spark PartitionedPairBuffer 源码

spark PartitionedPairBuffer 代码

文件路径：/core/src/main/scala/org/apache/spark/util/collection/PartitionedPairBuffer.scala

/*
 * 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.util.collection

import java.util.Comparator

import org.apache.spark.unsafe.array.ByteArrayMethods
import org.apache.spark.util.collection.WritablePartitionedPairCollection._

/**
 * Append-only buffer of key-value pairs, each with a corresponding partition ID, that keeps track
 * of its estimated size in bytes.
 *
 * The buffer can support up to 1073741819 elements.
 */
private[spark] class PartitionedPairBuffer[K, V](initialCapacity: Int = 64)
  extends WritablePartitionedPairCollection[K, V] with SizeTracker
{
  import PartitionedPairBuffer._

  require(initialCapacity <= MAXIMUM_CAPACITY,
    s"Can't make capacity bigger than ${MAXIMUM_CAPACITY} elements")
  require(initialCapacity >= 1, "Invalid initial capacity")

  // Basic growable array data structure. We use a single array of AnyRef to hold both the keys
  // and the values, so that we can sort them efficiently with KVArraySortDataFormat.
  private var capacity = initialCapacity
  private var curSize = 0
  private var data = new Array[AnyRef](2 * initialCapacity)

  /** Add an element into the buffer */
  def insert(partition: Int, key: K, value: V): Unit = {
    if (curSize == capacity) {
      growArray()
    }
    data(2 * curSize) = (partition, key.asInstanceOf[AnyRef])
    data(2 * curSize + 1) = value.asInstanceOf[AnyRef]
    curSize += 1
    afterUpdate()
  }

  /** Double the size of the array because we've reached capacity */
  private def growArray(): Unit = {
    if (capacity >= MAXIMUM_CAPACITY) {
      throw new IllegalStateException(s"Can't insert more than ${MAXIMUM_CAPACITY} elements")
    }
    val newCapacity =
      if (capacity * 2 > MAXIMUM_CAPACITY) { // Overflow
        MAXIMUM_CAPACITY
      } else {
        capacity * 2
      }
    val newArray = new Array[AnyRef](2 * newCapacity)
    System.arraycopy(data, 0, newArray, 0, 2 * capacity)
    data = newArray
    capacity = newCapacity
    resetSamples()
  }

  /** Iterate through the data in a given order. For this class this is not really destructive. */
  override def partitionedDestructiveSortedIterator(keyComparator: Option[Comparator[K]])
    : Iterator[((Int, K), V)] = {
    val comparator = keyComparator.map(partitionKeyComparator).getOrElse(partitionComparator)
    new Sorter(new KVArraySortDataFormat[(Int, K), AnyRef]).sort(data, 0, curSize, comparator)
    iterator
  }

  private def iterator(): Iterator[((Int, K), V)] = new Iterator[((Int, K), V)] {
    var pos = 0

    override def hasNext: Boolean = pos < curSize

    override def next(): ((Int, K), V) = {
      if (!hasNext) {
        throw new NoSuchElementException
      }
      val pair = (data(2 * pos).asInstanceOf[(Int, K)], data(2 * pos + 1).asInstanceOf[V])
      pos += 1
      pair
    }
  }
}

private object PartitionedPairBuffer {
  val MAXIMUM_CAPACITY: Int = ByteArrayMethods.MAX_ROUNDED_ARRAY_LENGTH / 2
}

相关信息

spark 源码目录

相关文章

spark AppendOnlyMap 源码

spark BitSet 源码

spark CompactBuffer 源码

spark ExternalAppendOnlyMap 源码

spark ExternalSorter 源码

spark ImmutableBitSet 源码

spark MedianHeap 源码

spark OpenHashMap 源码

spark OpenHashSet 源码

spark PairsWriter 源码