5

我们有两种消息传到 Flink

  1. 控制消息 -> 仅滚动文件
  2. 数据消息 -> 将使用 sink 存储在 S3

我们对两个消息都有单独的源流。我们将相同的接收器附加到两个流。我们要做的是广播控制消息，以便所有并行运行的接收器都应该接收它。

下面是相同的代码：

package com.ranjit.com.flinkdemo;

import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.fs.DateTimeBucketer;
import org.apache.flink.streaming.connectors.fs.RollingSink;

import org.apache.flink.streaming.connectors.fs.StringWriter;;

public class FlinkBroadcast {
    public static void main(String[] args) throws Exception {

        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(2);

        DataStream<String> ctrl_message_stream = env.socketTextStream("localhost", 8088);

        ctrl_message_stream.broadcast();

        DataStream<String> message_stream = env.socketTextStream("localhost", 8087);

        RollingSink sink = new RollingSink<String>("/base/path");
        sink.setBucketer(new DateTimeBucketer("yyyy-MM-dd--HHmm"));
        sink.setWriter(new StringWriter<String>() );
        sink.setBatchSize(1024 * 1024 * 400); // this is 400 MB,

        ctrl_message_stream.broadcast().addSink(sink);
        message_stream.addSink(sink);

        env.execute("stream");
    }

}

但我观察到的是，它正在创建 4 个接收器实例，并且控制消息仅广播到 2 个接收器（由控制消息流创建）。所以我的理解是两个流都应该通过相同的运算符链来执行我们不希望的操作，因为数据消息会有多个转换。我们已经编写了自己的接收器，如果它是控制消息，它将读取消息，然后它只会滚动文件。

示例代码：

package com.gslab.com.dataSets;
import java.io.File;
import java.util.ArrayList;
import java.util.List;
import org.apache.avro.Schema;
import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericData.Record;
import org.apache.avro.generic.GenericRecord;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

public class FlinkBroadcast {
    public static void main(String[] args) throws Exception {

        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(2);

        List<String> controlMessageList = new ArrayList<String>();
        controlMessageList.add("controlMessage1");
        controlMessageList.add("controlMessage2");

        List<String> dataMessageList = new ArrayList<String>();
        dataMessageList.add("Person1");
        dataMessageList.add("Person2");
        dataMessageList.add("Person3");
        dataMessageList.add("Person4");

        DataStream<String> controlMessageStream  = env.fromCollection(controlMessageList);
        DataStream<String> dataMessageStream  = env.fromCollection(dataMessageList);

        DataStream<GenericRecord> controlMessageGenericRecordStream = controlMessageStream.map(new MapFunction<String, GenericRecord>() {
            @Override
            public GenericRecord map(String value) throws Exception {
                 Record gr = new GenericData.Record(new Schema.Parser().parse(new File("src/main/resources/controlMessageSchema.avsc")));
                 gr.put("TYPE", value);
                 return gr;
            }
        });

        DataStream<GenericRecord> dataMessageGenericRecordStream = dataMessageStream.map(new MapFunction<String, GenericRecord>() {
            @Override
            public GenericRecord map(String value) throws Exception {
                 Record gr = new GenericData.Record(new Schema.Parser().parse(new File("src/main/resources/dataMessageSchema.avsc")));
                 gr.put("FIRSTNAME", value);
                 gr.put("LASTNAME", value+": lastname");
                 return gr;
            }
        });

        //Displaying Generic records
        dataMessageGenericRecordStream.map(new MapFunction<GenericRecord, GenericRecord>() {
            @Override
            public GenericRecord map(GenericRecord value) throws Exception {
                System.out.println("data before union: "+ value);
                return value;
            }
        });

        controlMessageGenericRecordStream.broadcast().union(dataMessageGenericRecordStream).map(new MapFunction<GenericRecord, GenericRecord>() {
            @Override
            public GenericRecord map(GenericRecord value) throws Exception {
                System.out.println("data after union: " + value);
                return value;
            }
        });
        env.execute("stream");
    }
}

输出：

05/09/2016 13:02:12 Source: Collection Source(1/1) switched to FINISHED 
05/09/2016 13:02:12 Source: Collection Source(1/1) switched to FINISHED 
05/09/2016 13:02:13 Map(1/2) switched to FINISHED 
05/09/2016 13:02:13 Map(2/2) switched to FINISHED 
data after union: {"TYPE": "controlMessage1"}
data before union: {"FIRSTNAME": "Person2", "LASTNAME": "Person2: lastname"}
data after union: {"TYPE": "controlMessage1"}
data before union: {"FIRSTNAME": "Person1", "LASTNAME": "Person1: lastname"}
data after union: {"TYPE": "controlMessage2"}
data after union: {"TYPE": "controlMessage2"}
data after union: {"FIRSTNAME": "Person1", "LASTNAME": "Person1"}
data before union: {"FIRSTNAME": "Person4", "LASTNAME": "Person4: lastname"}
data before union: {"FIRSTNAME": "Person3", "LASTNAME": "Person3: lastname"}
data after union: {"FIRSTNAME": "Person2", "LASTNAME": "Person2"}
data after union: {"FIRSTNAME": "Person3", "LASTNAME": "Person3"}
05/09/2016 13:02:13 Map -> Map(2/2) switched to FINISHED 
data after union: {"FIRSTNAME": "Person4", "LASTNAME": "Person4"}
05/09/2016 13:02:13 Map -> Map(1/2) switched to FINISHED 
05/09/2016 13:02:13 Map(1/2) switched to FINISHED 
05/09/2016 13:02:13 Map(2/2) switched to FINISHED 
05/09/2016 13:02:13 Job execution switched to status FINISHED.

我们可以看到 LASTNAME 值不正确，它被每条记录的 FIRSTNAME 值替换

4

1 回答 1

2

Your code essentially terminates both streams with their own copy of the sink you define. What you would want instead is something like this:

final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(2);

DataStream<String> ctrl_message_stream = env.socketTextStream("localhost", 8088);

DataStream<String> message_stream = env.socketTextStream("localhost", 8087);

RollingSink sink = new RollingSink<String>("/base/path");
sink.setBucketer(new DateTimeBucketer("yyyy-MM-dd--HHmm"));
sink.setWriter(new StringWriter<String>() );
sink.setBatchSize(1024 * 1024 * 400); // this is 400 MB,

ctrl_message_stream.broadcast().union(message_stream).addSink(sink);

env.execute("stream");
于 2016-05-07T13:04:34.950 回答