
Producer API


顺序:监控器 —> 序列化器 —> 分区器
batch.size #只有数据积累到 batch.size 之后,sender 才会发送数据。
linger.ms #如果数据迟迟未达到 batch.size,sender 等待 linger.time 之后就会发送数据。
<dependencies>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>2.4.1</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<version>2.12.0</version>
</dependency>
</dependencies>
<?xml version="1.0" encoding="UTF-8"?>
<Configuration status="error" strict="true" name="XMLConfig">
<Appenders>
<!-- 类型名为Console,名称为必须属性 -->
<Appender type="Console" name="STDOUT">
<!-- 布局为PatternLayout的方式,
输出样式为[INFO] [2018-01-22 17:34:01][org.test.Console]I'm here -->
<Layout type="PatternLayout"
pattern="[%p] [%d{yyyy-MM-dd HH:mm:ss}][%c{10}]%m%n" />
</Appender>
</Appenders>
<Loggers>
<!-- 可加性为false -->
<Logger name="test" level="info" additivity="false">
<AppenderRef ref="STDOUT" />
</Logger>
<!-- root loggerConfig设置 -->
<Root level="info">
<AppenderRef ref="STDOUT" />
</Root>
</Loggers>
</Configuration>
编写代码
需要用到的类:
KafkaProducer #需要创建一个生产者对象,用来发送数据
ProducerConfig #获取所需的一系列配置参数
ProducerRecord #每条数据都要封装成一个ProducerRecord对象
public class MyProducer{
public static void main(String[] args) {
Properties properties = new Properties();
properties.put("bootstrap.servers","hadoop105:9092");
properties.put("key.serializer","org.apache.kafka.common.serialization.StringSerializer");
properties.put("value.serializer","org.apache.kafka.common.serialization.StringSerializer");
KafkaProducer<String, String> producer = new KafkaProducer<String,String>(properties);
for (int i = 0; i < 10; i++) {
producer.send(new ProducerRecord<String, String>("bajie", "--gaolaozhuangshuiyundong--" + i));
}
producer.close();
}
}
[xiaoxq@hadoop105 kafka_2.11-2.4.1]$ bin/kafka-console-consumer.sh --bootstrap-server hadoop105:9092 --topic bajie
--gaolaozhuangshuiyundong--0
--gaolaozhuangshuiyundong--1
--gaolaozhuangshuiyundong--2
--gaolaozhuangshuiyundong--3
--gaolaozhuangshuiyundong--4
--gaolaozhuangshuiyundong--5
--gaolaozhuangshuiyundong--6
--gaolaozhuangshuiyundong--7
--gaolaozhuangshuiyundong--8
--gaolaozhuangshuiyundong--9
public class MyProducer2 {
public static void main(String[] args) {
//todo 创建生产者的配置对象
Properties properties = new Properties();
//1.设定集群
properties.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG,"hadoop105:9092");
//2.设定ack等级
properties.put(ProducerConfig.ACKS_CONFIG,"all");
//3.设定重试的次数
properties.put(ProducerConfig.RETRIES_CONFIG,"2");
//4.设定batch的大小
properties.put(ProducerConfig.BATCH_SIZE_CONFIG,"16384");
//5.设定间隔时间
properties.put(ProducerConfig.LINGER_MS_CONFIG,1);
//6.设定缓冲区大小
properties.put(ProducerConfig.BUFFER_MEMORY_CONFIG,"33554432");
//7.设定key和value的序列化方式
properties.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer");
properties.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer");
//todo 创建生产者的对象
KafkaProducer<String, String> producer = new KafkaProducer<>(properties);
//发送数据
for (int i = 0; i < 10; i++) {
producer.send(new ProducerRecord<String, String>("bajie","gaolaozhuang---" + i));
}
//TODO 关闭生产者对象
producer.close();
}
}
[xiaoxq@hadoop105 kafka_2.11-2.4.1]$ bin/kafka-console-consumer.sh --bootstrap-server hadoop105:9092 --topic bajie
gaolaozhuang---0
gaolaozhuang---1
gaolaozhuang---2
gaolaozhuang---3
gaolaozhuang---4
gaolaozhuang---5
gaolaozhuang---6
gaolaozhuang---7
gaolaozhuang---8
gaolaozhuang---9
public class MyProducer3 {
public static void main(String[] args) {
//todo 创建生产者的配置对象
Properties properties = new Properties();
//1.设定集群,broker-list
properties.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG,"hadoop105:9092");
//2.设定ack等级
properties.put(ProducerConfig.ACKS_CONFIG,"all");
//3.设定重试的次数
properties.put(ProducerConfig.RETRIES_CONFIG,"2");
//4.设定batch的大小 16kb
properties.put(ProducerConfig.BATCH_SIZE_CONFIG,"16384");
//5.设定间隔时间 1ms
properties.put(ProducerConfig.LINGER_MS_CONFIG,1);
//6.设定缓冲区大小 32M
properties.put(ProducerConfig.BUFFER_MEMORY_CONFIG,"33554432");
//7.设定key和value的序列化方式
properties.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer");
