org.apache.spark.streaming.util.FileBasedWriteAheadLogWriter.scala Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of spark-streaming_2.12 Show documentation
The newest version!
/*
 * 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.spark.streaming.util

import java.io._
import java.nio.ByteBuffer

import org.apache.hadoop.conf.Configuration

import org.apache.spark.util.Utils

/**
 * A writer for writing byte-buffers to a write ahead log file.
 */
private[streaming] class FileBasedWriteAheadLogWriter(path: String, hadoopConf: Configuration)
  extends Closeable {

  private lazy val stream = HdfsUtils.getOutputStream(path, hadoopConf)


  private var nextOffset = stream.getPos()
  private var closed = false

  /** Write the bytebuffer to the log file */
  def write(data: ByteBuffer): FileBasedWriteAheadLogSegment = synchronized {
    assertOpen()
    data.rewind() // Rewind to ensure all data in the buffer is retrieved
    val lengthToWrite = data.remaining()
    val segment = new FileBasedWriteAheadLogSegment(path, nextOffset, lengthToWrite)
    stream.writeInt(lengthToWrite)
    Utils.writeByteBuffer(data, stream: OutputStream)
    flush()
    nextOffset = stream.getPos()
    segment
  }

  override def close(): Unit = synchronized {
    closed = true
    stream.close()
  }

  private def flush(): Unit = {
    stream.hflush()
    // Useful for local file system where hflush/sync does not work (HADOOP-7844)
    stream.getWrappedStream.flush()
  }

  private def assertOpen(): Unit = {
    HdfsUtils.checkState(!closed, "Stream is closed. Create a new Writer to write to file.")
  }
}