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.mapreduce;
019
020import static org.junit.jupiter.api.Assertions.assertEquals;
021import static org.junit.jupiter.api.Assertions.assertFalse;
022
023import java.util.ArrayList;
024import java.util.List;
025import org.apache.hadoop.conf.Configuration;
026import org.apache.hadoop.fs.FileStatus;
027import org.apache.hadoop.fs.LocatedFileStatus;
028import org.apache.hadoop.fs.Path;
029import org.apache.hadoop.hbase.HBaseTestingUtil;
030import org.apache.hadoop.hbase.HConstants;
031import org.apache.hadoop.hbase.regionserver.HRegionServer;
032import org.apache.hadoop.hbase.regionserver.wal.AbstractFSWAL;
033import org.apache.hadoop.hbase.testclassification.MapReduceTests;
034import org.apache.hadoop.hbase.testclassification.MediumTests;
035import org.apache.hadoop.hbase.util.CommonFSUtils;
036import org.apache.hadoop.hbase.util.EnvironmentEdgeManager;
037import org.apache.hadoop.mapreduce.InputSplit;
038import org.apache.hadoop.mapreduce.Job;
039import org.apache.hadoop.mapreduce.JobContext;
040import org.apache.hadoop.mapreduce.TaskAttemptContext;
041import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
042import org.junit.jupiter.api.BeforeAll;
043import org.junit.jupiter.api.Tag;
044import org.junit.jupiter.api.Test;
045import org.mockito.Mockito;
046
047@Tag(MapReduceTests.TAG)
048@Tag(MediumTests.TAG)
049public class TestWALInputFormat {
050  private static final HBaseTestingUtil TEST_UTIL = new HBaseTestingUtil();
051
052  @BeforeAll
053  public static void setupClass() throws Exception {
054    TEST_UTIL.startMiniCluster();
055    TEST_UTIL.createWALRootDir();
056  }
057
058  /**
059   * Test the primitive start/end time filtering.
060   */
061  @Test
062  public void testAddFile() {
063    List<FileStatus> lfss = new ArrayList<>();
064    LocatedFileStatus lfs = Mockito.mock(LocatedFileStatus.class);
065    long now = EnvironmentEdgeManager.currentTime();
066    Mockito.when(lfs.getPath()).thenReturn(new Path("/name." + now));
067    WALInputFormat.addFile(lfss, lfs, now, now);
068    assertEquals(1, lfss.size());
069    WALInputFormat.addFile(lfss, lfs, now - 1, now - 1);
070    assertEquals(1, lfss.size());
071    WALInputFormat.addFile(lfss, lfs, now - 2, now - 1);
072    assertEquals(1, lfss.size());
073    WALInputFormat.addFile(lfss, lfs, now - 2, now);
074    assertEquals(2, lfss.size());
075    WALInputFormat.addFile(lfss, lfs, Long.MIN_VALUE, now);
076    assertEquals(3, lfss.size());
077    WALInputFormat.addFile(lfss, lfs, Long.MIN_VALUE, Long.MAX_VALUE);
078    assertEquals(4, lfss.size());
079    WALInputFormat.addFile(lfss, lfs, now, now + 2);
080    assertEquals(5, lfss.size());
081    WALInputFormat.addFile(lfss, lfs, now + 1, now + 2);
082    assertEquals(5, lfss.size());
083    Mockito.when(lfs.getPath()).thenReturn(new Path("/name"));
084    WALInputFormat.addFile(lfss, lfs, Long.MIN_VALUE, Long.MAX_VALUE);
085    assertEquals(6, lfss.size());
086    Mockito.when(lfs.getPath()).thenReturn(new Path("/name.123"));
087    WALInputFormat.addFile(lfss, lfs, Long.MIN_VALUE, Long.MAX_VALUE);
088    assertEquals(7, lfss.size());
089    Mockito.when(lfs.getPath()).thenReturn(new Path("/name." + now + ".meta"));
090    WALInputFormat.addFile(lfss, lfs, now, now);
091    assertEquals(8, lfss.size());
092  }
093
094  @Test
095  public void testHandlesArchivedWALFiles() throws Exception {
096    Configuration conf = TEST_UTIL.getConfiguration();
097    JobContext ctx = Mockito.mock(JobContext.class);
