Flink+Kafka实现End-to-End Exactly-Once
https://ververica.cn/developers/flink-kafka-end-to-end-exactly-once-analysis/
package xx.xxxxxx.flink.exactly;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.streaming.api.CheckpointingMode;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.CheckpointConfig;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer;
import org.apache.flink.streaming.connectors.kafka.KafkaSerializationSchema;
import org.apache.kafka.clients.CommonClientConfigs;
import org.apache.kafka.clients.producer.ProducerRecord;
import javax.annotation.Nullable;
import java.nio.charset.StandardCharsets;
import java.util.Properties;
/**
* 1. Kafka Producer的容错-Kafka 0.9 and 0.10
* 如果Flink开启了checkpoint,针对FlinkKafkaProducer09 和FlinkKafkaProducer010 可以提供 at-least-once的语义,配置如下参数
* setLogFailuresOnly(false)
* setFlushOnCheckpoint(true)
* retries【这个参数的值默认是0】 //注意:建议修改kafka 生产者的重试次数
*
* 2. Kafka Producer的容错-Kafka 0.11+
* 如果Flink开启了checkpoint,针对FlinkKafkaProducer011+ 就可以提供 exactly-once的语义
* 但是需要选择具体的语义
* Semantic.NONE
* Semantic.AT_LEAST_ONCE【默认】
* Semantic.EXACTLY_ONCE
*/
public class StreamExactlyOnceKafkaDemo {
/*
/export/server/kafka/bin/kafka-topics.sh --list --bootstrap-server node1.itcast.cn:9092
Source Kafka:
/export/server/kafka/bin/kafka-topics.sh --create \
--bootstrap-server node1.itcast.cn:9092 --replication-factor 1 --partitions 3 --topic flink-topic-source
/export/server/kafka/bin/kafka-console-producer.sh --broker-list node1.itcast.cn:9092 \
--topic flink-topic-source
Sink Kafka:
/export/server/kafka/bin/kafka-topics.sh --create --bootstrap-server node1.itcast.cn:9092 \
--replication-factor 1 --partitions 3 --topic flink-topic-sink
/export/server/kafka/bin/kafka-console-consumer.sh --bootstrap-server node1.itcast.cn:9092 \
--topic flink-topic-sink --from-beginning
*/
public static void main(String[] args) throws Exception {
// 1. 执行环境-env
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(2);
// 设置Checkpoint
env.enableCheckpointing(5000);
env.getCheckpointConfig().setCheckpointingMode(CheckpointingMode.EXACTLY_ONCE);
env.getCheckpointConfig().setMinPauseBetweenCheckpoints(500);
env.getCheckpointConfig().enableExternalizedCheckpoints(
CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION
);