hadoop日誌命令

㈠ 如何查看Hadoop運行過程中產生日誌

用hadoop也算有一段時間了，一直沒有注意過hadoop運行過程中，產生的數據日誌，比如說System列印的日誌，或者是log4j，slf4j等記錄的日誌，存放在哪裡，日誌信息的重要性，在這里散仙就不用多說了，調試任何程序基本上都得需要分析日誌。
hadoop的日誌主要是MapRece程序，運行過程中，產生的一些數據日誌，除了系統的日誌外，還包含一些我們自己在測試時候，或者線上環境輸出的日誌，這部分日誌通常會被放在userlogs這個文件夾下面，我們可以在mapred-site.xml裡面配置運行日誌的輸出目錄，散仙測試文件內容如下:

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<!-- Put site-specific property overrides in this file. -->

<configuration>
<!-- jobtracker的master地址-->
<property>
<name>mapred.job.tracker</name>
<value>192.168.75.130:9001</value>
</property>
<property>
<!-- hadoop的日誌輸出指定目錄-->
<name>mapred.local.dir</name>
<value>/root/hadoop1.2/mylogs</value>
</property>
</configuration>
配置好，日誌目錄後，我們就可以把這個配置文件，分發到各個節點上，然後啟動hadoop。
下面我們看來下在eclipse環境中如何調試，散仙在setup，map和rece方法中，分別使用System列印了一些數據，當我們使用local方式跑MR程序時候，日誌並不會被記錄下來，而是直接會在控制台列印，散仙的測試代碼如下：
package com.qin.testdistributed;

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.util.Scanner;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.FSDataInputStream;
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.maprece.Job;
import org.apache.hadoop.maprece.Mapper;
import org.apache.hadoop.maprece.Recer;
import org.apache.hadoop.maprece.lib.db.DBConfiguration;
import org.apache.hadoop.maprece.lib.input.FileInputFormat;
import org.apache.hadoop.maprece.lib.output.FileOutputFormat;
import org.apache.log4j.pattern.LogEvent;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import com.qin.operadb.WriteMapDB;

/**
* 測試hadoop的全局共享文件
* 使用DistributedCached
*
* 大數據技術交流群： 37693216
* @author qindongliang
*
* ***/
public class TestDistributed {

private static Logger logger=LoggerFactory.getLogger(TestDistributed.class);

private static class FileMapper extends Mapper<LongWritable, Text, Text, IntWritable>{

Path path[]=null;

/**
* Map函數前調用
*
* */
@Override
protected void setup(Context context)
throws IOException, InterruptedException {
logger.info("開始啟動setup了哈哈哈哈");
// System.out.println("運行了.........");
Configuration conf=context.getConfiguration();
path=DistributedCache.getLocalCacheFiles(conf);
System.out.println("獲取的路徑是： "+path[0].toString());
// FileSystem fs = FileSystem.get(conf);
FileSystem fsopen= FileSystem.getLocal(conf);
// FSDataInputStream in = fsopen.open(path[0]);
// System.out.println(in.readLine());
// for(Path tmpRefPath : path) {
// if(tmpRefPath.toString().indexOf("ref.png") != -1) {
// in = reffs.open(tmpRefPath);
// break;
// }
// }

// FileReader reader=new FileReader("file://"+path[0].toString());
// File f=new File("file://"+path[0].toString());
// FSDataInputStream in=fs.open(new Path(path[0].toString()));
// Scanner scan=new Scanner(in);
// while(scan.hasNext()){
// System.out.println(Thread.currentThread().getName()+"掃描的內容: "+scan.next());
// }
// scan.close();
//
// System.out.println("size: "+path.length);

}

@Override
protected void map(LongWritable key, Text value,Context context)
throws IOException, InterruptedException {

// System.out.println("map aaa");
//logger.info("Map里的任務");
System.out.println("map里輸出了");
// logger.info();
context.write(new Text(""), new IntWritable(0));

}

@Override
protected void cleanup(Context context)
throws IOException, InterruptedException {

logger.info("清空任務了。。。。。。");
}

}

private static class FileRece extends Recer<Object, Object, Object, Object>{

@Override
protected void rece(Object arg0, Iterable<Object> arg1,
Context arg2)throws IOException, InterruptedException {

System.out.println("我是rece裡面的東西");
}
}

public static void main(String[] args)throws Exception {

JobConf conf=new JobConf(TestDistributed.class);
//conf.set("mapred.local.dir", "/root/hadoop");
//Configuration conf=new Configuration();

// conf.set("mapred.job.tracker","192.168.75.130:9001");
//讀取person中的數據欄位
//conf.setJar("tt.jar");

//注意這行代碼放在最前面，進行初始化，否則會報
String inputPath="hdfs://192.168.75.130:9000/root/input";
String outputPath="hdfs://192.168.75.130:9000/root/outputsort";