properties.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer");
//todo 创建生产者的对象
KafkaProducer<String, String> producer = new KafkaProducer<>(properties);
//发送数据
for (int i = 0; i < 10; i++) {
//采用生产者对象发送数据
producer.send(new ProducerRecord<String, String>("bajie","er shi xiong shi fu bei yao guai zhua zou le---" + i),new Callback() {
@Override
//这个回调函数 在ack正常返回的时候是返回metadata,如果不正常返回则返回异常
public void onCompletion(RecordMetadata recordMetadata, Exception e) {
if (e==null){
System.out.println("topic:" + recordMetadata.topic()
+ "--partition:" + recordMetadata.partition()
+ "--offset:" + recordMetadata.offset() );
}
}
});
}
//TODO 关闭生产者对象
//这个close会在关闭前将所有数据处理完再退出生产者.
producer.close();
}
}
topic:bajie--partition:1--offset:10
topic:bajie--partition:1--offset:11
topic:bajie--partition:1--offset:12
topic:bajie--partition:1--offset:13
topic:bajie--partition:1--offset:14
topic:bajie--partition:1--offset:15
topic:bajie--partition:1--offset:16
topic:bajie--partition:1--offset:17
topic:bajie--partition:1--offset:18
topic:bajie--partition:1--offset:19
er shi xiong shi fu bei yao guai zhua zou le---0
er shi xiong shi fu bei yao guai zhua zou le---1
er shi xiong shi fu bei yao guai zhua zou le---2
er shi xiong shi fu bei yao guai zhua zou le---3
er shi xiong shi fu bei yao guai zhua zou le---4
er shi xiong shi fu bei yao guai zhua zou le---5
er shi xiong shi fu bei yao guai zhua zou le---6
er shi xiong shi fu bei yao guai zhua zou le---7
er shi xiong shi fu bei yao guai zhua zou le---8
er shi xiong shi fu bei yao guai zhua zou le---9
分区器
interceptors拦截器过滤 —–> serializer序列化器进行序列化方便数据的传输 —–> partitions分区
当指定了key,则采用固定的算法,每次都会计算出同一分区号,如果key不存在则计算出一个可用分区的的一个任意分区。
自定义分区器
public class MyPartitioner implements Partitioner {
@Override
/**
* 主要写分区逻辑
* 有bajie 的就往0号分区
* 没有bajie 的就往1号分区
*/
public int partition(String s, Object o, byte[] bytes, Object o1, byte[] bytes1, Cluster cluster) {
if (new String(bytes1).contains("bajie")){
return 0;
}else {
return 1;
}
}
@Override
public void close() {
}
@Override
public void configure(Map<String, ?> map) {
}
}
编写partitionerProducer
public class PartitionerProducer {
public static void main(String[] args) {
//todo 创建生产者的配置对象
Properties properties = new Properties();
//1.设定集群,broker-list
properties.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG,"hadoop105:9092");
//2.设定ack等级
properties.put(ProducerConfig.ACKS_CONFIG,"all");
//3.设定重试的次数
properties.put(ProducerConfig.RETRIES_CONFIG,"2");
//4.设定batch的大小 16kb
properties.put(ProducerConfig.BATCH_SIZE_CONFIG,"16384");
//5.设定间隔时间 1ms
properties.put(ProducerConfig.LINGER_MS_CONFIG,1);
//6.设定缓冲区大小 32M
properties.put(ProducerConfig.BUFFER_MEMORY_CONFIG,"33554432");
//7.设定分区器
properties.put(ProducerConfig.PARTITIONER_CLASS_CONFIG,"partitioner.MyPartitioner");
//8.设定key和value的序列化方式
properties.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer");
properties.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer");
//todo 创建生产者的对象
KafkaProducer<String, String> producer = new KafkaProducer<>(properties);
//发送数据
for (int i = 0; i < 10; i++) {
//采用生产者对象发送数据
if (i<5){
producer.send(new ProducerRecord<String, String>("bajie","er shi xiong shi bajie ---" + i),new Callback() {
@Override
//这个回调函数 在ack正常返回的时候是返回 metadata,如果不正常返回则返回异常
public void onCompletion(RecordMetadata recordMetadata, Exception e) {
if (e==null){
System.out.println("topic:" + recordMetadata.topic()
+ "--partition:" + recordMetadata.partition()
+ "--offset:" + recordMetadata.offset() );
}
}
});
}else{
producer.send(new ProducerRecord<String, String>("bajie","da shi xiong shi wu kong ---" + i),new Callback() {
@Override
//这个回调函数 在ack正常返回的时候是返回 metadata,如果不正常返回则返回异常
public void onCompletion(RecordMetadata recordMetadata, Exception e) {
if (e==null){
System.out.println("topic:" + recordMetadata.topic()
+ "--partition:" + recordMetadata.partition()
+ "--offset:" + recordMetadata.offset() );
}
}
});
}
}
//TODO 关闭生产者对象
//这个close会在关闭前将所有数据处理完再退出生产者.
