Hadoop 官方WordCount案例带你手把手的解析-低调大师

Hadoop 官方WordCount案例带你手把手的解析

2021-07-09 705

文章目录

1.需求

在给定的文本文件中统计输出每一个单词出现的总次数
hello.txt

hadoop hadoop
ss ss
cls cls
jiao
banzhang
xue

2.需求分析

3.项目结构图

4.项目依赖包

<dependencies>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>RELEASE</version>
    </dependency>
    <dependency>
        <groupId>org.apache.logging.log4j</groupId>
        <artifactId>log4j-core</artifactId>
        <version>2.8.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>2.7.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>2.7.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>2.7.2</version>
    </dependency>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>RELEASE</version>
        <scope>compile</scope>
    </dependency>

</dependencies>

5.编写Mapper

package wordcount_hdfs;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;


public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

//    0. 将创建对象的操作提取成变量，防止在 map 方法重复创建
    private Text text = new Text();
    private IntWritable i = new IntWritable(1);


    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 1. 将 Hadoop 内置的text 数据类型转换为string类型
        // 方便操作
        String string = value.toString();

        // 2. 对字符串进行切分
        String[] split = string.split(" ");

        // 3. 对字符串数组遍历，将单词映射成 （单词，1）
        for (String s : split) {
            text.set(s);
            context.write(text, i);
        }


    }
}

6.编写Reducer

package wordcount_hdfs;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;


public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {

    private IntWritable total  = new IntWritable();

  
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

        // 定义一个 sum，用来对每个键值对的 值 做 累加操作
        int sum = 0;

        for (IntWritable value : values) {
            int i = value.get();
            sum+=i;
        }
        total.set(sum);
        // 最后写出到文件
        context.write(key, total);

    }
}

7.编写Driver

package wordcount_hdfs;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;


public class WordCountDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        // 0 指定路径 这里路径有两种写法 ：
       args = new String[]{"E:\\Hadoop\\src\\main\\resources\\input", "E:\\Hadoop\\src\\main\\resources\\ouput"};
        //args = new String[]{"E:/Hadoop/src/main/resources/", "E:/Hadoop/src/main/resources/"};

// 1 获取配置信息configuration以及封装任务job
        Configuration configuration = new Configuration();

        Job job = Job.getInstance(configuration);

// 2 设置Driver加载路径 setJarByClass
        job.setJarByClass(WordCountDriver.class);
// 3 设置map和reduce类 setMaper setReducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
// 4 设置map输出   setmapoutputkey  setmapoutputvalue
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
// 5 设置最终输出kv类型 (reducer的输出kv类型) setoutoutkey  setoutputvalue
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
// 6 设置本地的输入和输出路径   fileinputformat.setinputpath
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 7 提交
        boolean completion = job.waitForCompletion(true);
        System.exit(completion ? 0 : 1);
    }
}

