第51课：HadoopMapReduce多维排序解析与实战
2016-02-26 23:02
537 查看
基于以下的失败过程，我们修改了数据文件再测试了一次，将tab分割改成了逗号“，”，相应的程序里面也进行了修改String[] splited = data.split(",");，再次运行，测试ok
数据文件
[root@master IMFdatatest]#hadoop dfs -cat /library/dataForMutipleSorting.txt
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
16/02/27 04:01:55 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Spark,100
Hadoop,60
Kafka,95
Spark,99
Hadoop,65
Kafka,98
Spark,99
Hadoop,63
Kafka,97
[root@master IMFdatatest]#hadoop dfs -cat /library/outputdataForMutipleSorting8/part-r-00000
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
16/02/27 04:04:11 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Hadoop 60,63,65
Kafka 95,97,98
Spark 99,99,100
运行结果
失败要查原因
问题定位：数组越界
是数据读入时解析有问题，我们先搞一个随机数来测试，而将读入的数据屏蔽，程序可以运行了。说明算法没有问题。
int splited1 = (int)(Math.random() * 1000);
// intMultiplePair.setSecond(Integer.valueOf(splited[1]));
// intWritable.set(Integer.valueOf(splited[1]));
intMultiplePair.setSecond(splited1); //排除数据预处理问题
intWritable.set(splited1);
输出结果
[root@master IMFdatatest]#hadoop dfs -cat /library/outputdataForMutipleSorting6/part-r-00000
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
16/02/26 19:41:26 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Hadoop 223,377
Hadoop 63 481
Kafka 147,188
Kafka 97 991
Spark 542,613
Spark 99 244
[root@master IMFdatatest]#
1、数据文件
[root@master IMFdatatest]#hadoop dfs -cat /library/dataForMutipleSorting.txt
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
16/02/26 07:56:52 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Spark 100
Hadoop 60
Kafka 95
Spark 99
Hadoop 65
Kafka 98
Spark 99
Hadoop 63
Kafka 97
2、运行结果失败
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:456) 2016-02-26 23:00:04,681 ---- map task executor complete.
WARN [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:560) 2016-02-26 23:00:05,687 ---- job_local1144770356_0001
java.lang.Exception: java.lang.ArrayIndexOutOfBoundsException: 1
at org.apache.hadoop.mapred.LocalJobRunner$Job.runTasks(LocalJobRunner.java:462)
at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:522)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 1
at com.dtspark.hadoop.hellomapreduce.MutipleSorting$DataMapper.map(MutipleSorting.java:40)
at com.dtspark.hadoop.hellomapreduce.MutipleSorting$DataMapper.map(MutipleSorting.java:1)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:784)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:243)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
打的日志
INFO [main] (org.apache.hadoop.conf.Configuration.deprecation:1049) 2016-02-26 22:59:53,289 ---- session.id is deprecated. Instead, use dfs.metrics.session-id
INFO [main] (org.apache.hadoop.metrics.jvm.JvmMetrics:76) 2016-02-26 22:59:53,296 ---- Initializing JVM Metrics with processName=JobTracker, sessionId=
WARN [main] (org.apache.hadoop.mapreduce.JobSubmitter:261) 2016-02-26 22:59:54,773 ---- No job jar file set. User classes may not be found. See Job or Job#setJar(String).
INFO [main] (org.apache.hadoop.mapreduce.lib.input.FileInputFormat:281) 2016-02-26 22:59:54,848 ---- Total input paths to process : 1
INFO [main] (org.apache.hadoop.mapreduce.JobSubmitter:494) 2016-02-26 22:59:55,276 ---- number of splits:1
INFO [main] (org.apache.hadoop.mapreduce.JobSubmitter:583) 2016-02-26 22:59:55,743 ---- Submitting tokens for job: job_local1144770356_0001
INFO [main] (org.apache.hadoop.mapreduce.Job:1300) 2016-02-26 22:59:56,147 ---- The url to track the job:http://localhost:8080/
INFO [main] (org.apache.hadoop.mapreduce.Job:1345) 2016-02-26 22:59:56,147 ---- Running job: job_local1144770356_0001
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:471) 2016-02-26 22:59:56,150 ---- OutputCommitter set in config null
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:489) 2016-02-26 22:59:56,162 ---- OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:448) 2016-02-26 22:59:56,362 ---- Waiting for map tasks
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:224) 2016-02-26 22:59:56,363 ---- Starting task: attempt_local1144770356_0001_m_000000_0
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.yarn.util.ProcfsBasedProcessTree:181) 2016-02-26 22:59:56,489 ---- ProcfsBasedProcessTree currently is supported only on Linux.
INFO [main] (org.apache.hadoop.mapreduce.Job:1366) 2016-02-26 22:59:57,150 ---- Job job_local1144770356_0001 running in uber mode : false
INFO [main] (org.apache.hadoop.mapreduce.Job:1373) 2016-02-26 22:59:57,232 ---- map 0% reduce 0%
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.Task:587) 2016-02-26 22:59:57,697 ---- Using ResourceCalculatorProcessTree :org.apache.hadoop.yarn.util.WindowsBasedProcessTree@1fa97f4
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:753) 2016-02-26 22:59:57,731 ---- Processing split: hdfs://192.168.2.100:9000/library/dataForMutipleSorting.txt:0+90
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1202) 2016-02-26 22:59:57,979 ---- (EQUATOR) 0 kvi 26214396(104857584)
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:995) 2016-02-26 22:59:57,979 ---- mapreduce.task.io.sort.mb: 100
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:996) 2016-02-26 22:59:57,980 ---- soft limit at 83886080
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:997) 2016-02-26 22:59:57,980 ---- bufstart = 0; bufvoid = 104857600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:998) 2016-02-26 22:59:57,980 ---- kvstart = 26214396; length = 6553600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:402) 2016-02-26 22:59:58,010 ---- Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
Map Methond Invoked!!!
Spark
100
100
Map Methond Invoked!!!
Hadoop
60
60
Map Methond Invoked!!!
Kafka
95
95
Map Methond Invoked!!!
Spark
99
99
Map Methond Invoked!!!
Hadoop
65
65
Map Methond Invoked!!!
Kafka
98
98
Map Methond Invoked!!!
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1457) 2016-02-26 23:00:01,125 ---- Starting flush of map output
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1475) 2016-02-26 23:00:01,125 ---- Spilling map output
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1476) 2016-02-26 23:00:01,125 ---- bufstart = 0; bufend = 92; bufvoid = 104857600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1478) 2016-02-26 23:00:01,125 ---- kvstart = 26214396(104857584); kvend = 26214376(104857504); length = 21/6553600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1660) 2016-02-26 23:00:03,684 ---- Finished spill 0
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:456) 2016-02-26 23:00:04,681 ---- map task executor complete.
