大数据Hadoop之Mapreduce_学习笔记
1.MapReduce
1.7 MapReduce编程规范
用户编写的程序分成三个部分：Mapper、Reducer和Driver。
- 编写程序
- Mapper类
package com.atguigu.mapreduce;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class WordcountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
Text k = new Text();
IntWritable v = new IntWritable(1);
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取一行
String line = value.toString();
// 2 切割
String[] words = line.split(" ");
// 3 输出
for (String word : words) {
k.set(word);
context.write(k, v);
}
}
}
- 编写reducer类
package com.atguigu.mapreduce.wordcount;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class WordcountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
int sum;
IntWritable v = new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
// 1 累加求和
sum = 0;
for (IntWritable count : values) {
sum += count.get();
}
// 2 输出
v.set(sum);
context.write(key,v);
}
}
- 编写Driver驱动类
package com.atguigu.mapreduce.wordcount;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordcountDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
// 1 获取配置信息以及封装任务
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 2 设置jar加载路径
job.setJarByClass(WordcountDriver.class);
// 3 设置map和reduce类
job.setMapperClass(WordcountMapper.class);
job.setReducerClass(WordcountReducer.class);
// 4 设置map输出
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
// 5 设置最终输出kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// 6 设置输入和输出路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 提交
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
2. Hadoop序列化
序列化案例实操
- 编写MapReduce程序
（1）编写流量统计的Bean对象
package com.atguigu.mapreduce.flowsum;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
// 1 实现writable接口
public class FlowBean implements Writable{
private long upFlow;
private long downFlow;
private long sumFlow;
//2 反序列化时，需要反射调用空参构造函数，所以必须有
public FlowBean() {
super();
}
public FlowBean(long upFlow, long downFlow) {
super();
this.upFlow = upFlow;
this.downFlow = downFlow;
this.sumFlow = upFlow + downFlow;
}
//3 写序列化方法
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(downFlow);
out.writeLong(sumFlow);
}
//4 反序列化方法
//5 反序列化方法读顺序必须和写序列化方法的写顺序必须一致
@Override
public void readFields(DataInput in) throws IOException {
this.upFlow = in.readLong();
this.downFlow = in.readLong();
this.sumFlow = in.readLong();
}
// 6 编写toString方法，方便后续打印到文本
@Override
public String toString() {
return upFlow + "\t" + downFlow + "\t" + sumFlow;
}
public long getUpFlow() {
return upFlow;
}
public void setUpFlow(long upFlow) {
this.upFlow = upFlow;
}
public long getDownFlow() {
return downFlow;
}
public void setDownFlow(long downFlow) {
this.downFlow = downFlow;
}
public long getSumFlow() {
return sumFlow;
}
public void setSumFlow(long sumFlow) {
this.sumFlow = sumFlow;
}
}
(2) 编写mapper类
package com.atguigu.mapreduce.flowsum;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean>{
FlowBean v = new FlowBean();
Text k = new Text();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取一行
String line = value.toString();
// 2 切割字段
String[] fields = line.split("\t");
// 3 封装对象
// 取出手机号码
String phoneNum = fields[1];
// 取出上行流量和下行流量
long upFlow = Long.parseLong(fields[fields.length - 3]);
long downFlow = Long.parseLong(fields[fields.length - 2]);
k.set(phoneNum);
v.set(downFlow, upFlow);
// 4 写出
context.write(k, v);
}
}
（3）编写Reducer类
import org.apache.hadoop.mapreduce.Reducer;
public class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Context context)throws IOException, InterruptedException {
long sum_upFlow = 0;
long sum_downFlow = 0;
// 1 遍历所用bean，将其中的上行流量，下行流量分别累加
for (FlowBean flowBean : values) {
sum_upFlow += flowBean.getUpFlow();
sum_downFlow += flowBean.getDownFlow();
}
// 2 封装对象
FlowBean resultBean = new FlowBean(sum_upFlow, sum_downFlow);
// 3 写出
context.write(key, resultBean);
}
}
（4）编写Driver驱动类
package com.atguigu.mapreduce.flowsum;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class FlowsumDriver {
public static void main(String[] args) throws IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {
// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
args = new String[] {
"e:/input/inputflow", "e:/output1" };
// 1 获取配置信息，或者job对象实例
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 6 指定本程序的jar包所在的本地路径