8.运行结果

出现如下所示就欧克，接着看结果

"D:\Program Files\Java\bin\java.exe" "-javaagent:D:\office\Program Files\IntelliJ2018.2.6\lib\idea_rt.jar=53527:D:\office\Program Files\IntelliJ2018.2.6\bin" -Dfile.encoding=UTF-8 -classpath "D:\Program Files\Java\jre\lib\charsets.jar;D:\Program Files\Java\jre\lib\deploy.jar;D:\Program Files\Java\jre\lib\ext\access-bridge-64.jar;D:\Program Files\Java\jre\lib\ext\cldrdata.jar;D:\Program Files\Java\jre\lib\ext\dnsns.jar;D:\Program Files\Java\jre\lib\ext\jaccess.jar;D:\Program Files\Java\jre\lib\ext\jfxrt.jar;D:\Program Files\Java\jre\lib\ext\localedata.jar;D:\Program Files\Java\jre\lib\ext\nashorn.jar;D:\Program Files\Java\jre\lib\ext\sunec.jar;D:\Program Files\Java\jre\lib\ext\sunjce_provider.jar;D:\Program Files\Java\jre\lib\ext\sunmscapi.jar;D:\Program Files\Java\jre\lib\ext\sunpkcs11.jar;D:\Program Files\Java\jre\lib\ext\zipfs.jar;D:\Program Files\Java\jre\lib\javaws.jar;D:\Program Files\Java\jre\lib\jce.jar;D:\Program Files\Java\jre\lib\jfr.jar;D:\Program Files\Java\jre\lib\jfxswt.jar;D:\Program Files\Java\jre\lib\jsse.jar;D:\Program Files\Java\jre\lib\management-agent.jar;D:\Program Files\Java\jre\lib\plugin.jar;D:\Program Files\Java\jre\lib\resources.jar;D:\Program Files\Java\jre\lib\rt.jar;E:\Hadoop\target\classes;C:\Users\Administrator\.m2\repository\junit\junit\4.13.1\junit-4.13.1.jar;C:\Users\Administrator\.m2\repository\org\hamcrest\hamcrest-core\1.3\hamcrest-core-1.3.jar;C:\Users\Administrator\.m2\repository\org\apache\logging\log4j\log4j-core\2.8.2\log4j-core-2.8.2.jar;C:\Users\Administrator\.m2\repository\org\apache\logging\log4j\log4j-api\2.8.2\log4j-api-2.8.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-common\2.7.2\hadoop-common-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-annotations\2.7.2\hadoop-annotations-2.7.2.jar;D:\Program Files\Java\lib\tools.jar;C:\Users\Administrator\.m2\repository\com\google\guava\guava\11.0.2\guava-11.0.2.jar;C:\Users\Administrator\.m2\repository\commons-cli\commons-cli\1.2\commons-cli-1.2.jar;C:\Users\Administrator\.m2\repository\org\apache\commons\commons-math3\3.1.1\commons-math3-3.1.1.jar;C:\Users\Administrator\.m2\repository\xmlenc\xmlenc\0.52\xmlenc-0.52.jar;C:\Users\Administrator\.m2\repository\commons-httpclient\commons-httpclient\3.1\commons-httpclient-3.1.jar;C:\Users\Administrator\.m2\repository\commons-codec\commons-codec\1.4\commons-codec-1.4.jar;C:\Users\Administrator\.m2\repository\commons-io\commons-io\2.4\commons-io-2.4.jar;C:\Users\Administrator\.m2\repository\commons-net\commons-net\3.1\commons-net-3.1.jar;C:\Users\Administrator\.m2\repository\commons-collections\commons-collections\3.2.2\commons-collections-3.2.2.jar;C:\Users\Administrator\.m2\repository\javax\servlet\servlet-api\2.5\servlet-api-2.5.jar;C:\Users\Administrator\.m2\repository\org\mortbay\jetty\jetty\6.1.26\jetty-6.1.26.jar;C:\Users\Administrator\.m2\repository\org\mortbay\jetty\jetty-util\6.1.26\jetty-util-6.1.26.jar;C:\Users\Administrator\.m2\repository\javax\servlet\jsp\jsp-api\2.1\jsp-api-2.1.jar;C:\Users\Administrator\.m2\repository\com\sun\jersey\jersey-core\1.9\jersey-core-1.9.jar;C:\Users\Administrator\.m2\repository\com\sun\jersey\jersey-json\1.9\jersey-json-1.9.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jettison\jettison\1.1\jettison-1.1.jar;C:\Users\Administrator\.m2\repository\com\sun\xml\bind\jaxb-impl\2.2.3-1\jaxb-impl-2.2.3-1.jar;C:\Users\Administrator\.m2\repository\javax\xml\bind\jaxb-api\2.2.2\jaxb-api-2.2.2.jar;C:\Users\Administrator\.m2\repository\javax\xml\stream\stax-api\1.0-2\stax-api-1.0-2.jar;C:\Users\Administrator\.m2\repository\javax\activation\activation\1.1\activation-1.1.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-jaxrs\1.8.3\jackson-jaxrs-1.8.3.