hadoop SpillRecord 源码

haddop SpillRecord 代码

文件路径：/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/SpillRecord.java

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.hadoop.mapred;

import static org.apache.hadoop.mapred.MapTask.MAP_OUTPUT_INDEX_RECORD_LENGTH;

import java.io.File;
import java.io.IOException;
import java.nio.ByteBuffer;
import java.nio.LongBuffer;
import java.util.zip.CheckedInputStream;
import java.util.zip.CheckedOutputStream;
import java.util.zip.Checksum;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.fs.ChecksumException;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.SecureIOUtils;
import org.apache.hadoop.util.PureJavaCrc32;

@InterfaceAudience.LimitedPrivate({"MapReduce"})
@InterfaceStability.Unstable
public class SpillRecord {

  /** Backing store */
  private final ByteBuffer buf;
  /** View of backing storage as longs */
  private final LongBuffer entries;

  public SpillRecord(int numPartitions) {
    buf = ByteBuffer.allocate(
        numPartitions * MapTask.MAP_OUTPUT_INDEX_RECORD_LENGTH);
    entries = buf.asLongBuffer();
  }

  public SpillRecord(Path indexFileName, JobConf job) throws IOException {
    this(indexFileName, job, null);
  }

  public SpillRecord(Path indexFileName, JobConf job, String expectedIndexOwner)
    throws IOException {
    this(indexFileName, job, new PureJavaCrc32(), expectedIndexOwner);
  }

  public SpillRecord(Path indexFileName, JobConf job, Checksum crc,
                     String expectedIndexOwner)
      throws IOException {

    final FileSystem rfs = FileSystem.getLocal(job).getRaw();
    final FSDataInputStream in =
        SecureIOUtils.openFSDataInputStream(new File(indexFileName.toUri()
            .getRawPath()), expectedIndexOwner, null);
    try {
      final long length = rfs.getFileStatus(indexFileName).getLen();
      final int partitions = (int) length / MAP_OUTPUT_INDEX_RECORD_LENGTH;
      final int size = partitions * MAP_OUTPUT_INDEX_RECORD_LENGTH;
      buf = ByteBuffer.allocate(size);
      if (crc != null) {
        crc.reset();
        CheckedInputStream chk = new CheckedInputStream(in, crc);
        IOUtils.readFully(chk, buf.array(), 0, size);
        
        if (chk.getChecksum().getValue() != in.readLong()) {
          throw new ChecksumException("Checksum error reading spill index: " +
                                indexFileName, -1);
        }
      } else {
        IOUtils.readFully(in, buf.array(), 0, size);
      }
      entries = buf.asLongBuffer();
    } finally {
      in.close();
    }
  }

  /**
   * Return number of IndexRecord entries in this spill.
   */
  public int size() {
    return entries.capacity() / (MapTask.MAP_OUTPUT_INDEX_RECORD_LENGTH / 8);
  }

  /**
   * Get spill offsets for given partition.
   */
  public IndexRecord getIndex(int partition) {
    final int pos = partition * MapTask.MAP_OUTPUT_INDEX_RECORD_LENGTH / 8;
    return new IndexRecord(entries.get(pos), entries.get(pos + 1),
                           entries.get(pos + 2));
  }

  /**
   * Set spill offsets for given partition.
   */
  public void putIndex(IndexRecord rec, int partition) {
    final int pos = partition * MapTask.MAP_OUTPUT_INDEX_RECORD_LENGTH / 8;
    entries.put(pos, rec.startOffset);
    entries.put(pos + 1, rec.rawLength);
    entries.put(pos + 2, rec.partLength);
  }

  /**
   * Write this spill record to the location provided.
   */
  public void writeToFile(Path loc, JobConf job)
      throws IOException {
    writeToFile(loc, job, new PureJavaCrc32());
  }

  public void writeToFile(Path loc, JobConf job, Checksum crc)
      throws IOException {
    final FileSystem rfs = FileSystem.getLocal(job).getRaw();
    CheckedOutputStream chk = null;
    final FSDataOutputStream out = rfs.create(loc);
    try {
      if (crc != null) {
        crc.reset();
        chk = new CheckedOutputStream(out, crc);
        chk.write(buf.array());
        out.writeLong(chk.getChecksum().getValue());
      } else {
        out.write(buf.array());
      }
    } finally {
      if (chk != null) {
        chk.close();
      } else {
        out.close();
      }
    }
  }

}

相关信息

hadoop 源码目录

相关文章

hadoop AMFeedback 源码

hadoop BackupStore 源码

hadoop BasicTypeSorterBase 源码

hadoop BufferSorter 源码

hadoop CleanupQueue 源码

hadoop Clock 源码

hadoop ClusterStatus 源码

hadoop Counters 源码

hadoop CumulativePeriodicStats 源码

hadoop DeprecatedQueueConfigurationParser 源码