小提示
hadoop namenode -format 必须将将前面集群遗留的文件删除,不然datanode启动会失败
比需在resources下面给处hadoop集群的关键配置文件
wordcount 代码
package org.shangu.wordcount;
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.output.FileOutputFormat;
import java.io.IOException;
/**
* @author : kean
* @version V1.0
* @Project: hadoop_spark_java
* @Package org.shangu.wordcount
* @Description: TODO
* @date Date : 2019-05-02 15:58
*/
public class WordCountDriver {
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJobName("wordcount");
job.setJarByClass(WordCountDriver.class);
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean status = job.waitForCompletion(true);
System.out.println(status);
}
}
package org.shangu.wordcount;
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;
import java.util.StringTokenizer;
/**
* @author : kean
* @version V1.0
* @Project: hadoop_spark_java
* @Package org.shangu.wordcount
* @Description: TODO
* @date Date : 2019-05-02 15:23
*/
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private Text text = new Text();
private final static IntWritable value = new IntWritable(1);
@Override
public void map (LongWritable key, Text text, Context context ) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(text.toString());
while (itr.hasMoreTokens()) {
text.set(itr.nextToken());
context.write(text, value);
}
}
}
package org.shangu.wordcount;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* @author : kean
* @version V1.0
* @Project: hadoop_spark_java
* @Package org.shangu.wordcount
* @Description: TODO
* @date Date : 2019-05-02 15:39
*/
public class WordCountReducer extends Reducer<Text, IntWritable, Text,IntWritable> {
private IntWritable value = new IntWritable();
@Override
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
value.set(sum);
context.write(key, value);
}
}
执行环境变量
DHADOOP_USER_NAME=root取决于你的hdfs文件系统属于哪个用户
执行结果
D:\apps\jdk\bin\java.exe -DHADOOP_USER_NAME=root "-javaagent:D:\apps\IntelliJ IDEA 2019.1\lib\idea_rt.jar=14504:D:\apps\IntelliJ IDEA 2019.1\bin" -Dfile.encoding=UTF-8 -classpath D:\apps\jdk\jre\lib\charsets.jar;D:\apps\jdk\jre\lib\deploy.jar;D:\apps\jdk\jre\lib\ext\access-bridge-64.jar;D:\apps\jdk\jre\lib\ext\cldrdata.jar;D:\apps\jdk\jre\lib\ext\dnsns.jar;D:\apps\jdk\jre\lib\ext\jaccess.jar;D:\apps\jdk\jre\lib\ext\jfxrt.jar;D:\apps\jdk\jre\lib\ext\localedata.jar;D:\apps\jdk\jre\lib\ext\nashorn.jar;D:\apps\jdk\jre\lib\ext\sunec.jar;D:\apps\jdk\jre\lib\ext\sunjce_provider.jar;D:\apps\jdk\jre\lib\ext\sunmscapi.jar;D:\apps\jdk\jre\lib\ext\sunpkcs11.jar;D:\apps\jdk\jre\lib\ext\zipfs.jar;D:\apps\jdk\jre\lib\javaws.jar;D:\apps\jdk\jre\lib\jce.jar;D:\apps\jdk\jre\lib\jfr.jar;D:\apps\jdk\jre\lib\jfxswt.jar;D:\apps\jdk\jre\lib\jsse.jar;D:\apps\jdk\jre\lib\management-agent.jar;D:\apps\jdk\jre\lib\plugin.jar;D:\apps\jdk\jre\lib\resources.jar;D:\apps\jdk\jre\lib\rt.jar;D:\java_workspace\hadoop_spark_java\target\classes;D:\repository\org\apache\hadoop\hadoop-common\2.7.3\hadoop-common-