早期的开发中经常用eclipse远程调试Hadoop集群,近期Idea的市场占有率逐渐增加,本文介绍如何在通过Idea远程调试Hadoop集群。
<configuration>
<property>
<name>hadoop.tmp.dirname>
<value>/home/hadoopadmin/hadoop/datavalue>
property>
<property>
<name>fs.defaultFSname>
<value>hdfs://L0:8020value>
property>
configuration>
<configuration>
<property>
<name>dfs.namenode.secondary.http-addressname>
<value>L0:50090value>
property>
<property>
<name>dfs.replicationname>
<value>2value>
property>
<property>
<name>dfs.namenode.http-addressname>
<value>L0:50070value>
property>
<property>
<name>dfs.datanode.data.dirname>
<value>file:///home/hadoopadmin/hadoop/data/dfs/dnvalue>
property>
configuration>
package com.edwin.hadooptest;
import java.io.IOException;
import java.util.StringTokenizer;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
public static class TokenizerMapper extends
Mapper<Object, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class IntSumReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args)
.getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount " );
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
job.setNumReduceTasks(2);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
log4j.properties
hadoop.root.logger=INFO,console
hadoop.log.dir=.
hadoop.log.file=hadoop.log
log4j.rootLogger=${hadoop.root.logger}, EventCounter
log4j.threshold=ALL
# Null Appender
log4j.appender.NullAppender=org.apache.log4j.varia.NullAppender
#
# Rolling File Appender - cap space usage at 5gb.
#
hadoop.log.maxfilesize=256MB
hadoop.log.maxbackupindex=20
log4j.appender.RFA=org.apache.log4j.RollingFileAppender
log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
log4j.appender.RFA.MaxFileSize=${hadoop.log.maxfilesize}
log4j.appender.RFA.MaxBackupIndex=${hadoop.log.maxbackupindex}
log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
# Pattern format: Date LogLevel LoggerName LogMessage
log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
# Debugging Pattern format
#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
#
# Daily Rolling File Appender
#
log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
# Rollver at midnight
log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
# 30-day backup
#log4j.appender.DRFA.MaxBackupIndex=30
log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
# Pattern format: Date LogLevel LoggerName LogMessage
log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
# Debugging Pattern format
#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
#
# console
# Add "console" to rootlogger above if you want to use this
#
log4j.appender.console=org.apache.log4j.ConsoleAppender
log4j.appender.console.target=System.err
log4j.appender.console.layout=org.apache.log4j.PatternLayout
log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
#
# TaskLog Appender
#
#Default values
hadoop.tasklog.taskid=null
hadoop.tasklog.iscleanup=false
hadoop.tasklog.noKeepSplits=4
hadoop.tasklog.totalLogFileSize=100
hadoop.tasklog.purgeLogSplits=true
hadoop.tasklog.logsRetainHours=12
log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
log4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}
log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
#
# HDFS block state change log from block manager
#
# Uncomment the following to suppress normal block state change
# messages from BlockManager in NameNode.
#log4j.logger.BlockStateChange=WARN
#
#Security appender
#
hadoop.security.logger=INFO,NullAppender
hadoop.security.log.maxfilesize=256MB
hadoop.security.log.maxbackupindex=20
log4j.category.SecurityLogger=${hadoop.security.logger}
hadoop.security.log.file=SecurityAuth-${user.name}.audit
log4j.appender.RFAS=org.apache.log4j.RollingFileAppender
log4j.appender.RFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
log4j.appender.RFAS.layout=org.apache.log4j.PatternLayout
log4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
log4j.appender.RFAS.MaxFileSize=${hadoop.security.log.maxfilesize}
log4j.appender.RFAS.MaxBackupIndex=${hadoop.security.log.maxbackupindex}
#
# Daily Rolling Security appender
#
log4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender
log4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
log4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout
log4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
log4j.appender.DRFAS.DatePattern=.yyyy-MM-dd
#
# hadoop configuration logging
#
# Uncomment the following line to turn off configuration deprecation warnings.
# log4j.logger.org.apache.hadoop.conf.Configuration.deprecation=WARN
#
# hdfs audit logging
#
hdfs.audit.logger=INFO,NullAppender
hdfs.audit.log.maxfilesize=256MB
hdfs.audit.log.maxbackupindex=20
log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}
log4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false
log4j.appender.RFAAUDIT=org.apache.log4j.RollingFileAppender
log4j.appender.RFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log
log4j.appender.RFAAUDIT.layout=org.apache.log4j.PatternLayout
log4j.appender.RFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
log4j.appender.RFAAUDIT.MaxFileSize=${hdfs.audit.log.maxfilesize}
log4j.appender.RFAAUDIT.MaxBackupIndex=${hdfs.audit.log.maxbackupindex}
#
# mapred audit logging
#
mapred.audit.logger=INFO,NullAppender
mapred.audit.log.maxfilesize=256MB
mapred.audit.log.maxbackupindex=20
log4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}
log4j.additivity.org.apache.hadoop.mapred.AuditLogger=false
log4j.appender.MRAUDIT=org.apache.log4j.RollingFileAppender
log4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log
log4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout
log4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
log4j.appender.MRAUDIT.MaxFileSize=${mapred.audit.log.maxfilesize}
log4j.appender.MRAUDIT.MaxBackupIndex=${mapred.audit.log.maxbackupindex}
# Custom Logging levels
#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
#log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=DEBUG
# Jets3t library
log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
# AWS SDK & S3A FileSystem
log4j.logger.com.amazonaws=ERROR
log4j.logger.com.amazonaws.http.AmazonHttpClient=ERROR
log4j.logger.org.apache.hadoop.fs.s3a.S3AFileSystem=WARN
#
# Event Counter Appender
# Sends counts of logging messages at different severity levels to Hadoop Metrics.
#
log4j.appender.EventCounter=org.apache.hadoop.log.metrics.EventCounter
#
# Job Summary Appender
#
# Use following logger to send summary to separate file defined by
# hadoop.mapreduce.jobsummary.log.file :
# hadoop.mapreduce.jobsummary.logger=INFO,JSA
#
hadoop.mapreduce.jobsummary.logger=${hadoop.root.logger}
hadoop.mapreduce.jobsummary.log.file=hadoop-mapreduce.jobsummary.log
hadoop.mapreduce.jobsummary.log.maxfilesize=256MB
hadoop.mapreduce.jobsummary.log.maxbackupindex=20
log4j.appender.JSA=org.apache.log4j.RollingFileAppender
log4j.appender.JSA.File=${hadoop.log.dir}/${hadoop.mapreduce.jobsummary.log.file}
log4j.appender.JSA.MaxFileSize=${hadoop.mapreduce.jobsummary.log.maxfilesize}
log4j.appender.JSA.MaxBackupIndex=${hadoop.mapreduce.jobsummary.log.maxbackupindex}
log4j.appender.JSA.layout=org.apache.log4j.PatternLayout
log4j.appender.JSA.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
log4j.logger.org.apache.hadoop.mapred.JobInProgress$JobSummary=${hadoop.mapreduce.jobsummary.logger}
log4j.additivity.org.apache.hadoop.mapred.JobInProgress$JobSummary=false
#
# Yarn ResourceManager Application Summary Log
#
# Set the ResourceManager summary log filename
yarn.server.resourcemanager.appsummary.log.file=rm-appsummary.log
# Set the ResourceManager summary log level and appender
yarn.server.resourcemanager.appsummary.logger=${hadoop.root.logger}
#yarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY
# To enable AppSummaryLogging for the RM,
# set yarn.server.resourcemanager.appsummary.logger to
# ,RMSUMMARY in hadoop-env.sh
# Appender for ResourceManager Application Summary Log
# Requires the following properties to be set
# - hadoop.log.dir (Hadoop Log directory)
# - yarn.server.resourcemanager.appsummary.log.file (resource manager app summary log filename)
# - yarn.server.resourcemanager.appsummary.logger (resource manager app summary log level and appender)
log4j.logger.org.apache.hadoop.yarn.server.resourcemanager.RMAppManager$ApplicationSummary=${yarn.server.resourcemanager.appsummary.logger}
log4j.additivity.org.apache.hadoop.yarn.server.resourcemanager.RMAppManager$ApplicationSummary=false
log4j.appender.RMSUMMARY=org.apache.log4j.RollingFileAppender
log4j.appender.RMSUMMARY.File=${hadoop.log.dir}/${yarn.server.resourcemanager.appsummary.log.file}
log4j.appender.RMSUMMARY.MaxFileSize=256MB
log4j.appender.RMSUMMARY.MaxBackupIndex=20
log4j.appender.RMSUMMARY.layout=org.apache.log4j.PatternLayout
log4j.appender.RMSUMMARY.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
# HS audit log configs
#mapreduce.hs.audit.logger=INFO,HSAUDIT
#log4j.logger.org.apache.hadoop.mapreduce.v2.hs.HSAuditLogger=${mapreduce.hs.audit.logger}
#log4j.additivity.org.apache.hadoop.mapreduce.v2.hs.HSAuditLogger=false
#log4j.appender.HSAUDIT=org.apache.log4j.DailyRollingFileAppender
#log4j.appender.HSAUDIT.File=${hadoop.log.dir}/hs-audit.log
#log4j.appender.HSAUDIT.layout=org.apache.log4j.PatternLayout
#log4j.appender.HSAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
#log4j.appender.HSAUDIT.DatePattern=.yyyy-MM-dd
# Http Server Request Logs
#log4j.logger.http.requests.namenode=INFO,namenoderequestlog
#log4j.appender.namenoderequestlog=org.apache.hadoop.http.HttpRequestLogAppender
#log4j.appender.namenoderequestlog.Filename=${hadoop.log.dir}/jetty-namenode-yyyy_mm_dd.log
#log4j.appender.namenoderequestlog.RetainDays=3
#log4j.logger.http.requests.datanode=INFO,datanoderequestlog
#log4j.appender.datanoderequestlog=org.apache.hadoop.http.HttpRequestLogAppender
#log4j.appender.datanoderequestlog.Filename=${hadoop.log.dir}/jetty-datanode-yyyy_mm_dd.log
#log4j.appender.datanoderequestlog.RetainDays=3
#log4j.logger.http.requests.resourcemanager=INFO,resourcemanagerrequestlog
#log4j.appender.resourcemanagerrequestlog=org.apache.hadoop.http.HttpRequestLogAppender
#log4j.appender.resourcemanagerrequestlog.Filename=${hadoop.log.dir}/jetty-resourcemanager-yyyy_mm_dd.log
#log4j.appender.resourcemanagerrequestlog.RetainDays=3
#log4j.logger.http.requests.jobhistory=INFO,jobhistoryrequestlog
#log4j.appender.jobhistoryrequestlog=org.apache.hadoop.http.HttpRequestLogAppender
#log4j.appender.jobhistoryrequestlog.Filename=${hadoop.log.dir}/jetty-jobhistory-yyyy_mm_dd.log
#log4j.appender.jobhistoryrequestlog.RetainDays=3
#log4j.logger.http.requests.nodemanager=INFO,nodemanagerrequestlog
#log4j.appender.nodemanagerrequestlog=org.apache.hadoop.http.HttpRequestLogAppender
#log4j.appender.nodemanagerrequestlog.Filename=${hadoop.log.dir}/jetty-nodemanager-yyyy_mm_dd.log
#log4j.appender.nodemanagerrequestlog.RetainDays=3