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-xc\1.8.3\jackson-xc-1.8.3.jar;C:\Users\Administrator\.m2\repository\com\sun\jersey\jersey-server\1.9\jersey-server-1.9.jar;C:\Users\Administrator\.m2\repository\asm\asm\3.1\asm-3.1.jar;C:\Users\Administrator\.m2\repository\commons-logging\commons-logging\1.1.3\commons-logging-1.1.3.jar;C:\Users\Administrator\.m2\repository\log4j\log4j\1.2.17\log4j-1.2.17.jar;C:\Users\Administrator\.m2\repository\net\java\dev\jets3t\jets3t\0.9.0\jets3t-0.9.0.jar;C:\Users\Administrator\.m2\repository\org\apache\httpcomponents\httpclient\4.1.2\httpclient-4.1.2.jar;C:\Users\Administrator\.m2\repository\org\apache\httpcomponents\httpcore\4.1.2\httpcore-4.1.2.jar;C:\Users\Administrator\.m2\repository\com\jamesmurty\utils\java-xmlbuilder\0.4\java-xmlbuilder-0.4.jar;C:\Users\Administrator\.m2\repository\commons-lang\commons-lang\2.6\commons-lang-2.6.jar;C:\Users\Administrator\.m2\repository\commons-configuration\commons-configuration\1.6\commons-configuration-1.6.jar;C:\Users\Administrator\.m2\repository\commons-digester\commons-digester\1.8\commons-digester-1.8.jar;C:\Users\Administrator\.m2\repository\commons-beanutils\commons-beanutils\1.7.0\commons-beanutils-1.7.0.jar;C:\Users\Administrator\.m2\repository\commons-beanutils\commons-beanutils-core\1.8.0\commons-beanutils-core-1.8.0.jar;C:\Users\Administrator\.m2\repository\org\slf4j\slf4j-api\1.7.10\slf4j-api-1.7.10.jar;C:\Users\Administrator\.m2\repository\org\slf4j\slf4j-log4j12\1.7.10\slf4j-log4j12-1.7.10.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-core-asl\1.9.13\jackson-core-asl-1.9.13.jar;C:\Users\Administrator\.m2\repository\org\codehaus\jackson\jackson-mapper-asl\1.9.13\jackson-mapper-asl-1.9.13.jar;C:\Users\Administrator\.m2\repository\org\apache\avro\avro\1.7.4\avro-1.7.4.jar;C:\Users\Administrator\.m2\repository\com\thoughtworks\paranamer\paranamer\2.3\paranamer-2.3.jar;C:\Users\Administrator\.m2\repository\org\xerial\snappy\snappy-java\1.0.4.1\snappy-java-1.0.4.1.jar;C:\Users\Administrator\.m2\repository\com\google\protobuf\protobuf-java\2.5.0\protobuf-java-2.5.0.jar;C:\Users\Administrator\.m2\repository\com\google\code\gson\gson\2.2.4\gson-2.2.4.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-auth\2.7.2\hadoop-auth-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\server\apacheds-kerberos-codec\2.0.0-M15\apacheds-kerberos-codec-2.0.0-M15.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\server\apacheds-i18n\2.0.0-M15\apacheds-i18n-2.0.0-M15.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\api\api-asn1-api\1.0.0-M20\api-asn1-api-1.0.0-M20.jar;C:\Users\Administrator\.m2\repository\org\apache\directory\api\api-util\1.0.0-M20\api-util-1.0.0-M20.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-framework\2.7.1\curator-framework-2.7.1.jar;C:\Users\Administrator\.m2\repository\com\jcraft\jsch\0.1.42\jsch-0.1.42.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-client\2.7.1\curator-client-2.7.1.jar;C:\Users\Administrator\.m2\repository\org\apache\curator\curator-recipes\2.7.1\curator-recipes-2.7.1.jar;C:\Users\Administrator\.m2\repository\com\google\code\findbugs\jsr305\3.0.0\jsr305-3.0.0.jar;C:\Users\Administrator\.m2\repository\org\apache\htrace\htrace-core\3.1.0-incubating\htrace-core-3.1.0-incubating.jar;C:\Users\Administrator\.m2\repository\org\apache\zookeeper\zookeeper\3.4.6\zookeeper-3.4.6.jar;C:\Users\Administrator\.m2\repository\org\apache\commons\commons-compress\1.4.1\commons-compress-1.4.1.jar;C:\Users\Administrator\.m2\repository\org\tukaani\xz\1.0\xz-1.0.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-client\2.7.2\hadoop-client-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-app\2.7.2\hadoop-mapreduce-client-app-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-common\2.7.2\hadoop-mapreduce-client-common-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-client\2.7.2\hadoop-yarn-client-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-server-common\2.7.2\hadoop-yarn-server-common-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-shuffle\2.7.2\hadoop-mapreduce-client-shuffle-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-api\2.7.2\hadoop-yarn-api-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-core\2.7.2\hadoop-mapreduce-client-core-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-yarn-common\2.7.2\hadoop-yarn-common-2.7.2.jar;C:\Users\Administrator\.m2\repository\com\sun\jersey\jersey-client\1.9\jersey-client-1.9.