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-annotations\2.7.3\hadoop-annotations-2.7.3.jar;D:\apps\jdk\lib\tools.jar;D:\repository\com\google\guava\guava\11.0.2\guava-11.0.2.jar;D:\repository\commons-cli\commons-cli\1.2\commons-cli-1.2.jar;D:\repository\org\apache\commons\commons-math3\3.1.1\commons-math3-3.1.1.jar;D:\repository\xmlenc\xmlenc\0.52\xmlenc-0.52.jar;D:\repository\commons-httpclient\commons-httpclient\3.1\commons-httpclient-3.1.jar;D:\repository\commons-codec\commons-codec\1.4\commons-codec-1.4.jar;D:\repository\commons-io\commons-io\2.4\commons-io-2.4.jar;D:\repository\commons-net\commons-net\3.1\commons-net-3.1.jar;D:\repository\commons-collections\commons-collections\3.2.2\commons-collections-3.2.2.jar;D:\repository\javax\servlet\servlet-api\2.5\servlet-api-2.5.jar;D:\repository\org\mortbay\jetty\jetty\6.1.26\jetty-6.1.26.jar;D:\repository\org\mortbay\jetty\jetty-util\6.1.26\jetty-util-6.1.26.jar;D:\repository\javax\servlet\jsp\jsp-api\2.1\jsp-api-2.1.jar;D:\repository\com\sun\jersey\jersey-core\1.9\jersey-core-1.9.jar;D:\repository\com\sun\jersey\jersey-json\1.9\jersey-json-1.9.jar;D:\repository\org\codehaus\jettison\jettison\1.1\jettison-1.1.jar;D:\repository\com\sun\xml\bind\jaxb-impl\2.2.3-1\jaxb-impl-2.2.3-1.jar;D:\repository\org\codehaus\jackson\jackson-jaxrs\1.8.3\jackson-jaxrs-1.8.3.jar;D:\repository\org\codehaus\jackson\jackson-xc\1.8.3\jackson-xc-1.8.3.jar;D:\repository\com\sun\jersey\jersey-server\1.9\jersey-server-1.9.jar;D:\repository\asm\asm\3.1\asm-3.1.jar;D:\repository\commons-logging\commons-logging\1.1.3\commons-logging-1.1.3.jar;D:\repository\net\java\dev\jets3t\jets3t\0.9.0\jets3t-0.9.0.jar;D:\repository\org\apache\httpcomponents\httpclient\4.1.2\httpclient-4.1.2.jar;D:\repository\org\apache\httpcomponents\httpcore\4.1.2\httpcore-4.1.2.jar;D:\repository\com\jamesmurty\utils\java-xmlbuilder\0.4\java-xmlbuilder-0.4.jar;D:\repository\commons-lang\commons-lang\2.6\commons-lang-2.6.jar;D:\repository\commons-configuration\commons-configuration\1.6\commons-configuration-1.6.jar;D:\repository\commons-digester\commons-digester\1.8\commons-digester-1.8.jar;D:\repository\commons-beanutils\commons-beanutils\1.7.0\commons-beanutils-1.7.0.jar;D:\repository\commons-beanutils\commons-beanutils-core\1.8.0\commons-beanutils-core-1.8.0.jar;D:\repository\org\slf4j\slf4j-api\1.7.10\slf4j-api-1.7.10.jar;D:\repository\org\slf4j\slf4j-log4j12\1.7.10\slf4j-log4j12-1.7.10.jar;D:\repository\org\codehaus\jackson\jackson-core-asl\1.9.13\jackson-core-asl-1.9.13.jar;D:\repository\org\codehaus\jackson\jackson-mapper-asl\1.9.13\jackson-mapper-asl-1.9.13.jar;D:\repository\org\apache\avro\avro\1.7.4\avro-1.7.4.jar;D:\repository\com\thoughtworks\paranamer\paranamer\2.3\paranamer-2.3.jar;D:\repository\com\google\protobuf\protobuf-java\2.5.0\protobuf-java-2.5.0.jar;D:\repository\com\google\code\gson\gson\2.2.4\gson-2.2.4.jar;D:\repository\org\apache\hadoop\hadoop-auth\2.7.3\hadoop-auth-2.7.3.jar;D:\repository\org\apache\directory\server\apacheds-kerberos-codec\2.0.0-M15\apacheds-kerberos-codec-2.0.0-M15.jar;D:\repository\org\apache\directory\server\apacheds-i18n\2.0.0-M15\apacheds-i18n-2.0.0-M15.jar;D:\repository\org\apache\directory\api\api-asn1-api\1.0.0-M20\api-asn1-api-1.0.0-M20.jar;D:\repository\org\apache\directory\api\api-util\1.0.0-M20\api-util-1.0.0-M20.jar;D:\repository\org\apache\curator\curator-framework\2.7.1\curator-framework-2.7.1.jar;D:\repository\com\jcraft\jsch\0.1.42\jsch-0.1.42.jar;D:\repository\org\apache\curator\curator-client\2.7.1\curator-client-2.7.1.jar;D:\repository\org\apache\curator\curator-recipes\2.7.1\curator-recipes-2.7.1.jar;D:\repository\com\google\code\findbugs\jsr305\3.0.0\jsr305-3.0.0.jar;D:\repository\org\apache\htrace\htrace-core\3.1.0-incubating\htrace-core-3.1.0-incubating.jar;D:\repository\org\apache\zookeeper\zookeeper\3.4.6\zookeeper-3.4.6.jar;D:\repository\org\apache\commons\commons-compress\1.4.1\commons-compress-1.4.1.jar;D:\repository\org\tukaani\xz\1.0\xz-1.0.jar;D:\repository\org\apache\hadoop\hadoop-mapreduce-client-core\2.7.3\hadoop-mapreduce-client-core-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-yarn-common\2.7.3\hadoop-yarn-common-2.7.3.jar;D:\repository\javax\xml\bind\jaxb-api\2.2.2\jaxb-api-2.2.2.jar;D:\repository\javax\xml\stream\stax-api\1.0-2\stax-api-1.0-2.jar;D:\repository\javax\activation\activation\1.1\activation-1.1.jar;D:\repository\com\sun\jersey\jersey-client\1.9\jersey-client-1.9.jar;D:\repository\com\google\inject\guice\3.0\guice-3.0.jar;D:\repository\javax\inject\javax.inject\1\javax.inject-1.jar;D:\repository\aopalliance\aopalliance\1.0\aopalliance-1.0.jar;D:\repository\com\sun\jersey\contribs\jersey-guice\1.9\jersey-guice-1.9.jar;D:\repository\com\google\inject\extensions\guice-servlet\3.0\guice-servlet-3.0.jar;D:\repository\io\netty\netty\3.6.2.Final\netty-3.6.2.Final.jar;D:\repository\org\apache\spark\spark-core_2.11\2.2.1\spark-core_2.11-2.2.1.jar;D:\repository\org\apache\avro\avro-mapred\1.7.7\avro-mapred-1.7.7-hadoop2.jar;D:\repository\org\apache\avro\avro-ipc\1.7.7\avro-ipc-1.7.7.jar;D:\repository\org\apache\avro\avro-ipc\1.7.7\avro-ipc-1.7.7-tests.jar;D:\repository\com\twitter\chill_2.11\0.8.0\chill_2.11-0.8.0.jar;D:\repository\com\esotericsoftware\kryo-shaded\3.0.3\kryo-shaded-3.0.3.jar;D:\repository\com\esotericsoftware\minlog\1.3.0\minlog-1.3.0.jar;D:\repository\org\objenesis\objenesis\2.1\objenesis-2.1.jar;D:\repository\com\twitter\chill-java\0.8.0\chill-java-0.8.0.jar;D:\repository\org\apache\xbean\xbean-asm5-shaded\4.4\xbean-asm5-shaded-4.4.jar;D:\repository\org\apache\spark\spark-launcher_2.11\2.2.1\spark-launcher_2.11-2.2.1.jar;D:\repository\org\apache\spark\spark-network-common_2.11\2.2.1\spark-network-common_2.11-2.2.1.jar;D:\repository\org\fusesource\leveldbjni\leveldbjni-all\1.8\leveldbjni-all-1.8.jar;D:\repository\com\fasterxml\jackson\core\jackson-annotations\2.6.5\jackson-annotations-2