job.setJarByClass(FlowsumDriver.class);
// 2 指定本业务job要使用的mapper/Reducer业务类
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
// 3 指定mapper输出数据的kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
// 4 指定最终输出的数据的kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
// 5 指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 将job中配置的相关参数，以及job所用的java类所在的jar包， 提交给yarn去运行
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
3. MapReduce框架原理
3.1 InputFormat数据输入
MapTask并行度决定机制
数据块：Block是HDFS物理上把数据分成一块一块。
数据切片：数据切片只是在逻辑上对输入进行分片，并不会在磁盘上将其切分成片进行存储。
Job提交流程源码和切片源码详解
waitForCompletion()
submit();
// 1建立连接
connect();
// 1）创建提交Job的代理
new Cluster(getConfiguration());
// （1）判断是本地yarn还是远程
initialize(jobTrackAddr, conf);
// 2 提交job
submitter.submitJobInternal(Job.this, cluster)
// 1）创建给集群提交数据的Stag路径
Path jobStagingArea = JobSubmissionFiles.getStagingDir(cluster, conf);
// 2）获取jobid ，并创建Job路径
JobID jobId = submitClient.getNewJobID();
// 3）拷贝jar包到集群
copyAndConfigureFiles(job, submitJobDir);
rUploader.uploadFiles(job, jobSubmitDir);
// 4）计算切片，生成切片规划文件
writeSplits(job, submitJobDir);
maps = writeNewSplits(job, jobSubmitDir);
input.getSplits(job);
// 5）向Stag路径写XML配置文件
writeConf(conf, submitJobFile);
conf.writeXml(out);
// 6）提交Job,返回提交状态
status = submitClient.submitJob(jobId, submitJobDir.toString(), job.getCredentials());
FileInputFormat切片源码解析(input.getSplits(job))
CombineTextInputFormat切片机制
框架默认的TextInputFormat切片机制是对任务按文件规划切片，不管文件多小，都会是一个单独的切片，都会交给一个MapTask，这样如果有大量小文件，就会产生大量的MapTask，处理效率极其低下。
测试举例：有4个小文件大小分别为1.7M、5.1M、3.4M以及6.8M这四个小文件，则虚拟存储之后形成6个文件块，大小分别为：1.7M，（2.55M、2.55M），3.4M以及（3.4M、3.4M）
最终会形成3个切片，大小分别为：
（1.7+2.55）M，（2.55+3.4）M，（3.4+3.4）M
CombineTextInputFormat案例实操
1．需求
将输入的大量小文件合并成一个切片统一处理。
（1）输入数据
准备4个小文件
（2）期望
期望一个切片处理4个文件
KeyValueTextInputFormat使用案例
（1）编写Mapper类
package com.atguigu.mapreduce.KeyValueTextInputFormat;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class KVTextMapper extends Mapper<Text, Text, Text, LongWritable>{
// 1 设置value
LongWritable v = new LongWritable(1);
@Override
protected void map(Text key, Text value, Context context)
throws IOException, InterruptedException {
// banzhang ni hao
// 2 写出
context.write(key, v);
}
}
（2）编写Reducer类
package com.atguigu.mapreduce.KeyValueTextInputFormat;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class KVTextReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
LongWritable v = new LongWritable();
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long sum = 0L;
// 1 汇总统计
for (LongWritable value : values) {
sum += value.get();
}
v.set(sum);
// 2 输出
context.write(key, v);
}
}
（3）编写Driver类
package com.atguigu.mapreduce.keyvaleTextInputFormat;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class KVTextDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
// 设置切割符
conf.set(KeyValueLineRecordReader.KEY_VALUE_SEPERATOR, " ");
// 1 获取job对象
Job job = Job.getInstance(conf);
// 2 设置jar包位置，关联mapper和reducer
job.setJarByClass(KVTextDriver.class);
job.setMapperClass(KVTextMapper.class);
job.setReducerClass(KVTextReducer.class);
// 3 设置map输出kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
// 4 设置最终输出kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
// 5 设置输入输出数据路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
// 设置输入格式
job.setInputFormatClass(KeyValueTextInputFormat.class);
// 6 设置输出数据路径
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 提交job
job.waitForCompletion(true);
}
}
NLineInputFormat使用案例
(1) 编写Mapper类
package com.atguigu.mapreduce.nline;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class NLineMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
private Text k = new Text();
private LongWritable v = new LongWritable(1);
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取一行
String line = value.toString();
// 2 切割
String[] splited = line.split(" ");
// 3 循环写出
for (int i = 0; i < splited.length; i++) {
k.set(splited[i]);
context.write(k, v);
}
}
}
（2）编写Reducer类
package com.atguigu.mapreduce.nline;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class NLineReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
LongWritable v = new LongWritable();
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long sum = 0l;
// 1 汇总
for (LongWritable value : values) {
