1 /**
2  * Licensed to the Apache Software Foundation (ASF) under one
3  * or more contributor license agreements.  See the NOTICE file
4  * distributed with this work for additional information
5  * regarding copyright ownership.  The ASF licenses this file
6  * to you under the Apache License, Version 2.0 (the
7  * "License"); you may not use this file except in compliance
8  * with the License.  You may obtain a copy of the License at
9  *
10  *     http://www.apache.org/licenses/LICENSE-2.0
11  *
12  * Unless required by applicable law or agreed to in writing, software
13  * distributed under the License is distributed on an "AS IS" BASIS,
14  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15  * See the License for the specific language governing permissions and
16  * limitations under the License.
17  */
18 
19 package org.apache.hadoop.hbase.regionserver;
20 
21 import java.util.Arrays;
22 
23 import org.apache.commons.logging.Log;
24 import org.apache.commons.logging.LogFactory;
25 import org.apache.hadoop.hbase.classification.InterfaceAudience;
26 import org.apache.hadoop.hbase.util.Bytes;
27 
28 /**
29  * A custom RegionSplitPolicy implementing a SplitPolicy that groups
30  * rows by a prefix of the row-key with a delimiter. Only the first delimiter
31  * for the row key will define the prefix of the row key that is used for grouping.
32  *
33  * This ensures that a region is not split "inside" a prefix of a row key.
34  * I.e. rows can be co-located in a region by their prefix.
35  *
36  * As an example, if you have row keys delimited with <code>_</code>, like
37  * <code>userid_eventtype_eventid</code>, and use prefix delimiter _, this split policy
38  * ensures that all rows starting with the same userid, belongs to the same region.
39  * @see KeyPrefixRegionSplitPolicy
40  */
41 @InterfaceAudience.Private
42 public class DelimitedKeyPrefixRegionSplitPolicy extends IncreasingToUpperBoundRegionSplitPolicy {
43 
44   private static final Log LOG = LogFactory
45       .getLog(DelimitedKeyPrefixRegionSplitPolicy.class);
46   public static final String DELIMITER_KEY = "DelimitedKeyPrefixRegionSplitPolicy.delimiter";
47 
48   private byte[] delimiter = null;
49 
50   @Override
configureForRegion(HRegion region)51   protected void configureForRegion(HRegion region) {
52     super.configureForRegion(region);
53     // read the prefix length from the table descriptor
54     String delimiterString = region.getTableDesc().getValue(DELIMITER_KEY);
55     if (delimiterString == null || delimiterString.length() == 0) {
56       LOG.error(DELIMITER_KEY + " not specified for table " + region.getTableDesc().getTableName() +
57         ". Using default RegionSplitPolicy");
58       return;
59     }
60     delimiter = Bytes.toBytes(delimiterString);
61   }
62 
63   @Override
getSplitPoint()64   protected byte[] getSplitPoint() {
65     byte[] splitPoint = super.getSplitPoint();
66     if (splitPoint != null && delimiter != null) {
67 
68       //find the first occurrence of delimiter in split point
69       int index = com.google.common.primitives.Bytes.indexOf(splitPoint, delimiter);
70       if (index < 0) {
71         LOG.warn("Delimiter " + Bytes.toString(delimiter) + "  not found for split key "
72             + Bytes.toString(splitPoint));
73         return splitPoint;
74       }
75 
76       // group split keys by a prefix
77       return Arrays.copyOf(splitPoint, Math.min(index, splitPoint.length));
78     } else {
79       return splitPoint;
80     }
81   }
82 }