zoukankan      html  css  js  c++  java
  • Spark Streaming 例子

    NetworkWordCount.scala
    /*
     * Licensed to the Apache Software Foundation (ASF) under one or more
     * contributor license agreements.  See the NOTICE file distributed with
     * this work for additional information regarding copyright ownership.
     * The ASF licenses this file to You under the Apache License, Version 2.0
     * (the "License"); you may not use this file except in compliance with
     * the License.  You may obtain a copy of the License at
     *
     *    http://www.apache.org/licenses/LICENSE-2.0
     *
     * Unless required by applicable law or agreed to in writing, software
     * distributed under the License is distributed on an "AS IS" BASIS,
     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     * See the License for the specific language governing permissions and
     * limitations under the License.
     */
    
    // scalastyle:off println
    package com.gong.spark161.streaming
    
    import org.apache.spark.SparkConf
    import org.apache.spark.storage.StorageLevel
    import org.apache.spark.streaming.{Seconds, StreamingContext}
    
    /**
     * Counts words in UTF8 encoded, '
    ' delimited text received from the network every second.
     *
     * Usage: NetworkWordCount <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.NetworkWordCount localhost 9999`
     */
    object NetworkWordCount {
      def main(args: Array[String]) {
        if (args.length < 2) {
          System.err.println("Usage: NetworkWordCount <hostname> <port>")
          System.exit(1)
        }
    
        StreamingExamples.setStreamingLogLevels()
    
        // Create the context with a 1 second batch size
        val sparkConf = new SparkConf().setAppName("NetworkWordCount")
        val ssc = new StreamingContext(sparkConf, Seconds(1))
    
        // Create a socket stream on target ip:port and count the
        // words in input stream of 
     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.
          //socket监听网络请求创建stream   args(0)机器   args(1)端口号    StorageLevel存储级别
        val lines = ssc.socketTextStream(args(0), args(1).toInt, StorageLevel.MEMORY_AND_DISK_SER)
        val words = lines.flatMap(_.split(" "))
        val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _)
        wordCounts.print()
        ssc.start()
        ssc.awaitTermination()
      }
    }
    // scalastyle:on println

     下在集群跑一下

    监听1212端口(端口可以自己随便取)

     

    可以看到反馈信息

  • 相关阅读:
    jmeter实现multipart/form-data类型请求
    jmeter(正则提取器、json提取器)做接口关联
    windows使用ubuntu启动linux服务
    Jmeter+Ant+Jenkins环境搭建
    ubuntu网卡驱动的安装
    Ubuntu 挂载U盘
    Linux下安装jdk8步骤详述(转载)
    springboot项目:项目部署
    springboot项目:Redis缓存使用
    springboot项目:Redis分布式锁的使用(模拟秒杀系统)
  • 原文地址:https://www.cnblogs.com/braveym/p/7482197.html
Copyright © 2011-2022 走看看