如何使用套接字实现Spark Streaming输出

Question

我一直在尝试用Java实现它：

dstream.foreachRDD { rdd =>
  rdd.foreachPartition { partitionOfRecords =>
    val connection = createNewConnection()
    partitionOfRecords.foreach(record => connection.send(record))
    connection.close()
  }
}

对于Spark文档提供的示例类型。 以下按预期工作：

import scala.Tuple2;
import com.google.common.collect.Lists;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.api.java.StorageLevels;
import org.apache.spark.streaming.Durations;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.streaming.Time;

import java.util.regex.Pattern;
import java.io.IOException;

/**
* Counts words in UTF8 encoded, '\n' delimited text received from the network every second.
*
* Usage: JavaNetworkWordCount <hostname> <port>
* <hostname> and <port> describe the TCP server that Spark Streaming would connect to receive data.
*
* To run this on your local machine, you need to first run a Netcat server
*    `$ nc -lk 9999`
* and then run the example
*    `$ bin/run-example org.apache.spark.examples.streaming.JavaNetworkWordCount localhost 9999`
*/
public final class SocketWriter {
  private static final Pattern SPACE = Pattern.compile(" ");

  public static void main(String[] args) {
    if (args.length < 2) {
      System.err.println("Usage: JavaNetworkWordCount <hostname> <port>");
      System.exit(1);
    }

    // Create the context with a 1 second batch size
    SparkConf sparkConf = new SparkConf().setAppName("JavaNetworkWordCount");
    JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1));

    // Create a JavaReceiverInputDStream on target ip:port and count the
    // words in input stream of \n delimited text (eg. generated by 'nc')
    // Note that no duplication in storage level only for running locally.
    // Replication necessary in distributed scenario for fault tolerance.
    JavaReceiverInputDStream<String> lines = ssc.socketTextStream(
    args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER);
    JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
      @Override
      public Iterable<String> call(String x) {
        return Lists.newArrayList(SPACE.split(x));
      }
    });
    JavaPairDStream<String, Integer> wordCounts = words.mapToPair(
    new PairFunction<String, String, Integer>() {
      @Override
      public Tuple2<String, Integer> call(String s) {
        return new Tuple2<String, Integer>(s, 1);
      }
    }).reduceByKey(new Function2<Integer, Integer, Integer>() {
      @Override
      public Integer call(Integer i1, Integer i2) {
        return i1 + i2;
      }
    });

    wordCounts.foreachRDD(new Function2<JavaPairRDD<String, Integer>, Time, Void>() {
      @Override
      public Void call(JavaPairRDD<String, Integer> rdd, Time time) throws IOException {
        String counts = "Counts at time " + time + " " + rdd.collect();
        System.out.println(counts);
        return null;
      }
    });

    ssc.start();
    ssc.awaitTermination();
  }
}

但是我需要能够通过修改此部分将数据输出到套接字以使用此问题顶部的Scala中指定的“设计模式”。

wordCounts.foreachRDD(new Function2<JavaPairRDD<String, Integer>, Time, Void>() {
  @Override
  public Void call(JavaPairRDD<String, Integer> rdd, Time time) throws IOException {
    String counts = "Counts at time " + time + " " + rdd.collect();
    System.out.println(counts);
    return null;
  }
});

我试图在这里使用Socket和PrintWriter对象，但不能使它工作，我找不到任何人这样做的例子。 任何帮助表示赞赏。

Answer 1

我只是向你展示问题，因为我试图做同样的事情，最后我做到了！ 对你来说可能为时已晚，但希望对许多其他人没有希望。

正如官方文档中所述 ，我没有以最佳方式完成它，即使用连接池，因此Spark不必为每个RDD打开和关闭连接，但仍然有效，这是我的代码：

wordCounts.foreachRDD(new VoidFunction<JavaRDD<String>>() {
    public void call(JavaRDD<String> rdd) throws Exception {
        rdd.foreachPartition(new VoidFunction<Iterator<String>>() {
            public void call(Iterator<String> partitionOfRecords) throws Exception {
                Socket mySocket = new Socket("localhost", 9998);
                final PrintWriter out = new PrintWriter(mySocket.getOutputStream(), true);
                while(partitionOfRecords.hasNext()) {
                    out.println(partitionOfRecords.next());
                }
                mySocket.close();
            }
        });
    }
});