Question

如何查看Hadoop运行过程中产生日志

Answer 1

用hadoop也算有一段时间了，一直没有注意过hadoop运行过程中，产生的数据日志，比如说System打印的日志，或者是log4j，slf4j等记录的日志，存放在哪里，日志信息的重要性，在这里散仙就不用多说了，调试任何程序基本上都得需要分析日志。
hadoop的日志主要是MapReduce程序，运行过程中，产生的一些数据日志，除了系统的日志外，还包含一些我们自己在测试时候，或者线上环境输出的日志，这部分日志通常会被放在userlogs这个文件夹下面，我们可以在mapred-site.xml里面配置运行日志的输出目录，散仙测试文件内容如下:

<?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的日志输出指定目录-->
<name>mapred.local.dir</name>
<value>/root/hadoop1.2/mylogs</value>
</property>
</configuration>
配置好，日志目录后，我们就可以把这个配置文件，分发到各个节点上，然后启动hadoop。
下面我们看来下在eclipse环境中如何调试，散仙在setup，map和reduce方法中，分别使用System打印了一些数据，当我们使用local方式跑MR程序时候，日志并不会被记录下来，而是直接会在控制台打印，散仙的测试代码如下：
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.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.pattern.LogEvent;

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

import com.qin.operadb.WriteMapDB;

/**
* 测试hadoop的全局共享文件
* 使用DistributedCached
*
* 大数据技术交流群： 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函数前调用
*
* */
@Override
protected void setup(Context context)
throws IOException, InterruptedException {
logger.info("开始启动setup了哈哈哈哈");
// System.out.println("运行了.........");
Configuration conf=context.getConfiguration();
path=DistributedCache.getLocalCacheFiles(conf);
System.out.println("获取的路径是： "+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()+"扫描的内容: "+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里的任务");
System.out.println("map里输出了");
// logger.info();
context.write(new Text(""), new IntWritable(0));

}

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

logger.info("清空任务了。。。。。。");
}

}

private static class FileReduce extends Reducer<Object, Object, Object, Object>{

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

System.out.println("我是reduce里面的东西");
}
}

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");
//读取person中的数据字段
//conf.setJar("tt.jar");

//注意这行代码放在最前面，进行初始化，否则会报
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("运行模式： "+conf.get("mapred.job.tracker"));
/**设置输出表的的信息 第一个参数是job任务，第二个参数是表名，第三个参数字段项**/
FileSystem fs=FileSystem.get(job.getConfiguration());

Path pout=new Path(outputPath);
if(fs.exists(pout)){
fs.delete(pout, true);
System.out.println("存在此路径, 已经删除......");
}
/**设置Map类**/
// job.setOutputKeyClass(Text.class);
//job.setOutputKeyClass(IntWritable.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setMapperClass(FileMapper.class);
job.setReducerClass(FileReduce.class);
FileInputFormat.setInputPaths(job, new Path(inputPath)); //输入路径
FileOutputFormat.setOutputPath(job, new Path(outputPath));//输出路径

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

}

}
Local模式下输出如下：
运行模式： local
存在此路径, 已经删除......
WARN - NativeCodeLoader.<clinit>(52) | Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
WARN - JobClient.copyAndConfigureFiles(746) | Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
WARN - JobClient.copyAndConfigureFiles(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 - TrackerDistributedCacheManager.downloadCacheObject(423) | Creating f1.txt in /root/hadoop1.2/hadooptmp/mapred/local/archive/9070031930820799196_1788685676_88844454/192.168.75.130/root/input-work-186410214545932656 with rwxr-xr-x
INFO - TrackerDistributedCacheManager.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 - TrackerDistributedCacheManager.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$FileMapper.setup(57) | 开始启动setup了哈哈哈哈
获取的路径是： /root/hadoop1.2/hadooptmp/mapred/local/archive/9070031930820799196_1788685676_88844454/192.168.75.130/root/input/f1.txt
map里输出了
map里输出了
INFO - TestDistributed$FileMapper.cleanup(107) | 清空任务了。。。。。。
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) |