hbase学习笔记-bulkload方式批量加载数据到HBase

加载数据到HBase当中去的方式多种多样，我们可以使用HBase的javaAPI或者使用sqoop将我们的数据写入或者导入到HBase当中去，但是这些方式不是慢就是在导入的过程的占用Region资料导致效率低下，我们也可以通过MR的程序，将我们的数据直接转换成HBase的最终存储格式HFile，然后直接load数据到HBase当中去即可.

• 优势

  • （1）.导入过程不占用Region资源

  • （2）.能快速导入海量的数据

  • （3）.节省内存

1：开发生成HFile文件的代码

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.HFileOutputFormat2;
import org.apache.hadoop.hbase.util.Bytes;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class HBaseLoad {

    public static class LoadMapper  extends Mapper<LongWritable,Text,ImmutableBytesWritable,Put> {
        @Override
        protected void map(LongWritable key, Text value, Mapper.Context context) throws IOException, InterruptedException {
            String[] split = value.toString().split(" ");
            Put put = new Put(Bytes.toBytes(split[0]));
            put.addColumn("f1".getBytes(),"name".getBytes(),split[1].getBytes());
            put.addColumn("f1".getBytes(),"age".getBytes(), split[2].getBytes());
            context.write(new ImmutableBytesWritable(Bytes.toBytes(split[0])),put);
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
            final String INPUT_PATH=  "hdfs://node1:9000/input";
            final String OUTPUT_PATH= "hdfs://node1:9000/output_HFile";
            Configuration conf = HBaseConfiguration.create();

            Connection connection = ConnectionFactory.createConnection(conf);
            Table table = connection.getTable(TableName.valueOf("t4"));
            Job job= Job.getInstance(conf);

            job.setJarByClass(HBaseLoad.class);
            job.setMapperClass(LoadMapper.class);
            job.setMapOutputKeyClass(ImmutableBytesWritable.class);
            job.setMapOutputValueClass(Put.class);
            //指定输出的类型HFileOutputFormat2
            job.setOutputFormatClass(HFileOutputFormat2.class);

         HFileOutputFormat2.configureIncrementalLoad(job,table,connection.getRegionLocator(TableName.valueOf("t4")));
            FileInputFormat.addInputPath(job,new Path(INPUT_PATH));
            FileOutputFormat.setOutputPath(job,new Path(OUTPUT_PATH));
            System.exit(job.waitForCompletion(true)?0:1);


    }
}

2：打成jar包提交到集群中运行

hadoop jar hbase_java_api-1.0-SNAPSHOT.jar com.study.HBaseLoad

3：加载HFile文件到hbase表中

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.mapreduce.LoadIncrementalHFiles;

public class LoadData {
    public static void main(String[] args) throws Exception {
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum", "node1:2181,node2:2181,node3:2181");
    //获取数据库连接
    Connection connection =  ConnectionFactory.createConnection(configuration);
    //获取表的管理器对象
    Admin admin = connection.getAdmin();
    //获取table对象
    TableName tableName = TableName.valueOf("t4");
    Table table = connection.getTable(tableName);
    //构建LoadIncrementalHFiles加载HFile文件
    LoadIncrementalHFiles load = new LoadIncrementalHFiles(configuration);
    load.doBulkLoad(new Path("hdfs://node1:9000/output_HFile"), admin,table,connection.getRegionLocator(tableName));
 }
}

• 命令加载

  • 命令格式

    hadoop jar hbase-server-VERSION.jar completebulkload [-c /path/to/hbase/config/hbase-site.xml] /output testtable
    

  • 先将hbase的jar包添加到hadoop的classpath路径下

    export HBASE_HOME=/opt/hbase
    export HADOOP_HOME=/opt/hadoop
    export HADOOP_CLASSPATH=`${HBASE_HOME}/bin/hbase mapredcp`
    

  • 命令加载演示

hadoop jar /opt/hbase/lib/hbase-server-1.2.1.jar completebulkload /output_HFile t5 

​