.6.5.jar;D:\repository\org\apache\spark\spark-network-shuffle_2.11\2.2.1\spark-network-shuffle_2.11-2.2.1.jar;D:\repository\org\apache\spark\spark-unsafe_2.11\2.2.1\spark-unsafe_2.11-2.2.1.jar;D:\repository\javax\servlet\javax.servlet-api\3.1.0\javax.servlet-api-3.1.0.jar;D:\repository\org\apache\commons\commons-lang3\3.5\commons-lang3-3.5.jar;D:\repository\org\slf4j\jul-to-slf4j\1.7.16\jul-to-slf4j-1.7.16.jar;D:\repository\org\slf4j\jcl-over-slf4j\1.7.16\jcl-over-slf4j-1.7.16.jar;D:\repository\com\ning\compress-lzf\1.0.3\compress-lzf-1.0.3.jar;D:\repository\org\xerial\snappy\snappy-java\1.1.2.6\snappy-java-1.1.2.6.jar;D:\repository\net\jpountz\lz4\lz4\1.3.0\lz4-1.3.0.jar;D:\repository\org\roaringbitmap\RoaringBitmap\0.5.11\RoaringBitmap-0.5.11.jar;D:\repository\org\scala-lang\scala-library\2.11.8\scala-library-2.11.8.jar;D:\repository\org\json4s\json4s-jackson_2.11\3.2.11\json4s-jackson_2.11-3.2.11.jar;D:\repository\org\json4s\json4s-core_2.11\3.2.11\json4s-core_2.11-3.2.11.jar;D:\repository\org\json4s\json4s-ast_2.11\3.2.11\json4s-ast_2.11-3.2.11.jar;D:\repository\org\scala-lang\scalap\2.11.0\scalap-2.11.0.jar;D:\repository\org\scala-lang\scala-compiler\2.11.0\scala-compiler-2.11.0.jar;D:\repository\org\scala-lang\modules\scala-xml_2.11\1.0.1\scala-xml_2.11-1.0.1.jar;D:\repository\org\scala-lang\modules\scala-parser-combinators_2.11\1.0.1\scala-parser-combinators_2.11-1.0.1.jar;D:\repository\org\glassfish\jersey\core\jersey-client\2.22.2\jersey-client-2.22.2.jar;D:\repository\javax\ws\rs\javax.ws.rs-api\2.0.1\javax.ws.rs-api-2.0.1.jar;D:\repository\org\glassfish\hk2\hk2-api\2.4.0-b34\hk2-api-2.4.0-b34.jar;D:\repository\org\glassfish\hk2\hk2-utils\2.4.0-b34\hk2-utils-2.4.0-b34.jar;D:\repository\org\glassfish\hk2\external\aopalliance-repackaged\2.4.0-b34\aopalliance-repackaged-2.4.0-b34.jar;D:\repository\org\glassfish\hk2\external\javax.inject\2.4.0-b34\javax.inject-2.4.0-b34.jar;D:\repository\org\glassfish\hk2\hk2-locator\2.4.0-b34\hk2-locator-2.4.0-b34.jar;D:\repository\org\javassist\javassist\3.18.1-GA\javassist-3.18.1-GA.jar;D:\repository\org\glassfish\jersey\core\jersey-common\2.22.2\jersey-common-2.22.2.jar;D:\repository\javax\annotation\javax.annotation-api\1.2\javax.annotation-api-1.2.jar;D:\repository\org\glassfish\jersey\bundles\repackaged\jersey-guava\2.22.2\jersey-guava-2.22.2.jar;D:\repository\org\glassfish\hk2\osgi-resource-locator\1.0.1\osgi-resource-locator-1.0.1.jar;D:\repository\org\glassfish\jersey\core\jersey-server\2.22.2\jersey-server-2.22.2.jar;D:\repository\org\glassfish\jersey\media\jersey-media-jaxb\2.22.2\jersey-media-jaxb-2.22.2.jar;D:\repository\javax\validation\validation-api\1.1.0.Final\validation-api-1.1.0.Final.jar;D:\repository\org\glassfish\jersey\containers\jersey-container-servlet\2.22.2\jersey-container-servlet-2.22.2.jar;D:\repository\org\glassfish\jersey\containers\jersey-container-servlet-core\2.22.2\jersey-container-servlet-core-2.22.2.jar;D:\repository\io\