WARN [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:560) 2016-02-26 23:00:05,687 ---- job_local1144770356_0001
java.lang.Exception: java.lang.ArrayIndexOutOfBoundsException: 1
at org.apache.hadoop.mapred.LocalJobRunner$Job.runTasks(LocalJobRunner.java:462)
at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:522)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 1
at com.dtspark.hadoop.hellomapreduce.MutipleSorting$DataMapper.map(MutipleSorting.java:40)
at com.dtspark.hadoop.hellomapreduce.MutipleSorting$DataMapper.map(MutipleSorting.java:1)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:784)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:243)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
INFO [main] (org.apache.hadoop.mapreduce.Job:1386) 2016-02-26 23:00:06,265 ---- Job job_local1144770356_0001 failed with state FAILED due to: NA
INFO [communication thread] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-26 23:00:06,403 ---- map > sort
INFO [main] (org.apache.hadoop.mapreduce.Job:1391) 2016-02-26 23:00:06,647 ---- Counters: 25
File System Counters
FILE: Number of bytes read=175
FILE: Number of bytes written=254813
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=90
HDFS: Number of bytes written=0
HDFS: Number of read operations=4
HDFS: Number of large read operations=0
HDFS: Number of write operations=2
Map-Reduce Framework
Map input records=7
Map output records=6
Map output bytes=92
Map output materialized bytes=110
Input split bytes=124
Combine input records=0
Spilled Records=6
Failed Shuffles=0
Merged Map outputs=0
GC time elapsed (ms)=25
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
Total committed heap usage (bytes)=234754048
File Input Format Counters
Bytes Read=90
3、源代码
package com.dtspark.hadoop.hellomapreduce;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
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 MutipleSorting {
public static class DataMapper
extends Mapper<LongWritable, Text, IntMultiplePair, IntWritable>{
private IntMultiplePair intMultiplePair = new IntMultiplePair();
private IntWritable intWritable = new IntWritable(0);
public void map(LongWritable key, Text value, Context context
) throws IOException, InterruptedException {
System.out.println("Map Methond Invoked!!!");
String data = value.toString();
String[] splited = data.split("\t");
intMultiplePair.setFirst(splited[0]);
intMultiplePair.setSecond(Integer.valueOf(splited[1]));
intWritable.set(Integer.valueOf(splited[1]));
System.out.println(intMultiplePair.getFirst());
System.out.println(intMultiplePair.getSecond());
System.out.println(intWritable);
context.write(intMultiplePair, intWritable);
}
}
public static class DataReducer
extends Reducer<IntMultiplePair,IntWritable,Text, Text> {
public void reduce(IntMultiplePair key , Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
System.out.println("Reduce Methond Invoked!!!" );
StringBuffer buffered = new StringBuffer();
Iterator<IntWritable> iter = values.iterator();
while(iter.hasNext()){
buffered.append(iter.next().get() + ",");
}
int length = buffered.toString().length();
String result = buffered.toString().substring(0, length -1);
context.write(new Text(key.getFirst()), new Text(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: MutlpleSorting <in> [<in>...] <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "MutlpleSorting");
job.setJarByClass(MutipleSorting.class);
job.setMapperClass(DataMapper.class);
job.setReducerClass(DataReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapOutputKeyClass(IntMultiplePair.class);
job.setMapOutputValueClass(IntWritable.class);
job.setPartitionerClass(MyMultipleSortingPartitioner.class);
job.setSortComparatorClass(IntMultipleSortingComparator.class);
job.setGroupingComparatorClass(GroupingMultipleComparator.class);
for (int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job,
new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
class IntMultiplePair implements WritableComparable<IntMultiplePair>{
private String first;
private int second;
public String getFirst() {
return first;
}
public void setFirst(String first) {
this.first = first;
}
public int getSecond() {
return second;
}
public void setSecond(int second) {
this.second = second;
}
public IntMultiplePair(){}
public IntMultiplePair(String first, int second) {
this.first = first;
this.second = second;
}
@Override
public void readFields(DataInput input) throws IOException {
this.first = input.readUTF();
this.second = input.readInt();
}
@Override
public void write(DataOutput output) throws IOException {
output.writeUTF(this.first);
output.writeInt(this.second);
}
@Override
public int compareTo(IntMultiplePair o) {
return 0;
}
}
class IntMultipleSortingComparator extends WritableComparator{
public IntMultipleSortingComparator(){
super(IntMultiplePair.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
IntMultiplePair x = (IntMultiplePair)a;
IntMultiplePair y = (IntMultiplePair)b;
if(!x.getFirst().equals(y.getFirst())){
return x.getFirst().compareTo(y.getFirst());
} else {
return x.getSecond() - y.getSecond();
}
}
}
class GroupingMultipleComparator extends WritableComparator{
public GroupingMultipleComparator(){
super(IntMultiplePair.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
IntMultiplePair x = (IntMultiplePair)a;
IntMultiplePair y = (IntMultiplePair)b;
return x.getFirst().compareTo(y.getFirst());
}
}
class MyMultipleSortingPartitioner extends Partitioner<IntMultiplePair, IntWritable>{
@Override
public int getPartition(IntMultiplePair arg0, IntWritable arg1, int arg2) {
return (arg0.getFirst().hashCode() & Integer.MAX_VALUE)%arg2;
}
}
完整的代码
package com.dtspark.hadoop.hellomapreduce;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
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 MutipleSorting {
public static class DataMapper
extends Mapper<LongWritable, Text, IntMultiplePair, IntWritable>{
private IntMultiplePair intMultiplePair = new IntMultiplePair();
private IntWritable intWritable = new IntWritable(0);
public void map(LongWritable key, Text value, Context context
) throws IOException, InterruptedException {
System.out.println("Map Methond Invoked!!!");
String data = value.toString();
// String[] splited = data.split("\t");
String[] splited = data.split(",");
intMultiplePair.setFirst(splited[0]);
intMultiplePair.setSecond(Integer.valueOf(splited[1]));
intWritable.set(Integer.valueOf(splited[1]));
context.write(intMultiplePair, intWritable);
}
}
public static class DataReducer
extends Reducer<IntMultiplePair,IntWritable,Text, Text> {
public void reduce(IntMultiplePair key , Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
System.out.println("Reduce Methond Invoked!!!" );
StringBuffer buffered = new StringBuffer();
Iterator<IntWritable> iter = values.iterator();
while(iter.hasNext()){
buffered.append(iter.next().get() + ",");
}
int length = buffered.toString().length();
String result = buffered.toString().substring(0, length -1);
context.write(new Text(key.getFirst()), new Text(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: MutlpleSorting <in> [<in>...] <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "MutlpleSorting");
job.setJarByClass(MutipleSorting.class);
job.setMapperClass(DataMapper.class);
job.setReducerClass(DataReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapOutputKeyClass(IntMultiplePair.class);
job.setMapOutputValueClass(IntWritable.class);
job.setPartitionerClass(MyMultipleSortingPartitioner.class);
job.setSortComparatorClass(IntMultipleSortingComparator.class);
job.setGroupingComparatorClass(GroupingMultipleComparator.class);
for (int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job,
new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
class IntMultiplePair implements WritableComparable<IntMultiplePair>{
private String first;
private int second;
public String getFirst() {
return first;
}
public void setFirst(String first) {
this.first = first;
}
public int getSecond() {
return second;
}
public void setSecond(int second) {
this.second = second;
}
public IntMultiplePair(){}
public IntMultiplePair(String first, int second) {
this.first = first;
this.second = second;
}
@Override
public void readFields(DataInput input) throws IOException {
this.first = input.readUTF();
this.second = input.readInt();
}
@Override
public void write(DataOutput output) throws IOException {
output.writeUTF(this.first);
output.writeInt(this.second);
}
@Override
public int compareTo(IntMultiplePair o) {
return 0;
}
}
class IntMultipleSortingComparator extends WritableComparator{
public IntMultipleSortingComparator(){
super(IntMultiplePair.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
IntMultiplePair x = (IntMultiplePair)a;
IntMultiplePair y = (IntMultiplePair)b;
if(!x.getFirst().equals(y.getFirst())){
System.out.println("排序开始了，比较第一个first： " +x.getFirst() +" "+ y.getFirst() +" "+ x.getFirst().compareTo(y.getFirst()));
return x.getFirst().compareTo(y.getFirst());
} else {
System.out.println("排序开始了，比较第二个second： " +x.getSecond() +" "+ y.getSecond() +" " +( x.getSecond() - y.getSecond()));
return x.getSecond() - y.getSecond();
}
}
}
class GroupingMultipleComparator extends WritableComparator{
public GroupingMultipleComparator(){
super(IntMultiplePair.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
IntMultiplePair x = (IntMultiplePair)a;
IntMultiplePair y = (IntMultiplePair)b;
System.out.println("分组开始了 : " +x.getFirst() +" "+ y.getFirst() +" "+ x.getFirst().compareTo(y.getFirst()));
return x.getFirst().compareTo(y.getFirst());
}
}
class MyMultipleSortingPartitioner extends Partitioner<IntMultiplePair, IntWritable>{
@Override
public int getPartition(IntMultiplePair arg0, IntWritable arg1, int arg2) {
System.out.println("getPartition分区的计算过程 ！！！！！！！ " +arg0.getFirst().hashCode() +" " + Integer.MAX_VALUE + arg2);
System.out.println("getPartition的值 " + (arg0.getFirst().hashCode() & Integer.MAX_VALUE)%arg2);
return (arg0.getFirst().hashCode() & Integer.MAX_VALUE)%arg2;
}
}
打得日志
INFO [main] (org.apache.hadoop.conf.Configuration.deprecation:1049) 2016-02-27 17:32:57,577 ---- session.id is deprecated. Instead, use dfs.metrics.session-id
INFO [main] (org.apache.hadoop.metrics.jvm.JvmMetrics:76) 2016-02-27 17:32:57,582 ---- Initializing JVM Metrics with processName=JobTracker, sessionId=
WARN [main] (org.apache.hadoop.mapreduce.JobSubmitter:261) 2016-02-27 17:32:57,978 ---- No job jar file set. User classes may not be found. See Job or Job#setJar(String).
INFO [main] (org.apache.hadoop.mapreduce.lib.input.FileInputFormat:281) 2016-02-27 17:32:58,014 ---- Total input paths to process : 1
INFO [main] (org.apache.hadoop.mapreduce.JobSubmitter:494) 2016-02-27 17:32:58,092 ---- number of splits:1
INFO [main] (org.apache.hadoop.mapreduce.JobSubmitter:583) 2016-02-27 17:32:58,167 ---- Submitting tokens for job: job_local1851923379_0001
INFO [main] (org.apache.hadoop.mapreduce.Job:1300) 2016-02-27 17:32:58,358 ---- The url to track the job:
http://localhost:8080/
INFO [main] (org.apache.hadoop.mapreduce.Job:1345) 2016-02-27 17:32:58,359 ---- Running job: job_local1851923379_0001
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:471) 2016-02-27 17:32:58,360 ---- OutputCommitter set in config null
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:489) 2016-02-27 17:32:58,367 ---- OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:448) 2016-02-27 17:32:58,415 ---- Waiting for map tasks
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:224) 2016-02-27 17:32:58,415 ---- Starting task: attempt_local1851923379_0001_m_000000_0
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.yarn.util.ProcfsBasedProcessTree:181) 2016-02-27 17:32:58,447 ---- ProcfsBasedProcessTree currently is supported only on Linux.
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.Task:587) 2016-02-27 17:32:58,986 ---- Using ResourceCalculatorProcessTree :
org.apache.hadoop.yarn.util.WindowsBasedProcessTree@16c89e
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:753) 2016-02-27 17:32:58,991 ---- Processing split: hdfs://192.168.2.100:9000/library/dataForMutipleSorting.txt:0+85
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1202) 2016-02-27 17:32:59,082 ---- (EQUATOR) 0 kvi 26214396(104857584)
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:995) 2016-02-27 17:32:59,083 ---- mapreduce.task.io.sort.mb: 100
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:996) 2016-02-27 17:32:59,083 ---- soft limit at 83886080
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:997) 2016-02-27 17:32:59,083 ---- bufstart = 0; bufvoid = 104857600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:998) 2016-02-27 17:32:59,083 ---- kvstart = 26214396; length = 6553600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:402) 2016-02-27 17:32:59,087 ---- Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
INFO [main] (org.apache.hadoop.mapreduce.Job:1366) 2016-02-27 17:32:59,362 ---- Job job_local1851923379_0001 running in uber mode : false
INFO [main] (org.apache.hadoop.mapreduce.Job:1373) 2016-02-27 17:32:59,363 ---- map 0% reduce 0%
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,086 ----
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1457) 2016-02-27 17:33:00,089 ---- Starting flush of map output
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1475) 2016-02-27 17:33:00,089 ---- Spilling map output
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1476) 2016-02-27 17:33:00,089 ---- bufstart = 0; bufend = 138; bufvoid = 104857600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1478) 2016-02-27 17:33:00,089 ---- kvstart = 26214396(104857584); kvend = 26214364(104857456); length = 33/6553600
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第一个first： Kafka Spark -8
排序开始了，比较第一个first： Spark Kafka 8
排序开始了，比较第二个second： 97 98 -1
排序开始了，比较第一个first： Spark Hadoop 11
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第二个second： 63 65 -2
排序开始了，比较第二个second： 99 99 0
排序开始了，比较第一个first： Spark Kafka 8
排序开始了，比较第一个first： Spark Kafka 8
排序开始了，比较第二个second： 98 95 3
排序开始了，比较第二个second： 97 95 2
排序开始了，比较第一个first： Hadoop Kafka -3
排序开始了，比较第一个first： Spark Hadoop 11
排序开始了，比较第一个first： Spark Hadoop 11
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第二个second： 65 60 5
排序开始了，比较第二个second： 63 60 3
排序开始了，比较第二个second： 99 100 -1
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1660) 2016-02-27 17:33:00,166 ---- Finished spill 0
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.Task:1001) 2016-02-27 17:33:00,178 ---- Task:attempt_local1851923379_0001_m_000000_0 is done. And is in the process of committing
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,195 ---- map
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.Task:1121) 2016-02-27 17:33:00,196 ---- Task 'attempt_local1851923379_0001_m_000000_0' done.
