001/*
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018package org.apache.hadoop.hbase.regionserver;
019
020import java.io.IOException;
021import java.util.Arrays;
022import org.apache.hadoop.conf.Configuration;
023import org.apache.hadoop.hbase.client.TableDescriptor;
024import org.apache.hadoop.hbase.util.Bytes;
025import org.apache.yetus.audience.InterfaceAudience;
026import org.slf4j.Logger;
027import org.slf4j.LoggerFactory;
028
029/**
030 * A {@link RegionSplitRestriction} implementation that groups rows by a prefix of the row-key with
031 * a delimiter. Only the first delimiter for the row key will define the prefix of the row key that
032 * is used for grouping.
033 * <p>
034 * This ensures that a region is not split "inside" a prefix of a row key. I.e. rows can be
035 * co-located in a region by their prefix. As an example, if you have row keys delimited with
036 * <code>_</code>, like <code>userid_eventtype_eventid</code>, and use prefix delimiter _, this
037 * split policy ensures that all rows starting with the same userid, belongs to the same region.
038 */
039@InterfaceAudience.Private
040public class DelimitedKeyPrefixRegionSplitRestriction extends RegionSplitRestriction {
041  private static final Logger LOG =
042    LoggerFactory.getLogger(DelimitedKeyPrefixRegionSplitRestriction.class);
043
044  public static final String DELIMITER_KEY =
045    "hbase.regionserver.region.split_restriction.delimiter";
046
047  private byte[] delimiter = null;
048
049  @Override
050  public void initialize(TableDescriptor tableDescriptor, Configuration conf) throws IOException {
051    String delimiterString = tableDescriptor.getValue(DELIMITER_KEY);
052    if (delimiterString == null || delimiterString.length() == 0) {
053      delimiterString = conf.get(DELIMITER_KEY);
054      if (delimiterString == null || delimiterString.length() == 0) {
055        LOG.error("{} not specified for table {}. " + "Using the default RegionSplitRestriction",
056          DELIMITER_KEY, tableDescriptor.getTableName());
057        return;
058      }
059    }
060    delimiter = Bytes.toBytes(delimiterString);
061  }
062
063  @Override
064  public byte[] getRestrictedSplitPoint(byte[] splitPoint) {
065    if (delimiter != null) {
066      // find the first occurrence of delimiter in split point
067      int index = org.apache.hbase.thirdparty.com.google.common.primitives.Bytes.indexOf(splitPoint,
068        delimiter);
069      if (index < 0) {
070        LOG.warn("Delimiter {} not found for split key {}", Bytes.toString(delimiter),
071          Bytes.toStringBinary(splitPoint));
072        return splitPoint;
073      }
074
075      // group split keys by a prefix
076      return Arrays.copyOf(splitPoint, Math.min(index, splitPoint.length));
077    } else {
078      return splitPoint;
079    }
080  }
081}