netty\netty-all\4.0.43.Final\netty-all-4.0.43.Final.jar;D:\repository\com\clearspring\analytics\stream\2.7.0\stream-2.7.0.jar;D:\repository\io\dropwizard\metrics\metrics-core\3.1.2\metrics-core-3.1.2.jar;D:\repository\io\dropwizard\metrics\metrics-jvm\3.1.2\metrics-jvm-3.1.2.jar;D:\repository\io\dropwizard\metrics\metrics-json\3.1.2\metrics-json-3.1.2.jar;D:\repository\io\dropwizard\metrics\metrics-graphite\3.1.2\metrics-graphite-3.1.2.jar;D:\repository\com\fasterxml\jackson\core\jackson-databind\2.6.5\jackson-databind-2.6.5.jar;D:\repository\com\fasterxml\jackson\core\jackson-core\2.6.5\jackson-core-2.6.5.jar;D:\repository\com\fasterxml\jackson\module\jackson-module-scala_2.11\2.6.5\jackson-module-scala_2.11-2.6.5.jar;D:\repository\org\scala-lang\scala-reflect\2.11.7\scala-reflect-2.11.7.jar;D:\repository\com\fasterxml\jackson\module\jackson-module-paranamer\2.6.5\jackson-module-paranamer-2.6.5.jar;D:\repository\org\apache\ivy\ivy\2.4.0\ivy-2.4.0.jar;D:\repository\oro\oro\2.0.8\oro-2.0.8.jar;D:\repository\net\razorvine\pyrolite\4.13\pyrolite-4.13.jar;D:\repository\net\sf\py4j\py4j\0.10.4\py4j-0.10.4.jar;D:\repository\org\apache\spark\spark-tags_2.11\2.2.1\spark-tags_2.11-2.2.1.jar;D:\repository\org\apache\commons\commons-crypto\1.0.0\commons-crypto-1.0.0.jar;D:\repository\org\spark-project\spark\unused\1.0.0\unused-1.0.0.jar;D:\repository\org\apache\commons\commons-math\2.2\commons-math-2.2.jar;D:\repository\org\apache\hadoop\hadoop-client\2.7.3\hadoop-client-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-hdfs\2.7.3\hadoop-hdfs-2.7.3.jar;D:\repository\xerces\xercesImpl\2.9.1\xercesImpl-2.9.1.jar;D:\repository\xml-apis\xml-apis\1.3.04\xml-apis-1.3.04.jar;D:\repository\org\apache\hadoop\hadoop-mapreduce-client-app\2.7.3\hadoop-mapreduce-client-app-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-mapreduce-client-common\2.7.3\hadoop-mapreduce-client-common-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-yarn-client\2.7.3\hadoop-yarn-client-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-yarn-server-common\2.7.3\hadoop-yarn-server-common-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-mapreduce-client-shuffle\2.7.3\hadoop-mapreduce-client-shuffle-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-yarn-api\2.7.3\hadoop-yarn-api-2.7.3.jar;D:\repository\org\apache\hadoop\hadoop-mapreduce-client-jobclient\2.7.3\hadoop-mapreduce-client-jobclient-2.7.3.jar;D:\repository\log4j\log4j\1.2.17\log4j-1.2.17.jar org.shangu.wordcount.WordCountDriver /wordcount/input /wordcount/output
2019-05-02 17:17:21 [main] [INFO] - session.id is deprecated. Instead, use dfs.metrics.session-id
2019-05-02 17:17:21 [main] [INFO] - Initializing JVM Metrics with processName=JobTracker, sessionId=
2019-05-02 17:17:32 [main] [WARN] - Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
2019-05-02 17:17:32 [main] [WARN] - No job jar file set. User classes may not be found. See Job or Job#setJar(String).
