单纯linux系统下hadoop2.7.3 eclipse，记一次成功的运行wordcount的注意事项

    1. hadoop要正确安装好
    2. hadoop eclipse plugin要对应相应的eclipse版本
      3. define hadoop location mr master:9000 另一个9001  下面的是代理不用理会

bin/hdfs dfs -mkdir /user，在hdfs上创建user文件夹\
bin/hdfs dfs -put /usr/local/hadoop/README.txt /input/     上传到input
      按照上面命令上传文件到hdfs上

，不要建output文件夹

将 /user权限开放

      有log4j警告时，把ssh包里的log4j.properties放入src里

      argument里要写好输入要具体到文件，输出文件只写路径  ，例如：hdfs://localhost:9000/user/input/README.txt hdfs://localhost:9000/user/output/

    暂时想到这么多

package WordCount;
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);
        }
    }

    @SuppressWarnings("deprecation")
    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 <in> <out>");
            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]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

 

 或者

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;

public class WordCount {

public static class Map extends MapReduceBase implements
Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();

public void map(LongWritable key, Text value,
OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
}

public static class Reduce extends MapReduceBase implements
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values,
OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}

public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("WordCount");

conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);

conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);

conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);

FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));

JobClient.runJob(conf);
}
}

 

      

 

 好像这两个图片显示不出来了

12:44:34,422  WARN NativeCodeLoader:62 - Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
12:44:35,109  INFO deprecation:1173 - session.id is deprecated. Instead, use dfs.metrics.session-id
12:44:35,111  INFO JvmMetrics:76 - Initializing JVM Metrics with processName=JobTracker, sessionId=
12:44:35,244  WARN JobResourceUploader:171 - No job jar file set.  User classes may not be found. See Job or Job#setJar(String).
12:44:35,273  INFO FileInputFormat:283 - Total input paths to process : 1
12:44:35,378  INFO JobSubmitter:198 - number of splits:1
12:44:35,490  INFO JobSubmitter:287 - Submitting tokens for job: job_local1396121088_0001
12:44:35,673  INFO Job:1294 - The url to track the job: http://localhost:8080/
12:44:35,674  INFO Job:1339 - Running job: job_local1396121088_0001
12:44:35,678  INFO LocalJobRunner:471 - OutputCommitter set in config null
12:44:35,685  INFO FileOutputCommitter:108 - File Output Committer Algorithm version is 1
12:44:35,687  INFO LocalJobRunner:489 - OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
12:44:35,799  INFO LocalJobRunner:448 - Waiting for map tasks
12:44:35,799  INFO LocalJobRunner:224 - Starting task: attempt_local1396121088_0001_m_000000_0
12:44:35,848  INFO FileOutputCommitter:108 - File Output Committer Algorithm version is 1
12:44:35,864  INFO Task:612 -  Using ResourceCalculatorProcessTree : [ ]
12:44:35,874  INFO MapTask:756 - Processing split: hdfs://localhost:9000/user/input/README.txt:0+1366
12:44:35,940  INFO MapTask:1205 - (EQUATOR) 0 kvi 26214396(104857584)
12:44:35,940  INFO MapTask:998 - mapreduce.task.io.sort.mb: 100
12:44:35,941  INFO MapTask:999 - soft limit at 83886080
12:44:35,941  INFO MapTask:1000 - bufstart = 0; bufvoid = 104857600
12:44:35,941  INFO MapTask:1001 - kvstart = 26214396; length = 6553600
12:44:35,945  INFO MapTask:403 - Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
12:44:36,064  INFO LocalJobRunner:591 - 
12:44:36,193  INFO MapTask:1460 - Starting flush of map output
12:44:36,193  INFO MapTask:1482 - Spilling map output
12:44:36,193  INFO MapTask:1483 - bufstart = 0; bufend = 2055; bufvoid = 104857600
12:44:36,193  INFO MapTask:1485 - kvstart = 26214396(104857584); kvend = 26213684(104854736); length = 713/6553600
12:44:36,226  INFO MapTask:1667 - Finished spill 0
12:44:36,234  INFO Task:1038 - Task:attempt_local1396121088_0001_m_000000_0 is done. And is in the process of committing
12:44:36,252  INFO LocalJobRunner:591 - map
12:44:36,252  INFO Task:1158 - Task 'attempt_local1396121088_0001_m_000000_0' done.
12:44:36,253  INFO LocalJobRunner:249 - Finishing task: attempt_local1396121088_0001_m_000000_0
12:44:36,253  INFO LocalJobRunner:456 - map task executor complete.
12:44:36,261  INFO LocalJobRunner:448 - Waiting for reduce tasks
12:44:36,263  INFO LocalJobRunner:302 - Starting task: attempt_local1396121088_0001_r_000000_0
12:44:36,274  INFO FileOutputCommitter:108 - File Output Committer Algorithm version is 1
12:44:36,275  INFO Task:612 -  Using ResourceCalculatorProcessTree : [ ]
12:44:36,279  INFO ReduceTask:362 - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@10c41eda
12:44:36,326  INFO MergeManagerImpl:197 - MergerManager: memoryLimit=1941805440, maxSingleShuffleLimit=485451360, mergeThreshold=1281591680, ioSortFactor=10, memToMemMergeOutputsThreshold=10
12:44:36,333  INFO EventFetcher:61 - attempt_local1396121088_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