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:249) 2016-02-27 17:33:00,196 ---- Finishing task: attempt_local1851923379_0001_m_000000_0
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:456) 2016-02-27 17:33:00,196 ---- map task executor complete.
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:448) 2016-02-27 17:33:00,198 ---- Waiting for reduce tasks
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:302) 2016-02-27 17:33:00,199 ---- Starting task: attempt_local1851923379_0001_r_000000_0
INFO [pool-6-thread-1] (org.apache.hadoop.yarn.util.ProcfsBasedProcessTree:181) 2016-02-27 17:33:00,207 ---- ProcfsBasedProcessTree currently is supported only on Linux.
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Task:587) 2016-02-27 17:33:00,326 ---- Using ResourceCalculatorProcessTree :
org.apache.hadoop.yarn.util.WindowsBasedProcessTree@675767
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.ReduceTask:362) 2016-02-27 17:33:00,330 ---- Using ShuffleConsumerPlugin:
org.apache.hadoop.mapreduce.task.reduce.Shuffle@902038
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:196) 2016-02-27 17:33:00,345 ---- MergerManager: memoryLimit=363285696, maxSingleShuffleLimit=90821424, mergeThreshold=239768576, ioSortFactor=10, memToMemMergeOutputsThreshold=10
INFO [EventFetcher for fetching Map Completion Events] (org.apache.hadoop.mapreduce.task.reduce.EventFetcher:61) 2016-02-27 17:33:00,349 ---- attempt_local1851923379_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
INFO [main] (org.apache.hadoop.mapreduce.Job:1373) 2016-02-27 17:33:00,365 ---- map 100% reduce 0%
INFO [localfetcher#1] (org.apache.hadoop.mapreduce.task.reduce.LocalFetcher:141) 2016-02-27 17:33:00,392 ---- localfetcher#1 about to shuffle output of map attempt_local1851923379_0001_m_000000_0 decomp: 158 len: 162 to MEMORY
INFO [localfetcher#1] (org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput:100) 2016-02-27 17:33:00,397 ---- Read 158 bytes from map-output for attempt_local1851923379_0001_m_000000_0
INFO [localfetcher#1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:314) 2016-02-27 17:33:00,400 ---- closeInMemoryFile -> map-output of size: 158, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->158
INFO [EventFetcher for fetching Map Completion Events] (org.apache.hadoop.mapreduce.task.reduce.EventFetcher:76) 2016-02-27 17:33:00,402 ---- EventFetcher is interrupted.. Returning
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,403 ---- 1 / 1 copied.
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:674) 2016-02-27 17:33:00,403 ---- finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Merger:597) 2016-02-27 17:33:00,422 ---- Merging 1 sorted segments
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Merger:696) 2016-02-27 17:33:00,423 ---- Down to the last merge-pass, with 1 segments left of total size: 144 bytes
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:751) 2016-02-27 17:33:00,426 ---- Merged 1 segments, 158 bytes to disk to satisfy reduce memory limit
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:781) 2016-02-27 17:33:00,427 ---- Merging 1 files, 162 bytes from disk
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:796) 2016-02-27 17:33:00,429 ---- Merging 0 segments, 0 bytes from memory into reduce
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Merger:597) 2016-02-27 17:33:00,429 ---- Merging 1 sorted segments
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Merger:696) 2016-02-27 17:33:00,431 ---- Down to the last merge-pass, with 1 segments left of total size: 144 bytes
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,431 ---- 1 / 1 copied.
INFO [pool-6-thread-1] (org.apache.hadoop.conf.Configuration.deprecation:1049) 2016-02-27 17:33:00,453 ---- mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
分组开始了 : Hadoop Hadoop 0
Reduce Methond Invoked!!!
分组开始了 : Hadoop Hadoop 0
分组开始了 : Hadoop Kafka -3
分组开始了 : Kafka Kafka 0
Reduce Methond Invoked!!!
分组开始了 : Kafka Kafka 0
分组开始了 : Kafka Spark -8
分组开始了 : Spark Spark 0
Reduce Methond Invoked!!!
分组开始了 : Spark Spark 0
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Task:1001) 2016-02-27 17:33:00,560 ---- Task:attempt_local1851923379_0001_r_000000_0 is done. And is in the process of committing
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,563 ---- 1 / 1 copied.
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Task:1162) 2016-02-27 17:33:00,563 ---- Task attempt_local1851923379_0001_r_000000_0 is allowed to commit now
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter:439) 2016-02-27 17:33:00,573 ---- Saved output of task 'attempt_local1851923379_0001_r_000000_0' to hdfs://192.168.2.100:9000/library/outputdataForMutipleSorting12/_temporary/0/task_local1851923379_0001_r_000000
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,574 ---- reduce > reduce
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Task:1121) 2016-02-27 17:33:00,574 ---- Task 'attempt_local1851923379_0001_r_000000_0' done.
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:325) 2016-02-27 17:33:00,574 ---- Finishing task: attempt_local1851923379_0001_r_000000_0
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:456) 2016-02-27 17:33:00,574 ---- reduce task executor complete.
INFO [main] (org.apache.hadoop.mapreduce.Job:1373) 2016-02-27 17:33:01,365 ---- map 100% reduce 100%
INFO [main] (org.apache.hadoop.mapreduce.Job:1384) 2016-02-27 17:33:01,367 ---- Job job_local1851923379_0001 completed successfully
INFO [main] (org.apache.hadoop.mapreduce.Job:1391) 2016-02-27 17:33:01,412 ---- Counters: 38
File System Counters
FILE: Number of bytes read=706
FILE: Number of bytes written=509896
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=170
HDFS: Number of bytes written=47
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=9
Map output records=9
Map output bytes=138
Map output materialized bytes=162
Input split bytes=124
Combine input records=0
Combine output records=0
Reduce input groups=3
Reduce shuffle bytes=162
Reduce input records=9
Reduce output records=3
Spilled Records=18
Shuffled Maps =1
Failed Shuffles=0
Merged Map outputs=1
GC time elapsed (ms)=23
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
Total committed heap usage (bytes)=469508096
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=85
File Output Format Counters
Bytes Written=47
数据文件
[root@master IMFdatatest]#hadoop dfs -cat /library/dataForMutipleSorting.txt
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
16/02/27 04:01:55 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Spark,100
Hadoop,60
Kafka,95
Spark,99
Hadoop,65
Kafka,98
Spark,99
Hadoop,63
Kafka,97
[root@master IMFdatatest]#hadoop dfs -cat /library/outputdataForMutipleSorting8/part-r-00000
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
16/02/27 04:04:11 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Hadoop 60,63,65
Kafka 95,97,98
Spark 99,99,100
运行结果
失败要查原因
问题定位：数组越界
是数据读入时解析有问题，我们先搞一个随机数来测试，而将读入的数据屏蔽，程序可以运行了。说明算法没有问题。
int splited1 = (int)(Math.random() * 1000);
// intMultiplePair.setSecond(Integer.valueOf(splited[1]));
// intWritable.set(Integer.valueOf(splited[1]));
intMultiplePair.setSecond(splited1); //排除数据预处理问题
intWritable.set(splited1);
输出结果
[root@master IMFdatatest]#hadoop dfs -cat /library/outputdataForMutipleSorting6/part-r-00000
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
16/02/26 19:41:26 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Hadoop 223,377
Hadoop 63 481
Kafka 147,188
Kafka 97 991
Spark 542,613
Spark 99 244
[root@master IMFdatatest]#
1、数据文件
[root@master IMFdatatest]#hadoop dfs -cat /library/dataForMutipleSorting.txt
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.