2019-05-02 17:17:32 [main] [INFO] - Total input paths to process : 1
2019-05-02 17:17:32 [main] [INFO] - number of splits:1
2019-05-02 17:17:32 [main] [INFO] - Submitting tokens for job: job_local1926305669_0001
2019-05-02 17:17:32 [main] [INFO] - The url to track the job: http://localhost:8080/
2019-05-02 17:17:32 [main] [INFO] - Running job: job_local1926305669_0001
2019-05-02 17:17:32 [Thread-4] [INFO] - OutputCommitter set in config null
2019-05-02 17:17:32 [Thread-4] [INFO] - File Output Committer Algorithm version is 1
2019-05-02 17:17:32 [Thread-4] [INFO] - OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
2019-05-02 17:17:32 [Thread-4] [INFO] - Waiting for map tasks
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - Starting task: attempt_local1926305669_0001_m_000000_0
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - File Output Committer Algorithm version is 1
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - ProcfsBasedProcessTree currently is supported only on Linux.
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@68c046f0
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - Processing split: hdfs://172.16.21.220:9000/wordcount/input/xiyouji.txt:0+2171334
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - (EQUATOR) 0 kvi 26214396(104857584)
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - mapreduce.task.io.sort.mb: 100
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - soft limit at 83886080
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - bufstart = 0; bufvoid = 104857600
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - kvstart = 26214396; length = 6553600
2019-05-02 17:17:32 [LocalJobRunner Map Task Executor #0] [INFO] - Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
2019-05-02 17:17:33 [main] [INFO] - Job job_local1926305669_0001 running in uber mode : false
2019-05-02 17:17:33 [main] [INFO] - map 0% reduce 0%
2019-05-02 17:17:33 [LocalJobRunner Map Task Executor #0] [INFO] - Found UTF-8 BOM and skipped it
2019-05-02 17:17:33 [LocalJobRunner Map Task Executor #0] [INFO] -
2019-05-02 17:17:33 [LocalJobRunner Map Task Executor #0] [INFO] - Starting flush of map output
2019-05-02 17:17:33 [LocalJobRunner Map Task Executor #0] [INFO] - Spilling map output
2019-05-02 17:17:33 [LocalJobRunner Map Task Executor #0] [INFO] - bufstart = 0; bufend = 2169960; bufvoid = 104857600
2019-05-02 17:17:33 [LocalJobRunner Map Task Executor #0] [INFO] - kvstart = 26214396(104857584); kvend = 26200740(104802960); length = 13657/6553600
2019-05-02 17:17:33 [LocalJobRunner Map Task Executor #0] [INFO] - Finished spill 0
2019-05-02 17:17:34 [LocalJobRunner Map Task Executor #0] [INFO] - Task:attempt_local1926305669_0001_m_000000_0 is done. And is in the process of committing
2019-05-02 17:17:34 [LocalJobRunner Map Task Executor #0] [INFO] - map
2019-05-02 17:17:34 [LocalJobRunner Map Task Executor #0] [INFO] - Task 'attempt_local1926305669_0001_m_000000_0' done.
