View Javadoc

1   /**
2    *
3    * Licensed to the Apache Software Foundation (ASF) under one
4    * or more contributor license agreements.  See the NOTICE file
5    * distributed with this work for additional information
6    * regarding copyright ownership.  The ASF licenses this file
7    * to you under the Apache License, Version 2.0 (the
8    * "License"); you may not use this file except in compliance
9    * with the License.  You may obtain a copy of the License at
10   *
11   *     http://www.apache.org/licenses/LICENSE-2.0
12   *
13   * Unless required by applicable law or agreed to in writing, software
14   * distributed under the License is distributed on an "AS IS" BASIS,
15   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16   * See the License for the specific language governing permissions and
17   * limitations under the License.
18   */
19  package org.apache.hadoop.hbase.mapreduce;
20  
21  import java.util.Iterator;
22  import java.util.List;
23  import java.util.TreeSet;
24  
25  import org.apache.hadoop.classification.InterfaceAudience;
26  import org.apache.hadoop.classification.InterfaceStability;
27  import org.apache.hadoop.hbase.Cell;
28  import org.apache.hadoop.hbase.KeyValue;
29  import org.apache.hadoop.hbase.KeyValueUtil;
30  import org.apache.hadoop.hbase.client.Put;
31  import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
32  import org.apache.hadoop.mapreduce.Reducer;
33  import org.apache.hadoop.util.StringUtils;
34  
35  /**
36   * Emits sorted Puts.
37   * Reads in all Puts from passed Iterator, sorts them, then emits
38   * Puts in sorted order.  If lots of columns per row, it will use lots of
39   * memory sorting.
40   * @see HFileOutputFormat
41   * @see KeyValueSortReducer
42   */
43  @InterfaceAudience.Public
44  @InterfaceStability.Stable
45  public class PutSortReducer extends
46      Reducer<ImmutableBytesWritable, Put, ImmutableBytesWritable, KeyValue> {
47    
48    @Override
49    protected void reduce(
50        ImmutableBytesWritable row,
51        java.lang.Iterable<Put> puts,
52        Reducer<ImmutableBytesWritable, Put,
53                ImmutableBytesWritable, KeyValue>.Context context)
54        throws java.io.IOException, InterruptedException
55    {
56      // although reduce() is called per-row, handle pathological case
57      long threshold = context.getConfiguration().getLong(
58          "putsortreducer.row.threshold", 1L * (1<<30));
59      Iterator<Put> iter = puts.iterator();
60      while (iter.hasNext()) {
61        TreeSet<KeyValue> map = new TreeSet<KeyValue>(KeyValue.COMPARATOR);
62        long curSize = 0;
63        // stop at the end or the RAM threshold
64        while (iter.hasNext() && curSize < threshold) {
65          Put p = iter.next();
66          for (List<Cell> cells: p.getFamilyCellMap().values()) {
67            for (Cell cell: cells) {
68              KeyValue kv = KeyValueUtil.ensureKeyValue(cell);
69              map.add(kv);
70              curSize += kv.heapSize();
71            }
72          }
73        }
74        context.setStatus("Read " + map.size() + " entries of " + map.getClass()
75            + "(" + StringUtils.humanReadableInt(curSize) + ")");
76        int index = 0;
77        for (KeyValue kv : map) {
78          context.write(row, kv);
79          if (index > 0 && index % 100 == 0)
80            context.setStatus("Wrote " + index);
81        }
82  
83        // if we have more entries to process
84        if (iter.hasNext()) {
85          // force flush because we cannot guarantee intra-row sorted order
86          context.write(null, null);
87        }
88      }
89    }
90  }