16/02/26 07:56:52 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Spark 100
Hadoop 60
Kafka 95
Spark 99
Hadoop 65
Kafka 98
Spark 99
Hadoop 63
Kafka 97
2、运行结果失败
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:456) 2016-02-26 23:00:04,681 ---- map task executor complete.
WARN [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:560) 2016-02-26 23:00:05,687 ---- job_local1144770356_0001
java.lang.Exception: java.lang.ArrayIndexOutOfBoundsException: 1
at org.apache.hadoop.mapred.LocalJobRunner$Job.runTasks(LocalJobRunner.java:462)
at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:522)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 1
at com.dtspark.hadoop.hellomapreduce.MutipleSorting$DataMapper.map(MutipleSorting.java:40)
at com.dtspark.hadoop.hellomapreduce.MutipleSorting$DataMapper.map(MutipleSorting.java:1)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:784)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:243)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
打的日志
INFO [main] (org.apache.hadoop.conf.Configuration.deprecation:1049) 2016-02-26 22:59:53,289 ---- session.id is deprecated. Instead, use dfs.metrics.session-id
INFO [main] (org.apache.hadoop.metrics.jvm.JvmMetrics:76) 2016-02-26 22:59:53,296 ---- Initializing JVM Metrics with processName=JobTracker, sessionId=
WARN [main] (org.apache.hadoop.mapreduce.JobSubmitter:261) 2016-02-26 22:59:54,773 ---- No job jar file set. User classes may not be found. See Job or Job#setJar(String).
INFO [main] (org.apache.hadoop.mapreduce.lib.input.FileInputFormat:281) 2016-02-26 22:59:54,848 ---- Total input paths to process : 1
INFO [main] (org.apache.hadoop.mapreduce.JobSubmitter:494) 2016-02-26 22:59:55,276 ---- number of splits:1
INFO [main] (org.apache.hadoop.mapreduce.JobSubmitter:583) 2016-02-26 22:59:55,743 ---- Submitting tokens for job: job_local1144770356_0001
INFO [main] (org.apache.hadoop.mapreduce.Job:1300) 2016-02-26 22:59:56,147 ---- The url to track the job:http://localhost:8080/
INFO [main] (org.apache.hadoop.mapreduce.Job:1345) 2016-02-26 22:59:56,147 ---- Running job: job_local1144770356_0001
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:471) 2016-02-26 22:59:56,150 ---- OutputCommitter set in config null
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:489) 2016-02-26 22:59:56,162 ---- OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:448) 2016-02-26 22:59:56,362 ---- Waiting for map tasks
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:224) 2016-02-26 22:59:56,363 ---- Starting task: attempt_local1144770356_0001_m_000000_0
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.yarn.util.ProcfsBasedProcessTree:181) 2016-02-26 22:59:56,489 ---- ProcfsBasedProcessTree currently is supported only on Linux.
INFO [main] (org.apache.hadoop.mapreduce.Job:1366) 2016-02-26 22:59:57,150 ---- Job job_local1144770356_0001 running in uber mode : false
INFO [main] (org.apache.hadoop.mapreduce.Job:1373) 2016-02-26 22:59:57,232 ---- map 0% reduce 0%
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.Task:587) 2016-02-26 22:59:57,697 ---- Using ResourceCalculatorProcessTree :org.apache.hadoop.yarn.util.WindowsBasedProcessTree@1fa97f4
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:753) 2016-02-26 22:59:57,731 ---- Processing split: hdfs://192.168.2.100:9000/library/dataForMutipleSorting.txt:0+90
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1202) 2016-02-26 22:59:57,979 ---- (EQUATOR) 0 kvi 26214396(104857584)
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:995) 2016-02-26 22:59:57,979 ---- mapreduce.task.io.sort.mb: 100
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:996) 2016-02-26 22:59:57,980 ---- soft limit at 83886080
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:997) 2016-02-26 22:59:57,980 ---- bufstart = 0; bufvoid = 104857600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:998) 2016-02-26 22:59:57,980 ---- kvstart = 26214396; length = 6553600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:402) 2016-02-26 22:59:58,010 ---- Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
Map Methond Invoked!!!
Spark
100
100
Map Methond Invoked!!!
Hadoop
60
60
Map Methond Invoked!!!
Kafka
95
95
Map Methond Invoked!!!
Spark
99
99
Map Methond Invoked!!!
Hadoop
65
65
Map Methond Invoked!!!
Kafka
98
98
Map Methond Invoked!!!
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1457) 2016-02-26 23:00:01,125 ---- Starting flush of map output
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1475) 2016-02-26 23:00:01,125 ---- Spilling map output
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1476) 2016-02-26 23:00:01,125 ---- bufstart = 0; bufend = 92; bufvoid = 104857600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1478) 2016-02-26 23:00:01,125 ---- kvstart = 26214396(104857584); kvend = 26214376(104857504); length = 21/6553600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1660) 2016-02-26 23:00:03,684 ---- Finished spill 0
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:456) 2016-02-26 23:00:04,681 ---- map task executor complete.
