1.å¦ä½å¨win7ä¸çeclipseä¸è°è¯Hadoop2.2.0çç¨åº
2.å¦ä½å¨windowså¹³å°ä¸ç¨Eclipseè°è¯è¿è¡HBase
å¦ä½å¨win7ä¸çeclipseä¸è°è¯Hadoop2.2.0çç¨åº
å¨ä¸ä¸ç¯åæä¸ï¼æ£ä»å·²ç»è®²äºHadoopçåæºä¼ªåå¸çé¨ç½²ï¼æ¬ç¯ï¼æ£ä»å°±è¯´ä¸ï¼å¦ä½eclipseä¸è°è¯hadoop2.2.0,vc发送封包源码å¦æä½ ä½¿ç¨çè¿æ¯hadoop1.xççæ¬ï¼é£ä¹ï¼ä¹æ²¡äºï¼æ£ä»å¨ä»¥åçå客éï¼ä¹åè¿eclipseè°è¯1.xçhadoopç¨åºï¼ä¸¤è æ大çä¸åä¹å¤å¨äºä½¿ç¨çeclipseæ件ä¸åï¼hadoop2.xä¸hadoop1.xçAPIï¼ä¸å¤ªä¸è´ï¼æ以æ件ä¹ä¸ä¸æ ·ï¼æ们åªéè¦ä½¿ç¨åå«å¯¹åºçæ件å³å¯.ä¸é¢å¼å§è¿å ¥æ£é¢:
åºå· å称 æè¿°
1 eclipse Juno Service Release 4.2çæ¬
2 æä½ç³»ç» Windows7
3 hadoopçeclipseæ件 hadoop-eclipse-plugin-2.2.0.jar
4 hadoopçé群ç¯å¢ èææºLinuxçCentos6.5åæºä¼ªåå¸å¼
5 è°è¯ç¨åº Hellow World
éå°çå 个é®é¢å¦ä¸ï¼
Java代ç
java.io.IOException: Could not locate executable null\bin\winutils.exe in the Hadoop binaries.
解å³åæ³:
å¨org.apache.hadoop.util.Shellç±»çcheckHadoopHome()æ¹æ³çè¿åå¼éååºå®ç
æ¬æºhadoopçè·¯å¾ï¼æ£ä»å¨è¿éæ´æ¹å¦ä¸ï¼
Java代ç private static String checkHadoopHome() {
// first check the Dflag hadoop.home.dir with JVM scope
//System.setProperty("hadoop.home.dir", "...");
String home = System.getProperty("hadoop.home.dir");
// fall back to the system/user-global env variable
if (home == null) {
home = System.getenv("HADOOP_HOME");
}
try {
// couldn't find either setting for hadoop's home directory
if (home == null) {
throw new IOException("HADOOP_HOME or hadoop.home.dir are not set.");
}
if (home.startsWith("\"") && home.endsWith("\"")) {
home = home.substring(1, home.length()-1);
}
// check that the home setting is actually a directory that exists
File homedir = new File(home);
if (!homedir.isAbsolute() || !homedir.exists() || !homedir.isDirectory()) {
throw new IOException("Hadoop home directory " + homedir
+ " does not exist, is not a directory, or is not an absolute path.");
}
home = homedir.getCanonicalPath();
} catch (IOException ioe) {
if (LOG.isDebugEnabled()) {
LOG.debug("Failed to detect a valid hadoop home directory", ioe);
}
home = null;
}
//åºå®æ¬æºçhadoopå°å
home="D:\\hadoop-2.2.0";
return home;
}
第äºä¸ªå¼å¸¸ï¼Could not locate executable D:\Hadoop\tar\hadoop-2.2.0\hadoop-2.2.0\bin\winutils.exe in the Hadoop binaries. æ¾ä¸å°winä¸çæ§è¡ç¨åºï¼å¯ä»¥å»ä¸è½½binå ï¼è¦çæ¬æºçhadoopè·ç®å½ä¸çbinå å³å¯
第ä¸ä¸ªå¼å¸¸ï¼
Java代ç Exception in thread "main" java.lang.IllegalArgumentException: Wrong FS: hdfs://...:/user/hmail/output/part-, expected: file:///
at org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:)
at org.apache.hadoop.fs.RawLocalFileSystem.pathToFile(RawLocalFileSystem.java:)
at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:)
at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:)
at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:)
at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:)
at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:)
at com.netease.hadoop.HDFSCatWithAPI.main(HDFSCatWithAPI.java:)
åºç°è¿ä¸ªå¼å¸¸ï¼ä¸è¬æ¯HDFSçè·¯å¾åçæé®é¢ï¼è§£å³åæ³ï¼æ·è´é群ä¸çcore-site.xmlåhdfs-site.xmlæ件ï¼æ¾å¨eclipseçsrcæ ¹ç®å½ä¸å³å¯ã
第å个å¼å¸¸ï¼
Java代ç Exception in thread "main" java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z
åºç°è¿ä¸ªå¼å¸¸ï¼ä¸è¬æ¯ç±äºHADOOP_HOMEçç¯å¢åéé ç½®çæé®é¢ï¼å¨è¿éæ£ä»ç¹å«è¯´æä¸ä¸ï¼å¦ææ³å¨Winä¸çeclipseä¸æåè°è¯Hadoop2.2ï¼å°±éè¦å¨æ¬æºçç¯å¢åéä¸ï¼æ·»å å¦ä¸çç¯å¢åéï¼
