Hadoop大数据平台架构与实践--基础篇

最新推荐文章于 2022-03-23 17:02:56 发布

chengyuelie9585

最新推荐文章于 2022-03-23 17:02:56 发布

阅读量122

点赞数

原文链接：https://my.oschina.net/u/3765607/blog/2051698

版权

简介：本课程首页介绍了hadoop架构体系，包括NameNode和DataNode的作用；然后介绍了MapReduce作业的中间过程和原理，包括缓存的使用，相关参数的性能调优；之后介绍了如何运用MapReduce实现矩阵相乘，并且实现简单的推荐算法

使用wget工具：

设置JAVA_HOME的路径：

设置hadoop的工作目录，namenode的目录，文件系统namenode的访问：

设置文件系统数据的存放目录：

设置任务调度器的访问方式：

添加HADOOP_HOME和修改PATH：

测试Hadoop的安装效果：

namenode的格式化：

进行启动：

查看hadoop是否正常运行：

查看hadoop下的文件：

若某个节点出现故障：

若某个机架出现故障：

客户端发送文件读请求——>namenode返回元数据（从哪些datanode找到）——>客户端读取block，下载下来之后组装；

客户端文件拆分成block——>通知namenode返回可用的有足够磁盘空间的datanode——>客户端对block进行写入——>流水线复制——>更新元数据；

mkdir examples //生成一个examples目录

cd examples //进入examples文件路径

mkdir word_count //生成word_count目录

cd word_count //进入word_count目录

mkdir input //用于存放提交的作业

mkdir word_count_class //用于存放编译好的类

hadoop存放文件命令 hadoop fs -put hadoop-env.sh /input

hadoop获取文件命令 hadoop fs -get

hadoop删除文件命令 hadoop fs -rm

hadoop创建目录命令 hadoop fs -mkdir

hadoop 格式化操作 : hadoop namenode -formet

hadoop查看存储信息 hadoop dfsadmin -report

MapReduce容错机制

1.重复执行，任务失败后，重复执行4次；

2.推测执行，对于较慢的任务，新建taskTracker执行相同任务，使用最先完成的task。

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.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

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

       public void map(LongWritable key, Text value, Context context)
               throws IOException, InterruptedException {
           String line = value.toString();
           StringTokenizer token = new StringTokenizer(line);
           while (token.hasMoreTokens()) {
               word.set(token.nextToken());
               context.write(word, one);
           }
       }
   }

public static class WordCountReduce extends
 Reducer<Text, IntWritable, Text, IntWritable> {
 public void reduce(Text key, Iterable<IntWritable> values,
 Context context) throws IOException, InterruptedException {
 int sum = 0;
 for (IntWritable val : values) {
 sum += val.get();
 }
 context.write(key, new IntWritable(sum));
 }
 }

   public static void main(String[] args) throws Exception {
       Configuration conf = new Configuration();
       Job job = new Job(conf);
       job.setJarByClass(WordCount.class);
       job.setJobName("wordcount");
       job.setOutputKeyClass(Text.class);
       job.setOutputValueClass(IntWritable.class);
       job.setMapperClass(WordCountMap.class);
       job.setReducerClass(WordCountReduce.class);
       job.setInputFormatClass(TextInputFormat.class);
       job.setOutputFormatClass(TextOutputFormat.class);
       FileInputFormat.addInputPath(job, new Path(args[0]));
       FileOutputFormat.setOutputPath(job, new Path(args[1]));
       job.waitForCompletion(true);
   }
}

public class Sort {

public static class Map extends
Mapper<Object, Text, IntWritable, IntWritable> {

private static IntWritable data = new IntWritable();

       public void map(Object key, Text value, Context context)
               throws IOException, InterruptedException {
           String line = value.toString();

data.set(Integer.parseInt(line));

context.write(data, new IntWritable(1));

}

public static class Reduce extends
Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {

private static IntWritable linenum = new IntWritable(1);

public void reduce(IntWritable key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {

for (IntWritable val : values) {

context.write(linenum, key);

linenum = new IntWritable(linenum.get() + 1);
}

}
}

public static class Partition extends Partitioner<IntWritable, IntWritable> {

@Override
 public int getPartition(IntWritable key, IntWritable value,
 int numPartitions) {
 int MaxNumber = 65223;
 int bound = MaxNumber / numPartitions + 1;
 int keynumber = key.get();
 for (int i = 0; i < numPartitions; i++) {
 if (keynumber < bound * i && keynumber >= bound * (i - 1))
 return i - 1;
 }
 return 0;
 }
 }

   /**
   * @param args
   */

public static void main(String[] args) throws Exception {
 // TODO Auto-generated method stub
 Configuration conf = new Configuration();
 String[] otherArgs = new GenericOptionsParser(conf, args)
 .getRemainingArgs();
 if (otherArgs.length != 2) {
 System.err.println("Usage WordCount <int> <out>");
 System.exit(2);
 }
 Job job = new Job(conf, "Sort");
 job.setJarByClass(Sort.class);
 job.setMapperClass(Map.class);
 job.setPartitionerClass(Partition.class);
 job.setReducerClass(Reduce.class);
 job.setOutputKeyClass(IntWritable.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);
 }