Job job=new Job(conf, "a");
DistributedCache.addCacheFile(new URI("hdfs://192.168.75.130:9000/root/input/f1.txt"), job.getConfiguration());
job.setJarByClass(TestDistributed.class);
System.out.println("運行模式： "+conf.get("mapred.job.tracker"));
/**設置輸出表的的信息 第一個參數是job任務，第二個參數是表名，第三個參數欄位項**/
FileSystem fs=FileSystem.get(job.getConfiguration());

Path pout=new Path(outputPath);
if(fs.exists(pout)){
fs.delete(pout, true);
System.out.println("存在此路徑, 已經刪除......");
}
/**設置Map類**/
// job.setOutputKeyClass(Text.class);
//job.setOutputKeyClass(IntWritable.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setMapperClass(FileMapper.class);
job.setRecerClass(FileRece.class);
FileInputFormat.setInputPaths(job, new Path(inputPath)); //輸入路徑
FileOutputFormat.setOutputPath(job, new Path(outputPath));//輸出路徑

System.exit(job.waitForCompletion(true) ? 0 : 1);

}

}
Local模式下輸出如下：
運行模式： local
存在此路徑, 已經刪除......
WARN - NativeCodeLoader.<clinit>(52) | Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
WARN - JobClient.AndConfigureFiles(746) | Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
WARN - JobClient.AndConfigureFiles(870) | No job jar file set. User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
INFO - FileInputFormat.listStatus(237) | Total input paths to process : 1
WARN - LoadSnappy.<clinit>(46) | Snappy native library not loaded
INFO - .downloadCacheObject(423) | Creating f1.txt in /root/hadoop1.2/hadooptmp/mapred/local/archive/9070031930820799196_1788685676_88844454/192.168.75.130/root/input-work-18614545932656 with rwxr-xr-x
INFO - .downloadCacheObject(463) | Cached hdfs://192.168.75.130:9000/root/input/f1.txt as /root/hadoop1.2/hadooptmp/mapred/local/archive/9070031930820799196_1788685676_88844454/192.168.75.130/root/input/f1.txt
INFO - .localizePublicCacheObject(486) | Cached hdfs://192.168.75.130:9000/root/input/f1.txt as /root/hadoop1.2/hadooptmp/mapred/local/archive/9070031930820799196_1788685676_88844454/192.168.75.130/root/input/f1.txt
INFO - JobClient.monitorAndPrintJob(1380) | Running job: job_local479869714_0001
INFO - LocalJobRunner$Job.run(340) | Waiting for map tasks
INFO - LocalJobRunner$Job$MapTaskRunnable.run(204) | Starting task: attempt_local479869714_0001_m_000000_0
INFO - Task.initialize(534) | Using ResourceCalculatorPlugin : null
INFO - MapTask.runNewMapper(729) | Processing split: hdfs://192.168.75.130:9000/root/input/f1.txt:0+31
INFO - MapTask$MapOutputBuffer.<init>(949) | io.sort.mb = 100
INFO - MapTask$MapOutputBuffer.<init>(961) | data buffer = 79691776/99614720
INFO - MapTask$MapOutputBuffer.<init>(962) | record buffer = 262144/327680
INFO - TestDistributed$FileMapper.setup(57) | 開始啟動setup了哈哈哈哈
獲取的路徑是： /root/hadoop1.2/hadooptmp/mapred/local/archive/9070031930820799196_1788685676_88844454/192.168.75.130/root/input/f1.txt
map里輸出了
map里輸出了
INFO - TestDistributed$FileMapper.cleanup(107) | 清空任務了。。。。。。
INFO - MapTask$MapOutputBuffer.flush(1289) | Starting flush of map output
INFO - MapTask$MapOutputBuffer.sortAndSpill(1471) | Finished spill 0
INFO - Task.done(858) | Task:attempt_local479869714_0001_m_000000_0 is done. And is in the process of commiting
INFO - LocalJobRunner$Job.statusUpdate(466) |
INFO - Task.sendDone(970) | Task 'attempt_local479869714_0001_m_000000_0' done.
INFO - LocalJobRunner$Job$MapTaskRunnable.run(229) | Finishing task: attempt_local479869714_0001_m_000000_0
INFO - LocalJobRunner$Job.run(348) | Map task executor complete.
INFO - Task.initialize(534) | Using ResourceCalculatorPlugin : null
INFO - LocalJobRunner$Job.statusUpdate(466) |
INFO - Merger$MergeQueue.merge(408) | Merging 1 sorted segments
INFO - Merger$MergeQueue.merge(491) | Down to the last merge-pass, with 1 segments left of total size: 16 bytes
INFO - LocalJobRunner$Job.statusUpdate(466) |