ï¼1ï¼å¨ç³»ç»åéä¸ï¼æ°å»ºHADOOP_HOMEåéï¼å±æ§å¼ä¸ºD:\hadoop-2.2.0.ä¹å°±æ¯æ¬æºå¯¹åºçhadoopç®å½
(2)å¨ç³»ç»åéçPathéï¼è¿½å %HADOOP_HOME%/binå³å¯
以ä¸çé®é¢ï¼æ¯æ£ä»å¨æµè¯éå°çï¼ç»è¿å¯¹çä¸è¯ï¼æ们çeclipseç»äºå¯ä»¥æåçè°è¯MRç¨åºäºï¼æ£ä»è¿éçHellow Worldæºç å¦ä¸ï¼
Java代ç package com.qin.wordcount;
import java.io.IOException;
import org.apache.hadoop.fs.FileSystem;
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.JobConf;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
/***
*
* Hadoop2.2.0æµè¯
* æ¾WordCountçä¾å
*
* @author qindongliang
*
* hadoopææ¯äº¤æµç¾¤ï¼
*
*
* */
public class MyWordCount {
/**
* Mapper
*
* **/
private static class WMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
private IntWritable count=new IntWritable(1);
private Text text=new Text();
@Override
protected void map(LongWritable key, Text value,Context context)
throws IOException, InterruptedException {
String values[]=value.toString().split("#");
//System.out.println(values[0]+"========"+values[1]);
count.set(Integer.parseInt(values[1]));
text.set(values[0]);
context.write(text,count);
}
}
/**
* Reducer
*
* **/
private static class WReducer extends Reducer<Text, IntWritable, Text, Text>{
private Text t=new Text();
@Override
protected void reduce(Text key, Iterable<IntWritable> value,Context context)
throws IOException, InterruptedException {
int count=0;
for(IntWritable i:value){
count+=i.get();
}
t.set(count+"");
context.write(key,t);
}
}
/**
* æ¹å¨ä¸
* (1)shellæºç éæ·»å checkHadoopHomeçè·¯å¾
* (2)è¡ï¼FileUtilséé¢
* **/
public static void main(String[] args) throws Exception{
// String path1=System.getenv("HADOOP_HOME");
// System.out.println(path1);
// System.exit(0);
JobConf conf=new JobConf(MyWordCount.class);
//Configuration conf=new Configuration();
//conf.set("mapred.job.tracker","...:");
//读åpersonä¸çæ°æ®å段
// conf.setJar("tt.jar");
//注æè¿è¡ä»£ç æ¾å¨æåé¢ï¼è¿è¡åå§åï¼å¦åä¼æ¥
/**Jobä»»å¡**/
Job job=new Job(conf, "testwordcount");
job.setJarByClass(MyWordCount.class);
System.out.println("模å¼ï¼ "+conf.get("mapred.job.tracker"));;
// job.setCombinerClass(PCombine.class);
// job.setNumReduceTasks(3);//设置为3
job.setMapperClass(WMapper.class);
job.setReducerClass(WReducer.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
String path="hdfs://...:/qin/output";
FileSystem fs=FileSystem.get(conf);
Path p=new Path(path);
if(fs.exists(p)){
fs.delete(p, true);
System.out.println("è¾åºè·¯å¾åå¨ï¼å·²å é¤ï¼");
}
FileInputFormat.setInputPaths(job, "hdfs://...:/qin/input");
FileOutputFormat.setOutputPath(job,p );
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
æ§å¶å°ï¼æå°æ¥å¿å¦ä¸ï¼
Java代ç INFO - Configuration.warnOnceIfDeprecated() | mapred.job.tracker is deprecated. Instead, use mapreduce.jobtracker.address
模å¼ï¼ local
è¾åºè·¯å¾åå¨ï¼å·²å é¤ï¼
INFO - Configuration.warnOnceIfDeprecated() | session.id is deprecated. Instead, use dfs.metrics.session-id
INFO - JvmMetrics.init() | Initializing JVM Metrics with processName=JobTracker, sessionId=
WARN - JobSubmitter.copyAndConfigureFiles() | Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
WARN - JobSubmitter.copyAndConfigureFiles() | No job jar file set. User classes may not be found. See Job or Job#setJar(String).
