Question

I have a simple map/reduce job that scans one hbase table, and modifies another hbase table. The hadoop job seems to complete successfully, but when I check the hbase table, the entry does not appear in there.

Here is the hadoop program:

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.output.NullOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class HBaseInsertTest extends Configured implements Tool {

    @Override
    public int run(String[] args) throws Exception {
        String table = "duplicates";

        Scan scan = new Scan();
        scan.setCaching(500);
        scan.setCacheBlocks(false);

        Job job = new Job(getConf(), "HBaseInsertTest");
        job.setJarByClass(HBaseInsertTest.class);

        TableMapReduceUtil.initTableMapperJob(table, scan, Mapper.class, /* mapper output key = */null,
            /* mapper output value= */null, job);
        TableMapReduceUtil.initTableReducerJob("tablecopy", /*output table=*/null, /*reducer class=*/job);

        job.setNumReduceTasks(0);

        // Note that these are the default.
        job.setOutputFormatClass(NullOutputFormat.class);

        return job.waitForCompletion(true) ? 0 : 1;
    }

    private static class Mapper extends TableMapper<ImmutableBytesWritable, Put> {
        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            super.setup(context);
        }

        @Override
        public void map(ImmutableBytesWritable row, Result columns, Context context) throws IOException {
            long id = 1260018L;

            try {
                Put put = new Put(Bytes.toBytes(id));
                put.add(Bytes.toBytes("mapping"), Bytes.toBytes("foo"), Bytes.toBytes("bar"));
                context.write(row, put);
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration config = HBaseConfiguration.create();
        int res = ToolRunner.run(config, new HBaseInsertTest(), args);
        System.exit(res);
    }
}

From HBase shell:

hbase(main):008:0> get 'tablecopy', '1260018', 'mapping'
COLUMN                          CELL                                                                                    
0 row(s) in 0.0100 seconds

I’ve simplified the program a lot to try to demonstrate/isolate the problem. I’m also relatively new to both hadoop/hbase. I did verify that mapping is a column family that exists in the tablecopy table.

Answer 1

I think the problem was you were querying for
hbase(main):008:0> get ‘tablecopy’, ‘1260018’, ‘mapping’

instead you should have queried for this:
hbase(main):008:0> get ‘tablecopy’, 1260018, ‘mapping’

HBase was thinking it was a string key you were querying for, because of the quotations. Also if you just ran a simple client job at your end to retrieve this key from HBase, it would have gotten you the values correctly if it was already present.