58、Spark Streaming: DStream的output操作以及foreachRDD详解-白红宇

58、Spark Streaming: DStream的output操作以及foreachRDD详解

阅读量：5219 次

发布时间：2019-06-14

本文共 8254 字，大约阅读时间需要 27 分钟。

一、output操作

1、output操作

DStream中的所有计算，都是由output操作触发的，比如print()。如果没有任何output操作，那么，压根儿就不会执行定义的计算逻辑。此外，即使你使用了foreachRDD output操作，也必须在里面对RDD执行action操作，才能触发对每一个batch的计算逻辑。否则，光有foreachRDD output操作，在里面没有对RDD执行action操作，也不会触发任何逻辑。

2、output操作概览

二、foreachRDD

1、foreachRDD详解

通常在foreachRDD中，都会创建一个Connection，比如JDBC Connection，然后通过Connection将数据写入外部存储。误区一：在RDD的foreach操作外部，创建Connection这种方式是错误的，因为它会导致Connection对象被序列化后传输到每个Task中。而这种Connection对象，实际上一般是不支持序列化的，也就无法被传输。dstream.foreachRDD { rdd =>  val connection = createNewConnection()   rdd.foreach { record => connection.send(record)  }}误区二：在RDD的foreach操作内部，创建Connection这种方式是可以的，但是效率低下。因为它会导致对于RDD中的每一条数据，都创建一个Connection对象。而通常来说，Connection的创建，是很消耗性能的。dstream.foreachRDD { rdd =>  rdd.foreach { record =>    val connection = createNewConnection()    connection.send(record)    connection.close()  }}合理方式一：使用RDD的foreachPartition操作，并且在该操作内部，创建Connection对象，这样就相当于是，为RDD的每个partition创建一个Connection对象，节省资源的多了。dstream.foreachRDD { rdd =>  rdd.foreachPartition { partitionOfRecords =>    val connection = createNewConnection()    partitionOfRecords.foreach(record => connection.send(record))    connection.close()  }}合理方式二：自己手动封装一个静态连接池，使用RDD的foreachPartition操作，并且在该操作内部，从静态连接池中，通过静态方法，获取到一个连接，使用之后再还回去。这样的话，甚至在多个RDD的partition之间，也可以复用连接了。而且可以让连接池采取懒创建的策略，并且空闲一段时间后，将其释放掉。dstream.foreachRDD { rdd =>  rdd.foreachPartition { partitionOfRecords =>    val connection = ConnectionPool.getConnection()    partitionOfRecords.foreach(record => connection.send(record))    ConnectionPool.returnConnection(connection)    }}案例：改写UpdateStateByKeyWordCount，将每次统计出来的全局的单词计数，写入一份，到MySQL数据库中。

2、java案例

创建mysql表

mysql> use testdb;Reading table information for completion of table and column namesYou can turn off this feature to get a quicker startup with -ADatabase changedmysql> create table wordcount (    ->   id integer auto_increment primary key,    ->   updated_time timestamp NOT NULL default CURRENT_TIMESTAMP on update CURRENT_TIMESTAMP,    ->   word varchar(255),    ->   count integer    -> );Query OK, 0 rows affected (0.05 sec)

java代码

###ConnectionPool package cn.spark.study.streaming;import java.sql.Connection;import java.sql.DriverManager;import java.util.LinkedList;/** * 简易版的连接池 * @author Administrator * */public class ConnectionPool {    // 静态的Connection队列    private static LinkedList
     
       connectionQueue;        /**     * 加载驱动     */    static {        try {            Class.forName("com.mysql.jdbc.Driver");        } catch (ClassNotFoundException e) {            e.printStackTrace();        }      }        /**     * 获取连接，多线程访问并发控制     * @return     */    public synchronized static Connection getConnection() {        try {            if(connectionQueue == null) {                connectionQueue = new LinkedList
      
       ();                for(int i = 0; i < 10; i++) {                    Connection conn = DriverManager.getConnection(                            "jdbc:mysql://spark1:3306/testdb",                             "",                             "");                    connectionQueue.push(conn);                  }            }        } catch (Exception e) {            e.printStackTrace();        }        return connectionQueue.poll();    }        /**     * 还回去一个连接     */    public static void returnConnection(Connection conn) {        connectionQueue.push(conn);      }    }###PersistWordCountpackage cn.spark.study.streaming;import java.sql.Connection;import java.sql.Statement;import java.util.Arrays;import java.util.Iterator;import java.util.List;import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaPairRDD;import org.apache.spark.api.java.function.FlatMapFunction;import org.apache.spark.api.java.function.Function;import org.apache.spark.api.java.function.Function2;import org.apache.spark.api.java.function.PairFunction;import org.apache.spark.api.java.function.VoidFunction;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 com.google.common.base.Optional;import scala.Tuple2;/** * 基于持久化机制的实时wordcount程序 * @author Administrator * */public class PersistWordCount {    public static void main(String[] args) {        SparkConf conf = new SparkConf()                .setMaster("local[2]")                .setAppName("PersistWordCount");          JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(5));        jssc.checkpoint("hdfs://spark1:9000/wordcount_checkpoint");                  JavaReceiverInputDStream
       