INFO - FileInputFormat.listStatus() | Total input paths to process : 1
INFO - JobSubmitter.submitJobInternal() | number of splits:1
INFO - Configuration.warnOnceIfDeprecated() | user.name is deprecated. Instead, use mapreduce.job.user.name
INFO - Configuration.warnOnceIfDeprecated() | mapred.output.value.class is deprecated. Instead, use mapreduce.job.output.value.class
INFO - Configuration.warnOnceIfDeprecated() | mapred.mapoutput.value.class is deprecated. Instead, use mapreduce.map.output.value.class
INFO - Configuration.warnOnceIfDeprecated() | mapreduce.map.class is deprecated. Instead, use mapreduce.job.map.class
INFO - C
å¦ä½å¨windowså¹³å°ä¸ç¨Eclipseè°è¯è¿è¡HBase
ããæä½æ¥éª¤å¦ä¸ï¼ãã1.ä¸è½½åå®è£ cygwinï¼
ãã2.ä¸è½½æ°çZookeeperå åHBaseå ï¼è¿éZooKeeperçæ¬ä¸º3.3.1ï¼HBaseçæ¬ä¸º0..4
ãã3.æå©ç¨å®ä»¬çæºç å å¨Eclipseä¸çæ2个ç¬ç«çProject,注æï¼zookeeperå·¥ç¨ï¼è¦æé£ä¸ªconfç®å½å å ¥å°å·¥ç¨çsrcä¸å»
ãã4.ä¿®æ¹zookeeperå·¥ç¨ä¸çconfç®å½ä¸çzoo.cfgæ件ï¼ä¾åå¦ä¸ï¼
ãã# The number of milliseconds of each tick
ããtickTime=
ãã# the directory where the snapshot is stored.
ããdataDir=D:/zookeeper-3.3.1/data
ãã# the port at which the clients will connect
ããclientPort=
ããå°±æ¯ç»zookeeperæå®æ件åæ¾çå°æ¹ä»¥å端å£
ãã5.å¯å¨zookeeper
ããå¨Eclipseä¸æ°å»ºä¸ä¸ªRun configï¼main class为ï¼org.apache.zookeeper.server.quorum.QuorumPeerMain
ããå¯å¨çç¨åºåæ°ä¸ºï¼D:/workspace/zookeeper3.3.1/conf/zoo.cfg
ããå¯å¨çèææºåæ°ä¸ºï¼
ãã-Dzookeeper.log.dir=D:/workspace/zookeeper3.3.1/log
ãã-Dzookeeper.root.logger=INFO,CONSOLE
ããå¦å¾æ示ï¼
ãã好äºï¼è¿æ ·å°±å¯ä»¥å¨Eclipseä¸æZooKeeperå¯å¨èµ·æ¥äºã
ãã6.ä¿®æ¹HBase projectä¸çä¸ä¸ªç±»
ããorg.apache.hadoop.hbase.LocalHBaseCluster
ããæ¾å°å®çmainå½æ°ï¼æmainå½æ°æ¹æä¸
ããpublic static void main(String[] args) throws IOException {
ããHBaseConfiguration conf = new HBaseConfiguration();
ããconf.set("hbase.zookeeper.quorum", "localhost");
ããconf.set("hbase.zookeeper.property.clientPort", "");
ããLocalHBaseCluster cluster = new LocalHBaseCluster(conf,1);
ããcluster.startup();
ãã}ãã
ãã注æè¡ï¼LocalHBaseCluster cluster = new LocalHBaseCluster(conf,1); æé å½æ°ä¸ç1æ¯ä»£è¡¨Region serverç个æ°ï¼å¨è¿éåªæ³èµ·ä¸ä¸ªregion server.
ãã7.ä¿®æ¹HBaseçé ç½®æ件
ããå¨HBase projectä¸çsrcä¸å¯ä»¥çå°hbase-default.xmlåhbase-site.xml两个æ件ï¼æ¹åªä¸ªé½å¯ä»¥ãç´æ¥å¨hbase-default.xmlæ¹çï¼éè¦çæ¯ä¸é¢3个å±æ§hbase.rootdirï¼hbase.cluster.distributedï¼hbase.tmp.dirï¼
ããæhbase.rootdirï¼hbase.tmp.diré½æåäºæ¬å°çç®å½ï¼å½ç¶å¯ä»¥æ ¹æ®èªå·±çéè¦è°æ´,å½ç¶æ ¼å¼ä¸å®ä¸æ ·åã
ãã<property>
ãã<name>hbase.rootdir</name>
ãã<value>file:///D:/hbase-0..3/data </value>
ãã<description>The directory shared by region servers.
ããShould be fully-qualified to include the filesystem to use.
ããE.g: hdfs://NAMENODE_SERVER:PORT/HBASE_ROOTDIR
ãã</description>
ãã</property>
ãã<property>
ãã<name>hbase.cluster.distributed</name>
ãã<value>false </value>
ãã<description>The mode the cluster will be in. Possible values are
ããfalse: standalone and pseudo-distributed setups with managed Zookeeper
ããtrue: fully-distributed with unmanaged Zookeeper Quorum (see hbase-env.sh)
ãã</description>
ãã</property>
ãã<property>
ãã<name>hbase.tmp.dir</name>
ãã<value>D:/hbase-0..3/tmp </value>
ãã<description>Temporary directory on the local filesystem.</description>
ãã</property>
ãã<property>ãã
ãã8.å¯å¨HBaseï¼ç´æ¥run org.apache.hadoop.hbase.LocalHBaseClusterå°±å¯ä»¥ï¼run configä¸éè¦æ²¡æä»ä¹å«çé ç½®ãå½ç¶å°±ä¹å¯ä»¥debugäºã