DistributedCache是Hadoop的一个分布式文件缓存类
DistributedCache是Hadoop的一个分布式文件缓存类，使用它有时候能完成一些比较方便的事，DistributedCache第一个比较方便的作用就是来完成分布式文件共享这件事，第二个比较有用的场景，就是在执行一些join操作时，将小表放入cache中，来提高连接效率。
那么，散仙今天要介绍的是如何使用DistributedCache来共享全局的缓存文件。
下面我们先通过一个表格来看下，在hadoop中，使用全局变量或全局文件共享的几种方法
| 序号 | 方法 |
| 1 | 使用Configuration的set方法，只适合数据内容比较小的场景 |
| 2 | 将共享文件放在HDFS上，每次都去读取，效率比较低 |
| 3 | 将共享文件放在DistributedCache里，在setup初始化一次后，即可多次使用，缺点是不支持修改操作，仅能读取 |
本篇散仙，将重点介绍，使用DistributedCache的方法，来共享一些全局配置文件，或变量，通过DistributedCache的addCacheFile方法，我们把HDFS上的一些文件，在hadoop任务启动时，就载入缓存里面，以供全局使用，使用这个方法时，我们需要注意几点，首先我们的本地文件，需要上传到HDFS上，然后再这个方法里，写入加载路径，接下来，我们就可以，在setup初始化时，读取出，其内容，然后在map或reduce方法，执行时，就可以实时的使用这个文件的一些内容了。
散仙，测试共享的一个文件内容如下：
代码如下，注意散仙在setup方法里，读取了文件内容，并打印：
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);
}
} 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);
}
}
在web页面上，查询日志输入情况，如下截图所示 
当然，我们也可以根据web上的路径，到对应的日志目录下，查找日志的内容，看到上图就说明，我们上传的共享文件，读取成功了，只要在setup方法里面进行初始化后，对我们的程序来说，就是全局共享了，然后我们就可以结合我们的业务逻辑，来处理一些事了。
最后，在简单总结一下：DistributedCache文件共享的模式，只能在集群的环境中使用，如果在Local模式下测试，就会报如下的文件找不到异常：
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/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input-work--1953076903080970848 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/-4778653900406898379_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/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input/f1.txt INFO - JobClient.monitorAndPrintJob(1380) | Running job: job_local697121855_0001 INFO - LocalJobRunner$Job.run(340) | Waiting for map tasks INFO - LocalJobRunner$Job$MapTaskRunnable.run(204) | Starting task: attempt_local697121855_0001_m_000000_0 INFO - Task.initialize(534) | Using ResourceCalculatorPlugin : null INFO - MapTask.runNewMapper(729) | Processing split: hdfs://192.168.75.130:9000/root/input/f1.txt:0+31 INFO - MapTask$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$FileMapper.setup(60) | 开始启动setup了哈哈哈哈 获取的路径是： /root/hadoop1.2/hadooptmp/mapred/local/archive/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input/f1.txt INFO - MapTask$MapOutputBuffer.flush(1289) | Starting flush of map output INFO - LocalJobRunner$Job.run(348) | Map task executor complete. WARN - LocalJobRunner$Job.run(435) | job_local697121855_0001 java.lang.Exception: java.io.FileNotFoundException: File /root/hadoop1.2/hadooptmp/mapred/local/archive/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input/f1.txt does not exist. at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:354) Caused by: java.io.FileNotFoundException: File /root/hadoop1.2/hadooptmp/mapred/local/archive/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input/f1.txt does not exist. at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:402) at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:255) at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:125) at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:283) at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:427) at com.qin.testdistributed.TestDistributed$FileMapper.setup(TestDistributed.java:67) at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:142) at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:764) at org.apache.hadoop.mapred.MapTask.run(MapTask.java:364) at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:223) at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471) at java.util.concurrent.FutureTask$Sync.innerRun(FutureTask.java:334) at java.util.concurrent.FutureTask.run(FutureTask.java:166) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1110) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:603) at java.lang.Thread.run(Thread.java:722) INFO - JobClient.monitorAndPrintJob(1393) | map 0% reduce 0% INFO - JobClient.monitorAndPrintJob(1448) | Job complete: job_local697121855_0001 INFO - Counters.log(585) | Counters: 0