WARN [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:560) 2016-02-26 23:00:05,687 ---- job_local1144770356_0001
java.lang.Exception: java.lang.ArrayIndexOutOfBoundsException: 1
at org.apache.hadoop.mapred.LocalJobRunner$Job.runTasks(LocalJobRunner.java:462)
at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:522)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 1
at com.dtspark.hadoop.hellomapreduce.MutipleSorting$DataMapper.map(MutipleSorting.java:40)
at com.dtspark.hadoop.hellomapreduce.MutipleSorting$DataMapper.map(MutipleSorting.java:1)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:784)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:243)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
INFO [main] (org.apache.hadoop.mapreduce.Job:1386) 2016-02-26 23:00:06,265 ---- Job job_local1144770356_0001 failed with state FAILED due to: NA
INFO [communication thread] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-26 23:00:06,403 ---- map > sort
INFO [main] (org.apache.hadoop.mapreduce.Job:1391) 2016-02-26 23:00:06,647 ---- Counters: 25
File System Counters
FILE: Number of bytes read=175
FILE: Number of bytes written=254813
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=90
HDFS: Number of bytes written=0
HDFS: Number of read operations=4
HDFS: Number of large read operations=0
HDFS: Number of write operations=2
Map-Reduce Framework
Map input records=7
Map output records=6
Map output bytes=92
Map output materialized bytes=110
Input split bytes=124
Combine input records=0
Spilled Records=6
Failed Shuffles=0
Merged Map outputs=0
GC time elapsed (ms)=25
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
Total committed heap usage (bytes)=234754048
File Input Format Counters
Bytes Read=90
3、源代码
package com.dtspark.hadoop.hellomapreduce;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
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 MutipleSorting {
public static class DataMapper
extends Mapper<LongWritable, Text, IntMultiplePair, IntWritable>{
private IntMultiplePair intMultiplePair = new IntMultiplePair();
private IntWritable intWritable = new IntWritable(0);
public void map(LongWritable key, Text value, Context context
) throws IOException, InterruptedException {
System.out.println("Map Methond Invoked!!!");
String data = value.toString();
String[] splited = data.split("\t");
intMultiplePair.setFirst(splited[0]);
intMultiplePair.setSecond(Integer.valueOf(splited[1]));
intWritable.set(Integer.valueOf(splited[1]));
System.out.println(intMultiplePair.getFirst());
System.out.println(intMultiplePair.getSecond());
System.out.println(intWritable);
context.write(intMultiplePair, intWritable);
}
}
public static class DataReducer
extends Reducer<IntMultiplePair,IntWritable,Text, Text> {
public void reduce(IntMultiplePair key , Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
System.out.println("Reduce Methond Invoked!!!" );
StringBuffer buffered = new StringBuffer();
Iterator<IntWritable> iter = values.iterator();
while(iter.hasNext()){
buffered.append(iter.next().get() + ",");
}
int length = buffered.toString().length();
String result = buffered.toString().substring(0, length -1);
context.write(new Text(key.getFirst()), new Text(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: MutlpleSorting <in> [<in>...] <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "MutlpleSorting");
job.setJarByClass(MutipleSorting.class);
job.setMapperClass(DataMapper.class);
job.setReducerClass(DataReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapOutputKeyClass(IntMultiplePair.class);
job.setMapOutputValueClass(IntWritable.class);
job.setPartitionerClass(MyMultipleSortingPartitioner.class);
job.setSortComparatorClass(IntMultipleSortingComparator.class);
job.setGroupingComparatorClass(GroupingMultipleComparator.class);
for (int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job,
new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
class IntMultiplePair implements WritableComparable<IntMultiplePair>{
private String first;
private int second;
public String getFirst() {
return first;
}
public void setFirst(String first) {
this.first = first;
}
public int getSecond() {
return second;
}
public void setSecond(int second) {
this.second = second;
}
public IntMultiplePair(){}
public IntMultiplePair(String first, int second) {
this.first = first;
this.second = second;
}
@Override
public void readFields(DataInput input) throws IOException {
this.first = input.readUTF();
this.second = input.readInt();
}
@Override
public void write(DataOutput output) throws IOException {
output.writeUTF(this.first);
output.writeInt(this.second);
}
@Override
public int compareTo(IntMultiplePair o) {
return 0;
}
}
class IntMultipleSortingComparator extends WritableComparator{
public IntMultipleSortingComparator(){
super(IntMultiplePair.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
IntMultiplePair x = (IntMultiplePair)a;
IntMultiplePair y = (IntMultiplePair)b;
if(!x.getFirst().equals(y.getFirst())){
return x.getFirst().compareTo(y.getFirst());
} else {
return x.getSecond() - y.getSecond();
}
}
}
class GroupingMultipleComparator extends WritableComparator{
public GroupingMultipleComparator(){
super(IntMultiplePair.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
IntMultiplePair x = (IntMultiplePair)a;
IntMultiplePair y = (IntMultiplePair)b;
return x.getFirst().compareTo(y.getFirst());
}
}
class MyMultipleSortingPartitioner extends Partitioner<IntMultiplePair, IntWritable>{
@Override
public int getPartition(IntMultiplePair arg0, IntWritable arg1, int arg2) {
return (arg0.getFirst().hashCode() & Integer.MAX_VALUE)%arg2;
}
}
完整的代码
package com.dtspark.hadoop.hellomapreduce;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
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 MutipleSorting {
public static class DataMapper
extends Mapper<LongWritable, Text, IntMultiplePair, IntWritable>{
private IntMultiplePair intMultiplePair = new IntMultiplePair();
private IntWritable intWritable = new IntWritable(0);
public void map(LongWritable key, Text value, Context context
) throws IOException, InterruptedException {
System.out.println("Map Methond Invoked!!!");
String data = value.toString();
// String[] splited = data.split("\t");
String[] splited = data.split(",");
intMultiplePair.setFirst(splited[0]);
intMultiplePair.setSecond(Integer.valueOf(splited[1]));
intWritable.set(Integer.valueOf(splited[1]));
context.write(intMultiplePair, intWritable);
}
}
public static class DataReducer
extends Reducer<IntMultiplePair,IntWritable,Text, Text> {
public void reduce(IntMultiplePair key , Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
System.out.println("Reduce Methond Invoked!!!" );
StringBuffer buffered = new StringBuffer();
Iterator<IntWritable> iter = values.iterator();
while(iter.hasNext()){
buffered.append(iter.next().get() + ",");
}
int length = buffered.toString().length();
String result = buffered.toString().substring(0, length -1);
context.write(new Text(key.getFirst()), new Text(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: MutlpleSorting <in> [<in>...] <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "MutlpleSorting");
job.setJarByClass(MutipleSorting.class);
job.setMapperClass(DataMapper.class);
job.setReducerClass(DataReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapOutputKeyClass(IntMultiplePair.class);
job.setMapOutputValueClass(IntWritable.class);
job.setPartitionerClass(MyMultipleSortingPartitioner.class);
job.setSortComparatorClass(IntMultipleSortingComparator.class);
job.setGroupingComparatorClass(GroupingMultipleComparator.class);