2019-05-02 17:17:34 [LocalJobRunner Map Task Executor #0] [INFO] - Finishing task: attempt_local1926305669_0001_m_000000_0
2019-05-02 17:17:34 [Thread-4] [INFO] - map task executor complete.
2019-05-02 17:17:34 [Thread-4] [INFO] - Waiting for reduce tasks
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Starting task: attempt_local1926305669_0001_r_000000_0
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - File Output Committer Algorithm version is 1
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - ProcfsBasedProcessTree currently is supported only on Linux.
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@1e712dff
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@3cbb9b3e
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - MergerManager: memoryLimit=2650485504, maxSingleShuffleLimit=662621376, mergeThreshold=1749320448, ioSortFactor=10, memToMemMergeOutputsThreshold=10
2019-05-02 17:17:34 [EventFetcher for fetching Map Completion Events] [INFO] - attempt_local1926305669_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
2019-05-02 17:17:34 [localfetcher#1] [INFO] - localfetcher#1 about to shuffle output of map attempt_local1926305669_0001_m_000000_0 decomp: 2181848 len: 2181852 to MEMORY
2019-05-02 17:17:34 [localfetcher#1] [INFO] - Read 2181848 bytes from map-output for attempt_local1926305669_0001_m_000000_0
2019-05-02 17:17:34 [localfetcher#1] [INFO] - closeInMemoryFile -> map-output of size: 2181848, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->2181848
2019-05-02 17:17:34 [EventFetcher for fetching Map Completion Events] [INFO] - EventFetcher is interrupted.. Returning
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - 1 / 1 copied.
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Merging 1 sorted segments
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Down to the last merge-pass, with 1 segments left of total size: 2181830 bytes
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Merged 1 segments, 2181848 bytes to disk to satisfy reduce memory limit
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Merging 1 files, 2181852 bytes from disk
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Merging 0 segments, 0 bytes from memory into reduce
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Merging 1 sorted segments
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Down to the last merge-pass, with 1 segments left of total size: 2181830 bytes
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - 1 / 1 copied.
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
2019-05-02 17:17:34 [main] [INFO] - map 100% reduce 0%
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Task:attempt_local1926305669_0001_r_000000_0 is done. And is in the process of committing
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - 1 / 1 copied.
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Task attempt_local1926305669_0001_r_000000_0 is allowed to commit now
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Saved output of task 'attempt_local1926305669_0001_r_000000_0' to hdfs://172.16.21.220:9000/wordcount/output/_temporary/0/task_local1926305669_0001_r_000000
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - reduce > reduce
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Task 'attempt_local1926305669_0001_r_000000_0' done.
2019-05-02 17:17:34 [pool-6-thread-1] [INFO] - Finishing task: attempt_local1926305669_0001_r_000000_0
2019-05-02 17:17:34 [Thread-4] [INFO] - reduce task executor complete.
2019-05-02 17:17:35 [main] [INFO] - map 100% reduce 100%
2019-05-02 17:17:35 [main] [INFO] - Job job_local1926305669_0001 completed successfully
2019-05-02 17:17:35 [main] [INFO] - Counters: 35
File System Counters
FILE: Number of bytes read=4364098
FILE: Number of bytes written=7117898
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=4342668
HDFS: Number of bytes written=2156551
HDFS: Number of read operations=13
HDFS: Number of large read operations=0
HDFS: Number of write operations=4
Map-Reduce Framework
Map input records=6823
Map output records=3415
Map output bytes=2169960
Map output materialized bytes=2181852
Input split bytes=118
Combine input records=0
Combine output records=0
Reduce input groups=3311
Reduce shuffle bytes=2181852
Reduce input records=3415
Reduce output records=3311
Spilled Records=6830
Shuffled Maps =1
Failed Shuffles=0
Merged Map outputs=1
GC time elapsed (ms)=9
Total committed heap usage (bytes)=508035072
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=2171334
File Output Format Counters
Bytes Written=2156551
true
Process finished with exit code 0