Github user jinxing64 commented on a diff in the pull request:
https://github.com/apache/spark/pull/16989#discussion_r114960041
--- Diff: core/src/main/scala/org/apache/spark/scheduler/MapStatus.scala ---
@@ -128,41 +130,52 @@ private[spark] class CompressedMapStatus(
* @param numNonEmptyBlocks the number of non-empty blocks
* @param emptyBlocks a bitmap tracking which blocks are empty
* @param avgSize average size of the non-empty blocks
+ * @param hugeBlockSizesArray sizes of huge blocks by their reduceId.
*/
private[spark] class HighlyCompressedMapStatus private (
private[this] var loc: BlockManagerId,
private[this] var numNonEmptyBlocks: Int,
private[this] var emptyBlocks: RoaringBitmap,
- private[this] var avgSize: Long)
+ private[this] var avgSize: Long,
+ private[this] var hugeBlockSizesArray: Array[Tuple2[Int, Byte]])
extends MapStatus with Externalizable {
+ @transient var hugeBlockSizes: Map[Int, Byte] =
+ if (hugeBlockSizesArray == null) null else hugeBlockSizesArray.toMap
+
// loc could be null when the default constructor is called during
deserialization
require(loc == null || avgSize > 0 || numNonEmptyBlocks == 0,
"Average size can only be zero for map stages that produced no output")
- protected def this() = this(null, -1, null, -1) // For deserialization
only
+ def this() = this(null, -1, null, -1, null) // For deserialization only
override def location: BlockManagerId = loc
override def getSizeForBlock(reduceId: Int): Long = {
if (emptyBlocks.contains(reduceId)) {
0
} else {
- avgSize
+ hugeBlockSizes.get(reduceId) match {
+ case Some(size) => MapStatus.decompressSize(size)
+ case None => avgSize
+ }
}
}
override def writeExternal(out: ObjectOutput): Unit =
Utils.tryOrIOException {
loc.writeExternal(out)
emptyBlocks.writeExternal(out)
out.writeLong(avgSize)
+ out.writeObject(hugeBlockSizesArray)
}
override def readExternal(in: ObjectInput): Unit =
Utils.tryOrIOException {
loc = BlockManagerId(in)
emptyBlocks = new RoaringBitmap()
emptyBlocks.readExternal(in)
avgSize = in.readLong()
+ hugeBlockSizesArray = in.readObject().asInstanceOf[Array[Tuple2[Int,
Byte]]]
+ hugeBlockSizes = hugeBlockSizesArray.toMap
--- End diff --
After the constructor is called, both `hugeBlockSizes` and
`hugeBlockSizesArray` are initialized to be null, I think we need to initialize
both in `readExternal` when deserialize.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