for (int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job,
new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
class IntMultiplePair implements WritableComparable<IntMultiplePair>{
private String first;
private int second;
public String getFirst() {
return first;
}
public void setFirst(String first) {
this.first = first;
}
public int getSecond() {
return second;
}
public void setSecond(int second) {
this.second = second;
}
public IntMultiplePair(){}
public IntMultiplePair(String first, int second) {
this.first = first;
this.second = second;
}
@Override
public void readFields(DataInput input) throws IOException {
this.first = input.readUTF();
this.second = input.readInt();
}
@Override
public void write(DataOutput output) throws IOException {
output.writeUTF(this.first);
output.writeInt(this.second);
}
@Override
public int compareTo(IntMultiplePair o) {
return 0;
}
}
class IntMultipleSortingComparator extends WritableComparator{
public IntMultipleSortingComparator(){
super(IntMultiplePair.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
IntMultiplePair x = (IntMultiplePair)a;
IntMultiplePair y = (IntMultiplePair)b;
if(!x.getFirst().equals(y.getFirst())){
System.out.println("排序开始了，比较第一个first： " +x.getFirst() +" "+ y.getFirst() +" "+ x.getFirst().compareTo(y.getFirst()));
return x.getFirst().compareTo(y.getFirst());
} else {
System.out.println("排序开始了，比较第二个second： " +x.getSecond() +" "+ y.getSecond() +" " +( x.getSecond() - y.getSecond()));
return x.getSecond() - y.getSecond();
}
}
}
class GroupingMultipleComparator extends WritableComparator{
public GroupingMultipleComparator(){
super(IntMultiplePair.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
IntMultiplePair x = (IntMultiplePair)a;
IntMultiplePair y = (IntMultiplePair)b;
System.out.println("分组开始了 : " +x.getFirst() +" "+ y.getFirst() +" "+ x.getFirst().compareTo(y.getFirst()));
return x.getFirst().compareTo(y.getFirst());
}
}
class MyMultipleSortingPartitioner extends Partitioner<IntMultiplePair, IntWritable>{
@Override
public int getPartition(IntMultiplePair arg0, IntWritable arg1, int arg2) {
System.out.println("getPartition分区的计算过程 ！！！！！！！ " +arg0.getFirst().hashCode() +" " + Integer.MAX_VALUE + arg2);
System.out.println("getPartition的值 " + (arg0.getFirst().hashCode() & Integer.MAX_VALUE)%arg2);
return (arg0.getFirst().hashCode() & Integer.MAX_VALUE)%arg2;
}
}
打得日志
INFO [main] (org.apache.hadoop.conf.Configuration.deprecation:1049) 2016-02-27 17:32:57,577 ---- session.id is deprecated. Instead, use dfs.metrics.session-id
INFO [main] (org.apache.hadoop.metrics.jvm.JvmMetrics:76) 2016-02-27 17:32:57,582 ---- Initializing JVM Metrics with processName=JobTracker, sessionId=
WARN [main] (org.apache.hadoop.mapreduce.JobSubmitter:261) 2016-02-27 17:32:57,978 ---- No job jar file set. User classes may not be found. See Job or Job#setJar(String).
INFO [main] (org.apache.hadoop.mapreduce.lib.input.FileInputFormat:281) 2016-02-27 17:32:58,014 ---- Total input paths to process : 1
INFO [main] (org.apache.hadoop.mapreduce.JobSubmitter:494) 2016-02-27 17:32:58,092 ---- number of splits:1
INFO [main] (org.apache.hadoop.mapreduce.JobSubmitter:583) 2016-02-27 17:32:58,167 ---- Submitting tokens for job: job_local1851923379_0001
INFO [main] (org.apache.hadoop.mapreduce.Job:1300) 2016-02-27 17:32:58,358 ---- The url to track the job:
http://localhost:8080/
INFO [main] (org.apache.hadoop.mapreduce.Job:1345) 2016-02-27 17:32:58,359 ---- Running job: job_local1851923379_0001
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:471) 2016-02-27 17:32:58,360 ---- OutputCommitter set in config null
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:489) 2016-02-27 17:32:58,367 ---- OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:448) 2016-02-27 17:32:58,415 ---- Waiting for map tasks
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:224) 2016-02-27 17:32:58,415 ---- Starting task: attempt_local1851923379_0001_m_000000_0
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.yarn.util.ProcfsBasedProcessTree:181) 2016-02-27 17:32:58,447 ---- ProcfsBasedProcessTree currently is supported only on Linux.
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.Task:587) 2016-02-27 17:32:58,986 ---- Using ResourceCalculatorProcessTree :
org.apache.hadoop.yarn.util.WindowsBasedProcessTree@16c89e
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:753) 2016-02-27 17:32:58,991 ---- Processing split: hdfs://192.168.2.100:9000/library/dataForMutipleSorting.txt:0+85
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1202) 2016-02-27 17:32:59,082 ---- (EQUATOR) 0 kvi 26214396(104857584)
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:995) 2016-02-27 17:32:59,083 ---- mapreduce.task.io.sort.mb: 100
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:996) 2016-02-27 17:32:59,083 ---- soft limit at 83886080
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:997) 2016-02-27 17:32:59,083 ---- bufstart = 0; bufvoid = 104857600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:998) 2016-02-27 17:32:59,083 ---- kvstart = 26214396; length = 6553600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:402) 2016-02-27 17:32:59,087 ---- Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
INFO [main] (org.apache.hadoop.mapreduce.Job:1366) 2016-02-27 17:32:59,362 ---- Job job_local1851923379_0001 running in uber mode : false
INFO [main] (org.apache.hadoop.mapreduce.Job:1373) 2016-02-27 17:32:59,363 ---- map 0% reduce 0%
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
Map Methond Invoked!!!
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,086 ----
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1457) 2016-02-27 17:33:00,089 ---- Starting flush of map output
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1475) 2016-02-27 17:33:00,089 ---- Spilling map output
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1476) 2016-02-27 17:33:00,089 ---- bufstart = 0; bufend = 138; bufvoid = 104857600
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1478) 2016-02-27 17:33:00,089 ---- kvstart = 26214396(104857584); kvend = 26214364(104857456); length = 33/6553600
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第一个first： Kafka Spark -8
排序开始了，比较第一个first： Spark Kafka 8
排序开始了，比较第二个second： 97 98 -1
排序开始了，比较第一个first： Spark Hadoop 11
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第二个second： 63 65 -2
排序开始了，比较第二个second： 99 99 0
排序开始了，比较第一个first： Spark Kafka 8
排序开始了，比较第一个first： Spark Kafka 8
排序开始了，比较第二个second： 98 95 3
排序开始了，比较第二个second： 97 95 2
排序开始了，比较第一个first： Hadoop Kafka -3
排序开始了，比较第一个first： Spark Hadoop 11
排序开始了，比较第一个first： Spark Hadoop 11
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第一个first： Kafka Hadoop 3
排序开始了，比较第二个second： 65 60 5
排序开始了，比较第二个second： 63 60 3
排序开始了，比较第二个second： 99 100 -1
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.MapTask:1660) 2016-02-27 17:33:00,166 ---- Finished spill 0
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.Task:1001) 2016-02-27 17:33:00,178 ---- Task:attempt_local1851923379_0001_m_000000_0 is done. And is in the process of committing
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,195 ---- map
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.Task:1121) 2016-02-27 17:33:00,196 ---- Task 'attempt_local1851923379_0001_m_000000_0' done.
INFO [LocalJobRunner Map Task Executor #0] (org.apache.hadoop.mapred.LocalJobRunner:249) 2016-02-27 17:33:00,196 ---- Finishing task: attempt_local1851923379_0001_m_000000_0
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:456) 2016-02-27 17:33:00,196 ---- map task executor complete.