098    Mockito.when(ctx.getConfiguration()).thenReturn(conf);
099    Job job = Job.getInstance(conf);
100    TableMapReduceUtil.initCredentialsForCluster(job, conf);
101    Mockito.when(ctx.getCredentials()).thenReturn(job.getCredentials());
102
103    // Setup WAL file, then archive it
104    HRegionServer rs = TEST_UTIL.getHBaseCluster().getRegionServer(0);
105    AbstractFSWAL wal = (AbstractFSWAL) rs.getWALs().get(0);
106    Path walPath = wal.getCurrentFileName();
107    TEST_UTIL.getConfiguration().set(FileInputFormat.INPUT_DIR, walPath.toString());
108    TEST_UTIL.getConfiguration().set(WALPlayer.INPUT_FILES_SEPARATOR_KEY, ";");
109
110    Path rootDir = CommonFSUtils.getWALRootDir(conf);
111    Path archiveWal = new Path(rootDir, HConstants.HREGION_OLDLOGDIR_NAME);
112    archiveWal = new Path(archiveWal, walPath.getName());
113    TEST_UTIL.getTestFileSystem().delete(walPath, true);
114    TEST_UTIL.getTestFileSystem().mkdirs(archiveWal.getParent());
115    TEST_UTIL.getTestFileSystem().create(archiveWal).close();
116
117    // Test for that we can read from the archived WAL file
118    WALInputFormat wif = new WALInputFormat();
119    List<InputSplit> splits = wif.getSplits(ctx);
120    assertEquals(1, splits.size());
121    WALInputFormat.WALSplit split = (WALInputFormat.WALSplit) splits.get(0);
122    assertEquals(archiveWal.toString(), split.getLogFileName());
123  }
124
125  /**
126   * Test that an empty WAL file (which causes WALHeaderEOFException) is gracefully handled and
127   * skipped rather than causing the job to fail.
128   */
129  @Test
130  public void testHandlesEmptyWALFile() throws Exception {
131    Configuration conf = TEST_UTIL.getConfiguration();
132
133    // Create an empty WAL file
134    Path walRootDir = CommonFSUtils.getWALRootDir(conf);
135    Path emptyWalFile =
136      new Path(walRootDir, "WALs/empty-wal-test/empty." + EnvironmentEdgeManager.currentTime());
137    TEST_UTIL.getTestFileSystem().mkdirs(emptyWalFile.getParent());
138    TEST_UTIL.getTestFileSystem().create(emptyWalFile).close();
139
140    try {
141      JobContext ctx = Mockito.mock(JobContext.class);
142      conf.set(FileInputFormat.INPUT_DIR, emptyWalFile.toString());
143      conf.set(WALPlayer.INPUT_FILES_SEPARATOR_KEY, ";");
144      Mockito.when(ctx.getConfiguration()).thenReturn(conf);
145      Job job = Job.getInstance(conf);
146      TableMapReduceUtil.initCredentialsForCluster(job, conf);
147      Mockito.when(ctx.getCredentials()).thenReturn(job.getCredentials());
148
149      // Create record reader and verify it handles the empty file gracefully
150      try (WALInputFormat.WALKeyRecordReader reader = new WALInputFormat.WALKeyRecordReader()) {
151        TaskAttemptContext taskCtx = Mockito.mock(TaskAttemptContext.class);
152        Mockito.when(taskCtx.getConfiguration()).thenReturn(conf);
153
154        WALInputFormat wif = new WALInputFormat();
155        List<InputSplit> splits = wif.getSplits(ctx);
156        assertEquals(1, splits.size());
157        WALInputFormat.WALSplit split = (WALInputFormat.WALSplit) splits.get(0);
158
159        // This should not throw WALHeaderEOFException - it should return false for nextKeyValue()
160        reader.initialize(split, taskCtx);
161        // nextKeyValue() should return false since the file is empty (reader is null)
162        assertFalse(reader.nextKeyValue());
163      }
164    } finally {
165      TEST_UTIL.getTestFileSystem().delete(emptyWalFile.getParent(), true);
166    }
167  }
168
169}