关于mapreduce的一些注意细节
如果把mapreduce程序打包放到了liux下去运行,
命令java –cp xxx.jar 主类名
如果报错了,说明是缺少相关的依赖jar包
用命令hadoop jar xxx.jar 类名因为在集群机器上用 hadoop jar xx.jar mr.wc.JobSubmitter 命令来启动客户端main方法时,hadoop jar这个命令会将所在机器上的hadoop安装目录中的jar包和配置文件加入到运行时的classpath中
那么,我们的客户端main方法中的new Configuration()语句就会加载classpath中的配置文件,自然就有了
fs.defaultFS 和 mapreduce.framework.name 和 yarn.resourcemanager.hostname 这些参数配置
会把本地hadoop的相关的所有jar包都会引用
Mapreduce也有本地的job运行,就是可以不用提交到yarn上,可以以单机的模式跑一边以多个线程模拟也可以。
就是如果不管在Linux下还是windows下,提交job都会默认的提交到本地去运行,
如果在linux默认提交到yarn上运行,需要写配置文件hadoop/etc/mapred-site.xml文件
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>
Key,value对,如果是自己的类的话,那么这个类要实现Writable,同时要把你想序列化的数据转化成二进制,然后放到重写方法wirte参数的DataOutput里面,另一个readFields重写方法是用来反序列化用的,
注意反序列化的时候,会先拿这个类的无参构造方法构造出一个对象出来,然后再通过readFields方法来复原这个对象。
DataOutput也是一种流,只不过是hadoop的在封装,自己用的时候,里面需要加个FileOutputStream对象
DataOutput写字符串的时候要用writeUTF(“字符串”),他这样编码的时候,会在字符串的前面先加上字符串的长度,这是考虑到字符编码对其的问题,hadoop解析的时候就会先读前面两个字节,看一看这个字符串有多长,不然如果用write(字符串.getBytes())这样他不知道这个字符串到底有多少个字节。
在reduce阶段,如果把一个对象写到hdfs里面,那么会调用字符串的toString方法,你可以重写这个类的toString方法
举例,下面这个类就可以在hadoop里序列化
- package mapreduce2;
- import java.io.DataInput;
- import java.io.DataOutput;
- import java.io.IOException;
- import org.apache.hadoop.hdfs.client.HdfsClientConfigKeys.Write;
- import org.apache.hadoop.io.Writable;
- import org.apache.hadoop.util.Waitable;
- public class FlowBean implements Writable {
- private int up;//上行流量
- private int down;//下行流量
- private int sum;//总流量
- private String phone;//电话号
-
- public FlowBean(int up, int down, String phone) {
- this.up = up;
- this.down = down;
- this.sum = up + down;
- this.phone = phone;
- }
- public int getUp() {
- return up;
- }
- public void setUp(int up) {
- this.up = up;
- }
- public int getDown() {
- return down;
- }
- public void setDown(int down) {
- this.down = down;
- }
- public int getSum() {
- return sum;
- }
- public void setSum(int sum) {
- this.sum = sum;
- }
- public String getPhone() {
- return phone;
- }
- public void setPhone(String phone) {
- this.phone = phone;
- }
- @Override
- public void readFields(DataInput di) throws IOException {
- //注意这里读的顺序要和写的顺序是一样的
- this.up = di.readInt();
- this.down = di.readInt();
- this.sum = this.up + this.down;
- this.phone = di.readUTF();
- }
- @Override
- public void write(DataOutput Do) throws IOException {
- Do.writeInt(this.up);
- Do.writeInt(this.down);
- Do.writeInt(this.sum);
- Do.writeUTF(this.phone);
- }
- @Override
- public String toString() {
- return "电话号"+this.phone+" 总流量"+this.sum;
- }
- }
当所有的reduceTask都运行完之后,还会调用一个cleanup方法
应用练习:统计一个页面访问总量为n条的数据
方案一:只用一个reducetask,利用cleanup方法,在reducetask阶段,先不直接放到hdfs里面,而是存到一个Treemap里面
再在reducetask结束后,在cleanup里面通过把Treemap里面前五输出到HDFS里面;
- package cn.edu360.mr.page.topn;
- public class PageCount implements Comparable<PageCount>{
-
- private String page;
- private int count;
-
- public void set(String page, int count) {
- this.page = page;
- this.count = count;
- }
-
- public String getPage() {
- return page;
- }
- public void setPage(String page) {
- this.page = page;
- }
- public int getCount() {
- return count;
- }
- public void setCount(int count) {
- this.count = count;
- }
- @Override
- public int compareTo(PageCount o) {
- return o.getCount()-this.count==0?this.page.compareTo(o.getPage()):o.getCount()-this.count;
- }
-
-
- }
map类
- 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 PageTopnMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
-
- @Override
- protected void map(LongWritable key, Text value, Context context)
- throws IOException, InterruptedException {
- String line = value.toString();
- String[] split = line.split(" ");
- context.write(new Text(split[1]), new IntWritable(1));
- }
- }
reduce类
- package cn.edu360.mr.page.topn;
- import java.io.IOException;
- import java.util.Map.Entry;
- import java.util.Set;
- import java.util.TreeMap;
- import org.apache.hadoop.conf.Configuration;
- import org.apache.hadoop.io.IntWritable;
- import org.apache.hadoop.io.Text;
- import org.apache.hadoop.mapreduce.Reducer;
- public class PageTopnReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
-
- TreeMap<PageCount, Object> treeMap = new TreeMap<>();
-
- @Override