producer.close();
}
}
执行后结果为
topic:bajie--partition:1--offset:25
topic:bajie--partition:1--offset:26
topic:bajie--partition:1--offset:27
topic:bajie--partition:1--offset:28
topic:bajie--partition:1--offset:29
topic:bajie--partition:0--offset:14
topic:bajie--partition:0--offset:15
topic:bajie--partition:0--offset:16
topic:bajie--partition:0--offset:17
topic:bajie--partition:0--offset:18
public class SyncProducer {
public static void main(String[] args) throws ExecutionException, InterruptedException {
//todo 创建生产者的配置对象
Properties properties = new Properties();
//1.设定集群,broker-list
properties.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG,"hadoop105:9092");
//2.设定ack等级
properties.put(ProducerConfig.ACKS_CONFIG,"all");
//3.设定重试的次数
properties.put(ProducerConfig.RETRIES_CONFIG,"2");
//4.设定batch的大小 16kb
properties.put(ProducerConfig.BATCH_SIZE_CONFIG,"16384");
//5.设定间隔时间 1ms
properties.put(ProducerConfig.LINGER_MS_CONFIG,1);
//6.设定缓冲区大小 32M
properties.put(ProducerConfig.BUFFER_MEMORY_CONFIG,"33554432");
//7.设定key和value的序列化方式
properties.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer");
properties.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer");
//todo 创建生产者的对象
KafkaProducer<String, String> producer = new KafkaProducer<>(properties);
//发送数据
for (int i = 0; i < 10; i++) {
//采用生产者对象发送数据
Future<RecordMetadata> future = producer.send(new ProducerRecord<String, String>("bajie", "er shi xiong shi bajie ---" + i), new Callback() {
@Override
//这个回调函数 在ack正常返回的时候是返回 metadata,如果不正常返回则返回异常
public void onCompletion(RecordMetadata recordMetadata, Exception e) {
if (e == null) {
System.out.println("topic:" + recordMetadata.topic()
+ "--partition:" + recordMetadata.partition()
+ "--offset:" + recordMetadata.offset());
}
}
});
//System.out.println("消息已经发送了");
future.get();
}
//TODO 关闭生产者对象
//这个close会在关闭前将所有数据处理完再退出生产者.
producer.close();
}
}
执行后结果
opic:bajie--partition:0--offset:34
topic:bajie--partition:1--offset:35
topic:bajie--partition:0--offset:35
topic:bajie--partition:1--offset:36
topic:bajie--partition:0--offset:36
topic:bajie--partition:1--offset:37
topic:bajie--partition:0--offset:37
topic:bajie--partition:1--offset:38
topic:bajie--partition:0--offset:38
topic:bajie--partition:1--offset:39
当 //System.out.println("消息已经发送了");注释打开后执行结果
消息已经发送了
topic:bajie--partition:0--offset:39
消息已经发送了
topic:bajie--partition:1--offset:40
消息已经发送了
topic:bajie--partition:0--offset:40
消息已经发送了
topic:bajie--partition:1--offset:41
消息已经发送了
topic:bajie--partition:0--offset:41
消息已经发送了
topic:bajie--partition:1--offset:42
消息已经发送了
topic:bajie--partition:0--offset:42
消息已经发送了
topic:bajie--partition:1--offset:43
消息已经发送了
topic:bajie--partition:0--offset:43
消息已经发送了
topic:bajie--partition:1--offset:44
参考文章:https://blog.csdn.net/weixin_48067943/article /details/108228622 blog.csdn.net/weixin_48067943 /article/details/108228557