyedMessage<String,
String> data = new KeyedMessage<String, String>("page_visits", ip,
msg); producer.send(data); }
producer.close();
}
}
The attached is the screen shot of library files.
Please let me know the cause of error/exception.
Edit: this is SimplePartitioner.java
package kafkaTest;
import kafka.producer.Partitioner;
import kafka.utils.VerifiableProperties;
public class SimplePartitioner implements Partitioner {
public SimplePartitioner(VerifiableProperties props) {
}
public int partition(Object key, int a_numPartitions) {
int partition = 0;
String stringKey = (String) key;
int offset = stringKey.lastIndexOf('.');
if (offset > 0) {
partition = Integer.parseInt(stringKey.substring(offset + 1))
% a_numPartitions;
}
return partition;
}
}
There's a space at the end of your broker list :
props.put("metadata.broker.list", "broker1:9092,broker2:9092 ");
Remove it and it should work fine then :
props.put("metadata.broker.list", "broker1:9092,broker2:9092");
I also got this error when metadata.broker.list has a broker with no port number.