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.io.hfile;
019
020import java.util.ArrayList;
021import java.util.List;
022import org.apache.hadoop.conf.Configuration;
023import org.apache.hadoop.fs.FileSystem;
024import org.apache.hadoop.fs.Path;
025import org.apache.hadoop.hbase.Cell;
026import org.apache.hadoop.hbase.CellBuilderType;
027import org.apache.hadoop.hbase.ExtendedCellBuilderFactory;
028import org.apache.hadoop.hbase.HBaseTestingUtil;
029import org.apache.hadoop.hbase.HConstants;
030import org.apache.hadoop.hbase.KeyValue;
031import org.apache.hadoop.hbase.testclassification.IOTests;
032import org.apache.hadoop.hbase.testclassification.SmallTests;
033import org.apache.hadoop.hbase.util.Bytes;
034import org.junit.jupiter.api.Tag;
035import org.junit.jupiter.api.Test;
036
037/**
038 * Test a case when an inline index chunk is converted to a root one. This reproduces the bug in
039 * HBASE-6871. We write a carefully selected number of relatively large keys so that we accumulate a
040 * leaf index chunk that only goes over the configured index chunk size after adding the last
041 * key/value. The bug is in that when we close the file, we convert that inline (leaf-level) chunk
042 * into a root chunk, but then look at the size of that root chunk, find that it is greater than the
043 * configured chunk size, and split it into a number of intermediate index blocks that should really
044 * be leaf-level blocks. If more keys were added, we would flush the leaf-level block, add another
045 * entry to the root-level block, and that would prevent us from upgrading the leaf-level chunk to
046 * the root chunk, thus not triggering the bug.
047 */
048@Tag(IOTests.TAG)
049@Tag(SmallTests.TAG)
050public class TestHFileInlineToRootChunkConversion {
051
052  private final HBaseTestingUtil testUtil = new HBaseTestingUtil();
053  private final Configuration conf = testUtil.getConfiguration();
054
055  @Test
056  public void testWriteHFile() throws Exception {
057    Path hfPath = new Path(testUtil.getDataTestDir(),
058      TestHFileInlineToRootChunkConversion.class.getSimpleName() + ".hfile");
059    int maxChunkSize = 1024;
060    FileSystem fs = FileSystem.get(conf);
061    CacheConfig cacheConf = new CacheConfig(conf);
062    conf.setInt(HFileBlockIndex.MAX_CHUNK_SIZE_KEY, maxChunkSize);
063    HFileContext context = new HFileContextBuilder().withBlockSize(16).build();
064    HFile.Writer hfw = new HFile.WriterFactory(conf, cacheConf).withFileContext(context)
065      .withPath(fs, hfPath).create();
066    List<byte[]> keys = new ArrayList<>();
067    StringBuilder sb = new StringBuilder();
068
069    for (int i = 0; i < 4; ++i) {
070      sb.append("key" + String.format("%05d", i));
071      sb.append("_");
072      for (int j = 0; j < 100; ++j) {
073        sb.append('0' + j);
074      }
075      String keyStr = sb.toString();
076      sb.setLength(0);
077
078      byte[] k = Bytes.toBytes(keyStr);
079      keys.add(k);
080      byte[] v = Bytes.toBytes("value" + i);
081      hfw.append(ExtendedCellBuilderFactory.create(CellBuilderType.DEEP_COPY).setRow(k)
082        .setFamily(HConstants.EMPTY_BYTE_ARRAY).setQualifier(HConstants.EMPTY_BYTE_ARRAY)
083        .setTimestamp(HConstants.LATEST_TIMESTAMP).setType(KeyValue.Type.Maximum.getCode())
084        .setValue(v).setType(Cell.Type.Put).build());
085    }
086    hfw.close();
087
088    HFile.Reader reader = HFile.createReader(fs, hfPath, cacheConf, true, conf);
089    // Scanner doesn't do Cells yet. Fix.
090    HFileScanner scanner = reader.getScanner(conf, true, true);
091    for (int i = 0; i < keys.size(); ++i) {
092      scanner.seekTo(ExtendedCellBuilderFactory.create(CellBuilderType.DEEP_COPY)
093        .setRow(keys.get(i)).setFamily(HConstants.EMPTY_BYTE_ARRAY)
094        .setQualifier(HConstants.EMPTY_BYTE_ARRAY).setTimestamp(HConstants.LATEST_TIMESTAMP)
095        .setType(KeyValue.Type.Maximum.getCode()).setValue(HConstants.EMPTY_BYTE_ARRAY).build());
096    }
097    reader.close();
098  }
099}