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/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input-work--1953076903080970848 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/-4778653900406898379_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/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input/f1.txt INFO - JobClient.monitorAndPrintJob(1380) | Running job: job_local697121855_0001 INFO - LocalJobRunner$Job.run(340) | Waiting for map tasks INFO - LocalJobRunner$Job$MapTaskRunnable.run(204) | Starting task: attempt_local697121855_0001_m_000000_0 INFO - Task.initialize(534) | Using ResourceCalculatorPlugin : null INFO - MapTask.runNewMapper(729) | Processing split: hdfs://192.168.75.130:9000/root/input/f1.txt:0+31 INFO - MapTask$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$FileMapper.setup(60) | 开始启动setup了哈哈哈哈 获取的路径是： /root/hadoop1.2/hadooptmp/mapred/local/archive/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input/f1.txt INFO - MapTask$MapOutputBuffer.flush(1289) | Starting flush of map output INFO - LocalJobRunner$Job.run(348) | Map task executor complete. WARN - LocalJobRunner$Job.run(435) | job_local697121855_0001 java.lang.Exception: java.io.FileNotFoundException: File /root/hadoop1.2/hadooptmp/mapred/local/archive/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input/f1.txt does not exist. at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:354) Caused by: java.io.FileNotFoundException: File /root/hadoop1.2/hadooptmp/mapred/local/archive/-4778653900406898379_1788685676_88844454/192.168.75.130/root/input/f1.txt does not exist. at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:402) at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:255) at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:125) at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:283) at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:427) at com.qin.testdistributed.TestDistributed$FileMapper.setup(TestDistributed.java:67) at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:142) at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:764) at org.apache.hadoop.mapred.MapTask.run(MapTask.java:364) at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:223) at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471) at java.util.concurrent.FutureTask$Sync.innerRun(FutureTask.java:334) at java.util.concurrent.FutureTask.run(FutureTask.java:166) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1110) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:603) at java.lang.Thread.run(Thread.java:722) INFO - JobClient.monitorAndPrintJob(1393) | map 0% reduce 0% INFO - JobClient.monitorAndPrintJob(1448) | Job complete: job_local697121855_0001 INFO - Counters.log(585) | Counters: 0
如果你很幸运，在1.x的hadoop里看到如下所示的异常，那么你应该考虑如下的几个问题，第一，是不是以Local模式启动的MR任务，第二读取时的路径是不是有问题，使用DistributedCache共享的文件，会在我们每个节点上配置的目录里面找到对应的共享文件：
Xml代码 
- <?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>
<?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>
共享的文件，会被下载到每个节点上的指定的文件夹里找到。
散仙找的一个的路径：
/root/hadoop1.2/mylogs/taskTracker/distcache/2726204645197711229_1788685676_88844454/192.168.75.130/root/input
其他的节点上也一样，只不过IP地址不一样，截图如下：
至此，我们就可以使用轻松的来使用DistributedCache来共享一些比较大的文件，或压缩包了。
相关推荐
loviezhang 2020-06-08
粗茶淡饭 2020-05-27
middleware0 2020-05-06
Cheetahcubs 2020-05-06
ol0 2020-05-02
枫叶上的雨露 2020-05-02
loviezhang 2020-03-28
blncle 2020-03-20
YZR 2020-02-29
枫叶上的雨露 2020-01-09
nbfcome 2019-11-13
亦碎流年 2019-11-01
Cheetahcubs 2019-10-30
LandryBean 2019-10-30
zhangll00 2019-10-27
summerZBH 2019-04-11