sum += value.get();
}
v.set(sum);
// 2 输出
context.write(key, v);
}
}
（3）编写Driver类
package com.atguigu.mapreduce.nline;
import java.io.IOException;
import java.net.URISyntaxException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.NLineInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class NLineDriver {
public static void main(String[] args) throws IOException, URISyntaxException, ClassNotFoundException, InterruptedException {
// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
args = new String[] {
"e:/input/inputword", "e:/output1" };
// 1 获取job对象
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 7设置每个切片InputSplit中划分三条记录
NLineInputFormat.setNumLinesPerSplit(job, 3);
// 8使用NLineInputFormat处理记录数
job.setInputFormatClass(NLineInputFormat.class);
// 2设置jar包位置，关联mapper和reducer
job.setJarByClass(NLineDriver.class);
job.setMapperClass(NLineMapper.class);
job.setReducerClass(NLineReducer.class);
// 3设置map输出kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
// 4设置最终输出kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
// 5设置输入输出数据路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 6提交job
job.waitForCompletion(true);
}
}
测试：
（1）输入数据
banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang banzhang ni hao
xihuan hadoop banzhang
（2）输出结果的切片数
略
（1）自定义InputFront
package com.atguigu.mapreduce.inputformat;
import java.io.IOException;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
// 定义类继承FileInputFormat
public class WholeFileInputformat extends FileInputFormat<Text, BytesWritable>{
@Override
protected boolean isSplitable(JobContext context, Path filename) {
return false;
}
@Override
public RecordReader<Text, BytesWritable> createRecordReader(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
WholeRecordReader recordReader = new WholeRecordReader();
recordReader.initialize(split, context);
return recordReader;
}
}
(2) 自定义RecordReader类
package com.atguigu.mapreduce.inputformat;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
public class WholeRecordReader extends RecordReader<Text, BytesWritable>{
private Configuration configuration;
private FileSplit split;
private boolean isProgress= true;
private BytesWritable value = new BytesWritable();
private Text k = new Text();
@Override
public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
this.split = (FileSplit)split;
configuration = context.getConfiguration();
}
@Override
public boolean nextKeyValue() throws IOException, InterruptedException {
if (isProgress) {
// 1 定义缓存区
byte[] contents = new byte[(int)split.getLength()];
FileSystem fs = null;
FSDataInputStream fis = null;
try {
// 2 获取文件系统
Path path = split.getPath();
fs = path.getFileSystem(configuration);
// 3 读取数据
fis = fs.open(path);
// 4 读取文件内容
IOUtils.readFully(fis, contents, 0,contents.length);
// 5 输出文件内容
value.set(contents, 0, contents.length);
// 6 获取文件路径及名称
String name = split.getPath().toString();
// 7 设置输出的key值
k.set(name);
} catch (Exception e) {
}finally {
IOUtils.closeStream(fis);
}
isProgress = false;
return true;
}
return false;
}
@Override
public Text getCurrentKey() throws IOException, InterruptedException {
return k;
}
@Override
public BytesWritable getCurrentValue() throws IOException, InterruptedException {
return value;
}
@Override
public float getProgress() throws IOException, InterruptedException {
return 0;
}
@Override
public void close() throws IOException {
}
}
（3）编写SequenceFileMapper类处理流程
package com.atguigu.mapreduce.inputformat;
import java.io.IOException;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
public class SequenceFileMapper extends Mapper<Text, BytesWritable, Text, BytesWritable>{
@Override
protected void map(Text key, BytesWritable value, Context context) throws IOException, InterruptedException {
context.write(key, value);
}
}
略
3.2MapReduce工作流程
上面的流程是整个MapReduce最全工作流程，但是Shuffle过程只是从第7步开始到第16步结束，具体Shuffle过程详解，如下：
1）MapTask收集我们的map()方法输出的kv对，放到内存缓冲区中
2）从内存缓冲区不断溢出本地磁盘文件，可能会溢出多个文件
3）多个溢出文件会被合并成大的溢出文件
4）在溢出过程及合并的过程中，都要调用Partitioner进行分区和针对key进行排序
5）ReduceTask根据自己的分区号，去各个MapTask机器上取相应的结果分区数据
6）ReduceTask会取到同一个分区的来自不同MapTask的结果文件，ReduceTask会将这些文件再进行合并（归并排序）
7）合并成大文件后，Shuffle的过程也就结束了，后面进入ReduceTask的逻辑运算过程（从文件中取出一个一个的键值对Group，调用用户自定义的reduce()方法）
Shuffle机制
Map方法之后，Reduce方法之前的数据处理过程称之为Shuffle。如图4-14所示。