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-mapreduce-client-jobclient\2.7.2\hadoop-mapreduce-client-jobclient-2.7.2.jar;C:\Users\Administrator\.m2\repository\org\apache\hadoop\hadoop-hdfs\2.7.2\hadoop-hdfs-2.7.2.jar;C:\Users\Administrator\.m2\repository\commons-daemon\commons-daemon\1.0.13\commons-daemon-1.0.13.jar;C:\Users\Administrator\.m2\repository\io\netty\netty\3.6.2.Final\netty-3.6.2.Final.jar;C:\Users\Administrator\.m2\repository\io\netty\netty-all\4.0.23.Final\netty-all-4.0.23.Final.jar;C:\Users\Administrator\.m2\repository\xerces\xercesImpl\2.9.1\xercesImpl-2.9.1.jar;C:\Users\Administrator\.m2\repository\xml-apis\xml-apis\1.3.04\xml-apis-1.3.04.jar;C:\Users\Administrator\.m2\repository\org\fusesource\leveldbjni\leveldbjni-all\1.8\leveldbjni-all-1.8.jar" KVText.KVTextDriver
2020-10-21 14:41:01,541 INFO [org.apache.hadoop.conf.Configuration.deprecation] - session.id is deprecated. Instead, use dfs.metrics.session-id
2020-10-21 14:41:01,551 INFO [org.apache.hadoop.metrics.jvm.JvmMetrics] - Initializing JVM Metrics with processName=JobTracker, sessionId=
2020-10-21 14:41:02,916 WARN [org.apache.hadoop.mapreduce.JobResourceUploader] - Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
2020-10-21 14:41:02,936 WARN [org.apache.hadoop.mapreduce.JobResourceUploader] - No job jar file set.  User classes may not be found. See Job or Job#setJar(String).
2020-10-21 14:41:03,236 INFO [org.apache.hadoop.mapreduce.lib.input.FileInputFormat] - Total input paths to process : 1
2020-10-21 14:41:03,256 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - number of splits:1
2020-10-21 14:41:03,326 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - Submitting tokens for job: job_local297471183_0001
2020-10-21 14:41:03,476 INFO [org.apache.hadoop.mapreduce.Job] - The url to track the job: http://localhost:8080/
2020-10-21 14:41:03,476 INFO [org.apache.hadoop.mapreduce.Job] - Running job: job_local297471183_0001
2020-10-21 14:41:03,476 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter set in config null
2020-10-21 14:41:03,486 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - File Output Committer Algorithm version is 1
2020-10-21 14:41:03,486 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
2020-10-21 14:41:03,536 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for map tasks
2020-10-21 14:41:03,536 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local297471183_0001_m_000000_0
2020-10-21 14:41:03,566 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - File Output Committer Algorithm version is 1
2020-10-21 14:41:03,576 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2020-10-21 14:41:03,616 INFO [org.apache.hadoop.mapred.Task] -  Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@6cec6fbe
2020-10-21 14:41:03,626 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/E:/Hadoop/src/main/resources/input/englishconment.txt:0+80
2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2020-10-21 14:41:03,666 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 
2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 48; bufvoid = 104857600
2020-10-21 14:41:03,676 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26214384(104857536); length = 13/6553600
2020-10-21 14:41:03,796 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
2020-10-21 14:41:03,806 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local297471183_0001_m_000000_0 is done. And is in the process of committing
2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - file:/E:/Hadoop/src/main/resources/input/englishconment.txt:0+80
2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local297471183_0001_m_000000_0' done.
2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local297471183_0001_m_000000_0
2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map task executor complete.
2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for reduce tasks
2020-10-21 14:41:03,826 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local297471183_0001_r_000000_0
2020-10-21 14:41:03,836 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - File Output Committer Algorithm version is 1
2020-10-21 14:41:03,836 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2020-10-21 14:41:04,115 INFO [org.apache.hadoop.mapred.Task] -  Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@2f6f6193
