kafka中实现自定义分区器:
import org.apache.kafka.clients.producer.Partitioner;
import org.apache.kafka.common.Cluster;
import org.apache.kafka.common.PartitionInfo;
import org.apache.kafka.common.utils.Utils;
import java.util.List;
import java.util.Map;
import java.util.concurrent.atomic.AtomicInteger;
public class MyPartitioner implements Partitioner {
private final AtomicInteger counter = new AtomicInteger(0);
@Override
public int partition(String topic, Object key, byte[] keyBytes, Object value, byte[] valueBytes, Cluster cluster) {
List<PartitionInfo> parts = cluster.partitionsForTopic(topic);
int partitionSize = parts.size();
if(key == null ){
return counter.getAndIncrement() % partitionSize;
}else{
//默认分区器DefaultPartitioner采用了MurmurHash2算法进行hash
return Utils.toPositive(Utils.murmur2(keyBytes)) % partitionSize;
}
}
@Override
public void close() {
}
@Override
public void configure(Map<String, ?> map) {
}
}
然后在生产者客户端中增加如下配置:
properties.setProperty(ProducerConfig.PARTITIONER_CLASS_CONFIG, MyPartitioner.class.getName());
这样,生产者客户端就指定了自定义分区器来实现自定义的分区逻辑