12:44:36,423  INFO LocalFetcher:144 - localfetcher#1 about to shuffle output of map attempt_local1396121088_0001_m_000000_0 decomp: 1832 len: 1836 to MEMORY
12:44:36,431  INFO InMemoryMapOutput:100 - Read 1832 bytes from map-output for attempt_local1396121088_0001_m_000000_0
12:44:36,433  INFO MergeManagerImpl:315 - closeInMemoryFile -> map-output of size: 1832, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->1832
12:44:36,437  INFO EventFetcher:76 - EventFetcher is interrupted.. Returning
12:44:36,439  INFO LocalJobRunner:591 - 1 / 1 copied.
12:44:36,440  INFO MergeManagerImpl:687 - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
12:44:36,456  INFO Merger:606 - Merging 1 sorted segments
12:44:36,457  INFO Merger:705 - Down to the last merge-pass, with 1 segments left of total size: 1823 bytes
12:44:36,460  INFO MergeManagerImpl:754 - Merged 1 segments, 1832 bytes to disk to satisfy reduce memory limit
12:44:36,461  INFO MergeManagerImpl:784 - Merging 1 files, 1836 bytes from disk
12:44:36,461  INFO MergeManagerImpl:799 - Merging 0 segments, 0 bytes from memory into reduce
12:44:36,462  INFO Merger:606 - Merging 1 sorted segments
12:44:36,462  INFO Merger:705 - Down to the last merge-pass, with 1 segments left of total size: 1823 bytes
12:44:36,463  INFO LocalJobRunner:591 - 1 / 1 copied.
12:44:36,530  INFO deprecation:1173 - mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
12:44:36,677  INFO Job:1360 - Job job_local1396121088_0001 running in uber mode : false
12:44:36,679  INFO Job:1367 -  map 100% reduce 0%
12:44:36,776  INFO Task:1038 - Task:attempt_local1396121088_0001_r_000000_0 is done. And is in the process of committing
12:44:36,782  INFO LocalJobRunner:591 - 1 / 1 copied.
12:44:36,782  INFO Task:1199 - Task attempt_local1396121088_0001_r_000000_0 is allowed to commit now
12:44:36,799  INFO FileOutputCommitter:535 - Saved output of task 'attempt_local1396121088_0001_r_000000_0' to hdfs://localhost:9000/user/output/_temporary/0/task_local1396121088_0001_r_000000
12:44:36,802  INFO LocalJobRunner:591 - reduce > reduce
12:44:36,802  INFO Task:1158 - Task 'attempt_local1396121088_0001_r_000000_0' done.
12:44:36,802  INFO LocalJobRunner:325 - Finishing task: attempt_local1396121088_0001_r_000000_0
12:44:36,803  INFO LocalJobRunner:456 - reduce task executor complete.
12:44:37,680  INFO Job:1367 -  map 100% reduce 100%
12:44:37,681  INFO Job:1378 - Job job_local1396121088_0001 completed successfully
12:44:37,708  INFO Job:1385 - Counters: 35
    File System Counters
        FILE: Number of bytes read=4048
        FILE: Number of bytes written=567860
        FILE: Number of read operations=0
        FILE: Number of large read operations=0
        FILE: Number of write operations=0
        HDFS: Number of bytes read=2732
        HDFS: Number of bytes written=1306
        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=31
        Map output records=179
        Map output bytes=2055
        Map output materialized bytes=1836
        Input split bytes=108
        Combine input records=179
        Combine output records=131
        Reduce input groups=131
        Reduce shuffle bytes=1836
        Reduce input records=131
        Reduce output records=131
        Spilled Records=262
        Shuffled Maps =1
        Failed Shuffles=0
        Merged Map outputs=1
        GC time elapsed (ms)=0
        Total committed heap usage (bytes)=571473920
    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=1366
    File Output Format Counters 
        Bytes Written=1306
View Code
hadoop@kali:/usr/local/hadoop$ bin/hdfs dfs -cat /user/output/*
17/02/20 12:51:19 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
(BIS),	1
(ECCN)	1
(TSU)	1
(see	1
5D002.C.1,	1
740.13)	1
<http://www.wassenaar.org/>	1
Administration	1
Apache	1
BEFORE	1
BIS	1
Bureau	1
Commerce,	1
Commodity	1
Control	1
Core	1
Department	1
ENC	1
Exception	1
Export	2
For	1
Foundation	1
Government	1
Hadoop	1
Hadoop,	1
Industry	1
Jetty	1
License	1
Number	1
Regulations,	1
SSL	1
Section	1
Security	1
See	1
Software	2
Technology	1
The	4
This	1
U.S.	1
Unrestricted	1
about	1
algorithms.	1
and	6
and/or	1
another	1
any	1
as	1
asymmetric	1
at:	2
both	1
by	1
check	1
classified	1
code	1
code.	1
concerning	1
country	1
country's	1
country,	1
cryptographic	3
currently	1
details	1
distribution	2
eligible	1
encryption	3
exception	1
export	1
following	1
for	3
form	1
from	1
functions	1
has	1
have	1
http://hadoop.apache.org/core/	1
http://wiki.apache.org/hadoop/	1
if	1
import,	2
in	1
included	1
includes	2
information	2
information.	1
is	1
it	1
latest	1
laws,	1
libraries	1
makes	1
manner	1
may	1
more	2
mortbay.org.	1
object	1
of	5
on	2
or	2
our	2
performing	1
permitted.	1
please	2
policies	1
possession,	2
project	1
provides	1
re-export	2
regulations	1
reside	1
restrictions	1
security	1
see	1
software	2
software,	2
software.	2
software:	1
source	1
the	8
this	3
to	2
under	1
use,	2
uses	1
using	2
visit	1
website	1
which	2
wiki,	1
with	1
written	1
you	1
your	1
hadoop@kali:/usr/local/hadoop$

 

posted on 2017-02-20 13:26  Honey_Badger  阅读(270)  评论(0)    收藏  举报

导航

Copyright © 2017 Honey_Badger
github