2020-10-21 14:41:04,115 INFO [org.apache.hadoop.mapred.ReduceTask] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@15648f8c
2020-10-21 14:41:04,135 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - MergerManager: memoryLimit=648858816, maxSingleShuffleLimit=162214704, mergeThreshold=428246848, ioSortFactor=10, memToMemMergeOutputsThreshold=10
2020-10-21 14:41:04,135 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - attempt_local297471183_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
2020-10-21 14:41:04,165 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local297471183_0001_m_000000_0 decomp: 58 len: 62 to MEMORY
2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 58 bytes from map-output for attempt_local297471183_0001_m_000000_0
2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of size: 58, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->58
2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - EventFetcher is interrupted.. Returning
2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2020-10-21 14:41:04,175 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
2020-10-21 14:41:04,195 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2020-10-21 14:41:04,195 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total size: 47 bytes
2020-10-21 14:41:04,205 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merged 1 segments, 58 bytes to disk to satisfy reduce memory limit
2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 1 files, 62 bytes from disk
2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 0 segments, 0 bytes from memory into reduce
2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total size: 47 bytes
2020-10-21 14:41:04,215 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2020-10-21 14:41:04,215 INFO [org.apache.hadoop.conf.Configuration.deprecation] - mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
2020-10-21 14:41:04,225 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local297471183_0001_r_000000_0 is done. And is in the process of committing
2020-10-21 14:41:04,225 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2020-10-21 14:41:04,225 INFO [org.apache.hadoop.mapred.Task] - Task attempt_local297471183_0001_r_000000_0 is allowed to commit now
2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - Saved output of task 'attempt_local297471183_0001_r_000000_0' to file:/E:/Hadoop/src/main/resources/ouput/_temporary/0/task_local297471183_0001_r_000000
2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce > reduce
2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local297471183_0001_r_000000_0' done.
2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local297471183_0001_r_000000_0
2020-10-21 14:41:04,235 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce task executor complete.
2020-10-21 14:41:04,485 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local297471183_0001 running in uber mode : false
2020-10-21 14:41:04,485 INFO [org.apache.hadoop.mapreduce.Job] -  map 100% reduce 100%
2020-10-21 14:41:04,485 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local297471183_0001 completed successfully
2020-10-21 14:41:04,515 INFO [org.apache.hadoop.mapreduce.Job] - Counters: 30
	File System Counters
		FILE: Number of bytes read=672
		FILE: Number of bytes written=583822
		FILE: Number of read operations=0
		FILE: Number of large read operations=0
		FILE: Number of write operations=0
	Map-Reduce Framework
		Map input records=4
		Map output records=4
		Map output bytes=48
		Map output materialized bytes=62
		Input split bytes=124
		Combine input records=0
		Combine output records=0
		Reduce input groups=2
		Reduce shuffle bytes=62
		Reduce input records=4
		Reduce output records=2
		Spilled Records=8
		Shuffled Maps =1
		Failed Shuffles=0
		Merged Map outputs=1
		GC time elapsed (ms)=12
		Total committed heap usage (bytes)=374865920
	Shuffle Errors
		BAD_ID=0
		CONNECTION=0
		IO_ERROR=0
		WRONG_LENGTH=0
		WRONG_MAP=0
		WRONG_REDUCE=0
	File Input Format Counters 
		Bytes Read=80
	File Output Format Counters 
		Bytes Written=32