- protected void reduce(Text key, Iterable<IntWritable> values,
- Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
- int count = 0;
- for (IntWritable value : values) {
- count += value.get();
- }
- PageCount pageCount = new PageCount();
- pageCount.set(key.toString(), count);
-
- treeMap.put(pageCount,null);
-
- }
- @Override
- protected void cleanup(Context context)
- throws IOException, InterruptedException {
- Configuration conf = context.getConfiguration();
//可以在cleanup里面拿到configuration,从里面读取要拿前几条数据 - int topn = conf.getInt("top.n", 5);
-
-
- Set<Entry<PageCount, Object>> entrySet = treeMap.entrySet();
- int i= 0;
-
- for (Entry<PageCount, Object> entry : entrySet) {
- context.write(new Text(entry.getKey().getPage()), new IntWritable(entry.getKey().getCount()));
- i++;
- if(i==topn) return;
- }
- }
- }
然后jobSubmit类,注意这个要设定Configuration,这里面有几种方法
第一种是加载配置文件
- Configuration conf = new Configuration();
- conf.addResource("xx-oo.xml");
然后再在xx-oo.xml文件里面写
- <configuration>
- <property>
- <name>top.n</name>
- <value>6</value>
- </property>
- </configuration>
第二种方式
- //通过直接设定
- conf.setInt("top.n", 3);
- //通过对java主程序 直接传进来的参数
- conf.setInt("top.n", Integer.parseInt(args[0]));
第三种方式通过获取配置文件参数
- Properties props = new Properties();
- props.load(JobSubmitter.class.getClassLoader().getResourceAsStream("topn.properties"));
- conf.setInt("top.n", Integer.parseInt(props.getProperty("top.n")));
然后再在topn.properties里面配置参数
subsubmit类,默认在本机模拟运行
- 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 JobSubmitter {
- public static void main(String[] args) throws Exception {
- /**
- * 通过加载classpath下的*-site.xml文件解析参数
- */
- Configuration conf = new Configuration();
- conf.addResource("xx-oo.xml");
-
- /**
- * 通过代码设置参数
- */
- //conf.setInt("top.n", 3);
- //conf.setInt("top.n", Integer.parseInt(args[0]));
-
- /**
- * 通过属性配置文件获取参数
- */
- /*Properties props = new Properties();
- props.load(JobSubmitter.class.getClassLoader().getResourceAsStream("topn.properties"));
- conf.setInt("top.n", Integer.parseInt(props.getProperty("top.n")));*/
-
- Job job = Job.getInstance(conf);
- job.setJarByClass(JobSubmitter.class);
- job.setMapperClass(PageTopnMapper.class);
- job.setReducerClass(PageTopnReducer.class);
- job.setMapOutputKeyClass(Text.class);
- job.setMapOutputValueClass(IntWritable.class);
-
- job.setOutputKeyClass(Text.class);
- job.setOutputValueClass(IntWritable.class);
- FileInputFormat.setInputPaths(job, new Path("F:\\mrdata\\url\\input"));
- FileOutputFormat.setOutputPath(job, new Path("F:\\mrdata\\url\\output"));
- job.waitForCompletion(true);
- }
- }
额外java知识点补充
Treemap,放进去的东西会自动排序
两种Treemap的自定义方法,第一种是传入一个Comparator
- public class TreeMapTest {
-
- public static void main(String[] args) {
-
- TreeMap<FlowBean, String> tm1 = new TreeMap<>(new Comparator<FlowBean>() {
- @Override
- public int compare(FlowBean o1, FlowBean o2) {
- //如果两个类总流量相同的会比较电话号
- if( o2.getAmountFlow()-o1.getAmountFlow()==0){
- return o1.getPhone().compareTo(o2.getPhone());
- }
- //如果流量不同,就按从小到大的顺序排序
- return o2.getAmountFlow()-o1.getAmountFlow();
- }
- });
- FlowBean b1 = new FlowBean("1367788", 500, 300);
- FlowBean b2 = new FlowBean("1367766", 400, 200);
- FlowBean b3 = new FlowBean("1367755", 600, 400);
- FlowBean b4 = new FlowBean("1367744", 300, 500);
-
- tm1.put(b1, null);
- tm1.put(b2, null);
- tm1.put(b3, null);
- tm1.put(b4, null);
- //treeset的遍历
- Set<Entry<FlowBean,String>> entrySet = tm1.entrySet();
- for (Entry<FlowBean,String> entry : entrySet) {
- System.out.println(entry.getKey() +"\t"+ entry.getValue());
- }
- }
- }
第二种是在这个类中,实现一个Comparable接口
- package cn.edu360.mr.page.topn;
- public class PageCount implements Comparable<PageCount>{
-
- private String page;
- private int count;
-
- public void set(String page, int count) {
- this.page = page;
- this.count = count;
- }
-
- public String getPage() {
- return page;
- }
- public void setPage(String page) {
- this.page = page;
- }
- public int getCount() {
- return count;
- }
- public void setCount(int count) {
- this.count = count;
- }
- @Override
- public int compareTo(PageCount o) {
- return o.getCount()-this.count==0?this.page.compareTo(o.getPage()):o.getCount()-this.count;
- }
-
-
- }