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.util.test;
019
020import java.io.IOException;
021import java.util.Random;
022import java.util.Set;
023import org.apache.hadoop.hbase.client.Get;
024import org.apache.hadoop.hbase.client.Mutation;
025import org.apache.hadoop.hbase.util.Bytes;
026import org.apache.hadoop.hbase.util.LoadTestKVGenerator;
027import org.apache.yetus.audience.InterfaceAudience;
028
029/**
030 * A generator of random data (keys/cfs/columns/values) for load testing. Contains
031 * LoadTestKVGenerator as a matter of convenience...
032 */
033@InterfaceAudience.Private
034public abstract class LoadTestDataGenerator {
035  protected LoadTestKVGenerator kvGenerator;
036
037  // The mutate info column stores information
038  // about update done to this column family this row.
039  public final static byte[] MUTATE_INFO = Bytes.toBytes("mutate_info");
040
041  // The increment column always has a long value,
042  // which can be incremented later on during updates.
043  public final static byte[] INCREMENT = Bytes.toBytes("increment");
044
045  protected String[] args;
046
047  public LoadTestDataGenerator() {
048
049  }
050
051  /**
052   * Initializes the object.
053   * @param minValueSize minimum size of the value generated by
054   *                     {@link #generateValue(byte[], byte[], byte[])}.
055   * @param maxValueSize maximum size of the value generated by
056   *                     {@link #generateValue(byte[], byte[], byte[])}.
057   */
058  public LoadTestDataGenerator(int minValueSize, int maxValueSize) {
059    this.kvGenerator = new LoadTestKVGenerator(minValueSize, maxValueSize);
060  }
061
062  public static byte[] generateData(final Random r, int length) {
063    byte[] b = new byte[length];
064    int i = 0;
065
066    for (i = 0; i < (length - 8); i += 8) {
067      b[i] = (byte) (65 + r.nextInt(26));
068      b[i + 1] = b[i];
069      b[i + 2] = b[i];
070      b[i + 3] = b[i];
071      b[i + 4] = b[i];
072      b[i + 5] = b[i];
073      b[i + 6] = b[i];
074      b[i + 7] = b[i];
075    }
076
077    byte a = (byte) (65 + r.nextInt(26));
078    for (; i < length; i++) {
079      b[i] = a;
080    }
081    return b;
082  }
083
084  /**
085   * initialize the LoadTestDataGenerator init args
086   */
087  public void initialize(String[] args) {
088    this.args = args;
089  }
090
091  /**
092   * Generates a deterministic, unique hashed row key from a number. That way, the user can keep
093   * track of numbers, without messing with byte array and ensuring key distribution.
094   * @param keyBase Base number for a key, such as a loop counter.
095   */
096  public abstract byte[] getDeterministicUniqueKey(long keyBase);
097
098  /**
099   * Gets column families for the load test table.
100   * @return The array of byte[]s representing column family names.
101   */
102  public abstract byte[][] getColumnFamilies();
103
104  /**
105   * Generates an applicable set of columns to be used for a particular key and family.
106   * @param rowKey The row key to generate for.
107   * @param cf     The column family name to generate for.
108   * @return The array of byte[]s representing column names.
109   */
110  public abstract byte[][] generateColumnsForCf(byte[] rowKey, byte[] cf);
111
112  /**
113   * Generates a value to be used for a particular row/cf/column.
114   * @param rowKey The row key to generate for.
115   * @param cf     The column family name to generate for.
116   * @param column The column name to generate for.
117   * @return The value to use.
118   */
119  public abstract byte[] generateValue(byte[] rowKey, byte[] cf, byte[] column);
120
121  /**
122   * Checks that columns for a rowKey and cf are valid if generated via
123   * {@link #generateColumnsForCf(byte[], byte[])}
124   * @param rowKey    The row key to verify for.
125   * @param cf        The column family name to verify for.
126   * @param columnSet The column set (for example, encountered by read).
127   * @return True iff valid.
128   */
129  public abstract boolean verify(byte[] rowKey, byte[] cf, Set<byte[]> columnSet);
130
131  /**
132   * Checks that value for a rowKey/cf/column is valid if generated via
133   * {@link #generateValue(byte[], byte[], byte[])}
134   * @param rowKey The row key to verify for.
135   * @param cf     The column family name to verify for.
136   * @param column The column name to verify for.
137   * @param value  The value (for example, encountered by read).
138   * @return True iff valid.
139   */
140  public abstract boolean verify(byte[] rowKey, byte[] cf, byte[] column, byte[] value);
141
142  /**
143   * Giving a chance for the LoadTestDataGenerator to change the Mutation load.
144   * @return updated Mutation
145   */
146  public Mutation beforeMutate(long rowkeyBase, Mutation m) throws IOException {
147    return m;
148  }
149
150  /**
151   * Giving a chance for the LoadTestDataGenerator to change the Get load.
152   * @return updated Get
153   */
154  public Get beforeGet(long rowkeyBase, Get get) throws IOException {
155    return get;
156  }
157
158  /** Returns the arguments passed to the generator as a list of objects. */
159  public String[] getArgs() {
160    return this.args;
161  }
162}