         lines = jssc.socketTextStream("spark1", 9999);                JavaDStream
        
          words = lines.flatMap(new FlatMapFunction
         
          () {            private static final long serialVersionUID = 1L;            @Override            public Iterable
          
            call(String line) throws Exception { return Arrays.asList(line.split(" ")); } }); JavaPairDStream
           
             pairs = words.mapToPair( new PairFunction
            
             () { private static final long serialVersionUID = 1L; @Override public Tuple2
             
               call(String word) throws Exception { return new Tuple2
              
               (word, 1); } }); JavaPairDStream
               
                 wordCounts = pairs.updateStateByKey( new Function2
                
                 
                  , Optional
                  
                   , Optional
                   
                    >() { private static final long serialVersionUID = 1L; @Override public Optional
                    
                      call(List
                     
                       values, Optional
                      
                        state) throws Exception { Integer newValue = 0; if(state.isPresent()) { newValue = state.get(); } for(Integer value : values) { newValue += value; } return Optional.of(newValue); } }); // 每次得到当前所有单词的统计次数之后，将其写入mysql存储，进行持久化，以便于后续的J2EE应用程序 // 进行显示 wordCounts.foreachRDD(new Function
                       
                        
                         , Void>() { private static final long serialVersionUID = 1L; @Override public Void call(JavaPairRDD
                         
                           wordCountsRDD) throws Exception { // 调用RDD的foreachPartition()方法 wordCountsRDD.foreachPartition(new VoidFunction
                          
                           
                            
                             >>() { private static final long serialVersionUID = 1L; @Override public void call(Iterator
                             
                              
                               > wordCounts) throws Exception { // 给每个partition，获取一个连接 Connection conn = ConnectionPool.getConnection(); // 遍历partition中的数据，使用一个连接，插入数据库 Tuple2
                               
                                 wordCount = null; while(wordCounts.hasNext()) { wordCount = wordCounts.next(); String sql = "insert into wordcount(word,count) " + "values('" + wordCount._1 + "'," + wordCount._2 + ")"; Statement stmt = conn.createStatement(); stmt.executeUpdate(sql); } // 用完以后，将连接还回去 ConnectionPool.returnConnection(conn); } }); return null; } }); jssc.start(); jssc.awaitTermination(); jssc.close(); } }##运行脚本[root@spark1 streaming]# cat persistWordCount.sh /usr/local/spark-1.5.1-bin-hadoop2.4/bin/spark-submit \--class cn.spark.study.streaming.PersistWordCount \--num-executors 3 \--driver-memory 100m \--executor-memory 100m \--executor-cores 3 \--files /usr/local/hive/conf/hive-site.xml \--driver-class-path /usr/local/hive/lib/mysql-connector-java-5.1.17.jar \/usr/local/spark-study/java/streaming/saprk-study-java-0.0.1-SNAPSHOT-jar-with-dependencies.jar \##运行nc[root@spark1 ~]# nc -lk 9999hello wordhello wordhello java##结果mysql> use testdb;mysql> select * from wordcount;+----+---------------------+-------+-------+| id | updated_time | word | count |+----+---------------------+-------+-------+| 1 | 2019-08-19 14:52:45 | hello | 1 || 2 | 2019-08-19 14:52:45 | word | 1 || 3 | 2019-08-19 14:52:50 | hello | 2 || 4 | 2019-08-19 14:52:50 | word | 2 || 5 | 2019-08-19 14:52:55 | hello | 2 || 6 | 2019-08-19 14:52:55 | word | 2 || 7 | 2019-08-19 14:53:00 | hello | 2 || 8 | 2019-08-19 14:53:00 | word | 2 || 9 | 2019-08-19 14:53:05 | hello | 2 || 10 | 2019-08-19 14:53:05 | word | 2 || 11 | 2019-08-19 14:53:10 | hello | 2 || 12 | 2019-08-19 14:53:10 | word | 2 || 13 | 2019-08-19 14:53:15 | hello | 3 || 14 | 2019-08-19 14:53:15 | word | 2 || 15 | 2019-08-19 14:53:15 | java | 1 || 16 | 2019-08-19 14:53:20 | hello | 3 || 17 | 2019-08-19 14:53:20 | word | 2 || 18 | 2019-08-19 14:53:20 | java | 1 || 19 | 2019-08-19 14:53:25 | hello | 3 || 20 | 2019-08-19 14:53:25 | word | 2 || 21 | 2019-08-19 14:53:25 | java | 1 |+----+---------------------+-------+-------+21 rows in set (0.00 sec)