Process finished with exit code 0

微信关注我们

原文链接：https://blog.51cto.com/u_15298458/3033253

转载内容版权归作者及来源网站所有！

低调大师中文资讯倾力打造互联网数据资讯、行业资源、电子商务、移动互联网、网络营销平台。持续更新报道IT业界、互联网、市场资讯、驱动更新,是最及时权威的产业资讯及硬件资讯报道平台。

spring boot+iview 前后端分离架构之数据字典模块布局和列表查询的实现（十二）

2 --> spring boot 与 iview 前后端分离架构之数据字典模块布局和列表查询的实现（十二）公众号数据字典数据字典列表布局数据字典列表查询搜索栏的实现数据列表的实现分页组件的实现加载数据字典数据到数据列表实现编辑和删除数据字典的数据大家可以直接微信扫描上面的二维码关注我的公众号，然后回复【bg12】里面就会给到源代码的下载地址同时会附上相应的视频教程，并定期在我的公众号上给大家推送相应的技术文章，欢迎大家关注我的公众号。数据字典以下就是我们实现数据字典的效果图：数据字典列表布局首先我们在开始开发我们的数据字典的时候我们需要设计好我们这个模块的布局，那么针对像这样增删改查的列表我基本是采用的是卡片式的布局，布局代码如下： <template> <div> <Card title="字典管理"> <div> <div style="display:inline-block;float:left;"> 这是一个按钮 </div> <div style="displa...

2021-07-09

674

2 --> 前言不论是校招还是社招都避免不了各种面试。笔试，如何去准备这些东西就显得格外重要。不论是笔试还是面试都是有章可循的，我这个有章可循‘说的意思只是说应对技术面试是可以提前准备。运筹帷幄之后，决胜千里之外!不打毫无准备的仗,我觉得大家可以先从下面几个方面来准备面试: 1.自我介绍。(你可千万这样介绍: “我叫某某，性别，来自哪里，学校是哪个，自己爱干什么”,记住:多说点简历_上没有的，多说点自己哪里比别人强! ) 2.自己面试中可能涉及哪些知识点、哪些知识点是重点。 3.面试中哪些问题会被经常问到、面试中自己该如何回答。(强烈不推荐背题，第一：通过背这种方式你能记住多少?能记住多久?第二:背题的方式的学习很难坚持下去! ) 4.自己的简历该如何写。 "80%的offer掌握在20%的人手中"这句话也不是不无道理的。决定你面试能否成功的因素中实力固然占有很大一部分比例，但是如果你的心态或者说运气不好的话，依然无法拿到满意的offer。运气暂且不谈,就拿心态来说，千万不要因为面试失败而气馁或者说怀疑自己的能力,面试失败之后多总结一下失败的原因，后面你就会发现自己会越来越强大。 ...

2021-07-09

512

资源下载

更多资源

优质分享App

近一个月的开发和优化，本站点的第一个app全新上线。该app采用极致压缩，本体才4.36MB。系统里面做了大量数据访问、缓存优化。方便用户在手机上查看文章。后续会推出HarmonyOS的适配版本。

腾讯云软件源

为解决软件依赖安装时官方源访问速度慢的问题，腾讯云为一些软件搭建了缓存服务。您可以通过使用腾讯云软件源站来提升依赖包的安装速度。为了方便用户自由搭建服务架构，目前腾讯云软件源站支持公网访问和内网访问。

Spring

Spring框架（Spring Framework）是由Rod Johnson于2002年提出的开源Java企业级应用框架，旨在通过使用JavaBean替代传统EJB实现方式降低企业级编程开发的复杂性。该框架基于简单性、可测试性和松耦合性设计理念，提供核心容器、应用上下文、数据访问集成等模块，支持整合Hibernate、Struts等第三方框架，其适用范围不仅限于服务器端开发，绝大多数Java应用均可从中受益。

Sublime Text

Sublime Text具有漂亮的用户界面和强大的功能，例如代码缩略图，Python的插件，代码段等。还可自定义键绑定，菜单和工具栏。Sublime Text 的主要功能包括：拼写检查，书签，完整的 Python API ， Goto 功能，即时项目切换，多选择，多窗口等等。Sublime Text 是一个跨平台的编辑器，同时支持Windows、Linux、Mac OS X等操作系统。