Question

我需要mapreduce作业的帮助，我的自定义分区器永远不会被调用。我检查了一百万次，但没有结果。它曾经工作了一段时间，我不知道为什么现在它不是。任何帮助都会非常有用我正在添加代码（对于非常简单的情况，它不能用于自定义键作为输入）。
Mapper输出100％的正确值，然后跳过分区器。

//import of libs
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
...

public class hbaseCountTest extends Configured implements Tool {
....

static class myMapper extends TableMapper<Text,Text> {
    @Override
    public void map(ImmutableBytesWritable rowKey,Result result, Context context) throws IOException {
        ...... //dropping some calculations
        context.write(new Text(gender), new Text(capsStr)); // everything is right here, checked.
    }

}

    public static class myPartitioner extends Partitioner<Text, Text> {
    @Override
    public int getPartition(Text key, Text value, int NumReduceTasks) {
//getPartitioner IS NEVER INVOKED
        System.out.println("partitioner started"); 
        String heur = value.toString().split(":")[0]; 
        int h = Integer.parseInt(heur);
        if (h<10) {
            ... return... //dropping some calculations
        } else if (h>9 && h<19) {
            ...
        } else 
            {
            ...
            }
    }

}

@Override
public int run(String[] arg0) throws Exception {
    Job job = Job.getInstance(getConf(), "jobName1");
    job.setNumReduceTasks(3);
    job.setJarByClass(getClass());
    Configuration conf = job.getConfiguration();
    HBaseConfiguration.merge(conf, HBaseConfiguration.create(conf));
    conf.addResource("/home/hadoop/Training/CDH4/hadoop-2.0.0-cdh4.0.0/conf/hadoop-local.xml");
    conf.addResource("/home/hadoop/Training/CDH4/hadoop-2.0.0-cdh4.0.0/conf/mapred-site.xml");
    FileSystem fs = FileSystem.get(getConf());
    if (fs.exists(new Path(arg0[0]))) {
        fs.delete(new Path(arg0[0]));
    }
    Scan scan = new Scan();
    scan.addColumn(toBytes(famName), toBytes(colNamePage));
    scan.addColumn(toBytes(famName), toBytes(colNameTime));
    scan.addColumn(toBytes(famName1), toBytes(colNameRegion));
    scan.addColumn(toBytes(famName1), toBytes(colNameGender));
    TableMapReduceUtil.initTableMapperJob(tableName, scan, myMapper.class, Text.class, Text.class, job);

    job.setPartitionerClass(myPartitioner.class);
    job.setReducerClass(myReducer.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    TextOutputFormat.setOutputPath(job, new Path(arg0[0]));
    job.setOutputKeyClass(TextOutputFormat.class);
    job.setOutputValueClass(TextOutputFormat.class);
            job.setNumReduceTasks(3);
    return job.waitForCompletion(true)?0:1;
}

}

提前多多谢谢，
亚历

Answer 1

尝试将减速器数量设置为大于唯一键数量的任何数量。

没有调用hadoop mapreduce分区器

1 个答案: