Retry attempted 10 times without completing, bailing out解决-优快云博客

本文分享了在HBase 2.0.0版本中，使用bulkload方式批量加载数据遇到异常的解决过程。通过修改代码和使用特定命令，成功实现了数据的批量导入，为HBase的大规模数据处理提供了实用技巧。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

今天在做通过bulkload的方式批量加载数据到HBase中去的时候遇到了这个异常

然后去网上找到了这个方案，我的Hbase是2.0.0，所以试了也没用

具体代码如下：

BulkLoadMain.class

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.hdfs.DFSUtil;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class BulkLoadMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        Configuration conf = super.getConf();

        //获取job对象
        Job job = Job.getInstance(conf, "bulkLoad");

        Connection connection = ConnectionFactory.createConnection(conf);

        Table table = connection.getTable(TableName.valueOf("myuser2"));

        //读取文件
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("hdfs://node01:8020/hbase/input"));

        job.setMapperClass(HDFSReadMapper.class);
        job.setMapOutputKeyClass(ImmutableBytesWritable.class);
        job.setMapOutputValueClass(Put.class);

        //将数据输出成为HFile格式

        //Job job, Table table, RegionLocator regionLocator
        //配置增量的添加数据
        HFileOutputFormat2.configureIncrementalLoad(job,table,connection.getRegionLocator(TableName.valueOf("myuser2")));
        //设置输出classs类，决定了我们输出数据格式
        job.setOutputFormatClass(HFileOutputFormat2.class);
        //设置输出路径
        HFileOutputFormat2.setOutputPath(job,new Path("hdfs://node01:8020/hbase/hfile_out"));

        boolean b = job.waitForCompletion(true);

        return b?0:1;
    }

    public static void main(String[] args) throws Exception {
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
        int run = ToolRunner.run(configuration, new BulkLoadMain(), args);
        System.exit(run);
    }
}

BulkLoadMapper.class

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * LongWritable  k1类型
 * Text   V1类型
 * ImmutableBytesWritable   rowkey
 * Put  插入的对象
 */
public class BulkLoadMapper 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("\t");
        Put put = new Put(split[0].getBytes());
        put.addColumn("f1".getBytes(),"name".getBytes(),split[1].getBytes());
        put.addColumn("f1".getBytes(),"age".getBytes(),split[2].getBytes());
        context.write(new ImmutableBytesWritable(split[0].getBytes()),put);
    }
}

PutMain.class


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.tool.LoadIncrementalHFiles;

import java.io.IOException;

public class PutMain {
    public static void main(String[] args) throws IOException {
        Configuration conf = HBaseConfiguration.create();
        Connection connection = ConnectionFactory.createConnection(conf);

        Admin admin = connection.getAdmin();
        TableName tableName = TableName.valueOf("myuser2");
        Table table = connection.getTable(tableName);
        LoadIncrementalHFiles load = new LoadIncrementalHFiles(conf);
        load.doBulkLoad(new Path("hdfs://node01:8020/hbase/hfile_out"),admin,table,connection.getRegionLocator(tableName));
    }
}

解决方法：

最后我把这个打包后，去集群上用如下命令跑了一下：

yarn jar bulkload-1.0-SNAPSHOT.jar PutMain /hbase/hfile_out myuser2

最后完美解决了！

Hbase的数据都有了