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:448) 2016-02-27 17:33:00,198 ---- Waiting for reduce tasks
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:302) 2016-02-27 17:33:00,199 ---- Starting task: attempt_local1851923379_0001_r_000000_0
INFO [pool-6-thread-1] (org.apache.hadoop.yarn.util.ProcfsBasedProcessTree:181) 2016-02-27 17:33:00,207 ---- ProcfsBasedProcessTree currently is supported only on Linux.
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Task:587) 2016-02-27 17:33:00,326 ---- Using ResourceCalculatorProcessTree :
org.apache.hadoop.yarn.util.WindowsBasedProcessTree@675767
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.ReduceTask:362) 2016-02-27 17:33:00,330 ---- Using ShuffleConsumerPlugin:
org.apache.hadoop.mapreduce.task.reduce.Shuffle@902038
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:196) 2016-02-27 17:33:00,345 ---- MergerManager: memoryLimit=363285696, maxSingleShuffleLimit=90821424, mergeThreshold=239768576, ioSortFactor=10, memToMemMergeOutputsThreshold=10
INFO [EventFetcher for fetching Map Completion Events] (org.apache.hadoop.mapreduce.task.reduce.EventFetcher:61) 2016-02-27 17:33:00,349 ---- attempt_local1851923379_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
INFO [main] (org.apache.hadoop.mapreduce.Job:1373) 2016-02-27 17:33:00,365 ---- map 100% reduce 0%
INFO [localfetcher#1] (org.apache.hadoop.mapreduce.task.reduce.LocalFetcher:141) 2016-02-27 17:33:00,392 ---- localfetcher#1 about to shuffle output of map attempt_local1851923379_0001_m_000000_0 decomp: 158 len: 162 to MEMORY
INFO [localfetcher#1] (org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput:100) 2016-02-27 17:33:00,397 ---- Read 158 bytes from map-output for attempt_local1851923379_0001_m_000000_0
INFO [localfetcher#1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:314) 2016-02-27 17:33:00,400 ---- closeInMemoryFile -> map-output of size: 158, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->158
INFO [EventFetcher for fetching Map Completion Events] (org.apache.hadoop.mapreduce.task.reduce.EventFetcher:76) 2016-02-27 17:33:00,402 ---- EventFetcher is interrupted.. Returning
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,403 ---- 1 / 1 copied.
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:674) 2016-02-27 17:33:00,403 ---- finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Merger:597) 2016-02-27 17:33:00,422 ---- Merging 1 sorted segments
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Merger:696) 2016-02-27 17:33:00,423 ---- Down to the last merge-pass, with 1 segments left of total size: 144 bytes
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:751) 2016-02-27 17:33:00,426 ---- Merged 1 segments, 158 bytes to disk to satisfy reduce memory limit
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:781) 2016-02-27 17:33:00,427 ---- Merging 1 files, 162 bytes from disk
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl:796) 2016-02-27 17:33:00,429 ---- Merging 0 segments, 0 bytes from memory into reduce
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Merger:597) 2016-02-27 17:33:00,429 ---- Merging 1 sorted segments
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Merger:696) 2016-02-27 17:33:00,431 ---- Down to the last merge-pass, with 1 segments left of total size: 144 bytes
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,431 ---- 1 / 1 copied.
INFO [pool-6-thread-1] (org.apache.hadoop.conf.Configuration.deprecation:1049) 2016-02-27 17:33:00,453 ---- mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
分组开始了 : Hadoop Hadoop 0
Reduce Methond Invoked!!!
分组开始了 : Hadoop Hadoop 0
分组开始了 : Hadoop Kafka -3
分组开始了 : Kafka Kafka 0
Reduce Methond Invoked!!!
分组开始了 : Kafka Kafka 0
分组开始了 : Kafka Spark -8
分组开始了 : Spark Spark 0
Reduce Methond Invoked!!!
分组开始了 : Spark Spark 0
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Task:1001) 2016-02-27 17:33:00,560 ---- Task:attempt_local1851923379_0001_r_000000_0 is done. And is in the process of committing
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,563 ---- 1 / 1 copied.
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Task:1162) 2016-02-27 17:33:00,563 ---- Task attempt_local1851923379_0001_r_000000_0 is allowed to commit now
INFO [pool-6-thread-1] (org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter:439) 2016-02-27 17:33:00,573 ---- Saved output of task 'attempt_local1851923379_0001_r_000000_0' to hdfs://192.168.2.100:9000/library/outputdataForMutipleSorting12/_temporary/0/task_local1851923379_0001_r_000000
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:591) 2016-02-27 17:33:00,574 ---- reduce > reduce
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.Task:1121) 2016-02-27 17:33:00,574 ---- Task 'attempt_local1851923379_0001_r_000000_0' done.
INFO [pool-6-thread-1] (org.apache.hadoop.mapred.LocalJobRunner:325) 2016-02-27 17:33:00,574 ---- Finishing task: attempt_local1851923379_0001_r_000000_0
INFO [Thread-3] (org.apache.hadoop.mapred.LocalJobRunner:456) 2016-02-27 17:33:00,574 ---- reduce task executor complete.
INFO [main] (org.apache.hadoop.mapreduce.Job:1373) 2016-02-27 17:33:01,365 ---- map 100% reduce 100%
INFO [main] (org.apache.hadoop.mapreduce.Job:1384) 2016-02-27 17:33:01,367 ---- Job job_local1851923379_0001 completed successfully
INFO [main] (org.apache.hadoop.mapreduce.Job:1391) 2016-02-27 17:33:01,412 ---- Counters: 38
File System Counters
FILE: Number of bytes read=706
FILE: Number of bytes written=509896
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=170
HDFS: Number of bytes written=47
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=9
Map output records=9
Map output bytes=138
Map output materialized bytes=162
Input split bytes=124
Combine input records=0
Combine output records=0
Reduce input groups=3
Reduce shuffle bytes=162
Reduce input records=9
Reduce output records=3
Spilled Records=18
Shuffled Maps =1
Failed Shuffles=0
Merged Map outputs=1
GC time elapsed (ms)=23
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
Total committed heap usage (bytes)=469508096
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=85
File Output Format Counters
Bytes Written=47
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- muShtaPmumixaMeerTyraniB.124
- 如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- Head First PMP – 7 – 成本管理(Cost Management)
- 产品经理面试常见问题
- 【Some】【搞逗】如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 【Some】【搞逗】如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 【Some】【搞逗】如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 【Some】【搞逗】如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 【Some】【搞逗】如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 【Some】【搞逗】如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 【Some】【搞逗】如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 【Some】【搞逗】如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 如何向外行解释产品经理频繁更改需求为何令程序员烦恼?
- npm 初识
- 如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- 党委会的工作方法[推荐程序员、产品经理仔细看看]
- 如何向外行解释产品经理频繁更改需求为什么会令程序员烦恼?
- am,pm命令
- APM软件原理分析
- Xcode attempted to locate or generate matching&miss iOS development signing identity