advancedxy commented on a change in pull request #26085: [SPARK-29434][Core]
Improve the MapStatuses Serialization Performance
URL: https://github.com/apache/spark/pull/26085#discussion_r365056779
##########
File path: core/src/main/scala/org/apache/spark/MapOutputTracker.scala
##########
@@ -900,18 +908,42 @@ private[spark] object MapOutputTracker extends Logging {
} {
objOut.close()
}
- val arr = out.toByteArray
+
+ val arr: Array[Byte] = {
+ val zos = new ZstdOutputStream(compressedOut)
+ Utils.tryWithSafeFinally {
+ compressedOut.write(DIRECT)
+ // `out.writeTo(zos)` will write the uncompressed data from `out` to
`zos`
+ // without copying to avoid unnecessary allocation and copy of byte[].
+ out.writeTo(zos)
+ } {
+ zos.close()
+ }
+ compressedOut.toByteArray
+ }
if (arr.length >= minBroadcastSize) {
// Use broadcast instead.
// Important arr(0) is the tag == DIRECT, ignore that while
deserializing !
val bcast = broadcastManager.newBroadcast(arr, isLocal)
// toByteArray creates copy, so we can reuse out
out.reset()
- out.write(BROADCAST)
- val oos = new ObjectOutputStream(new GZIPOutputStream(out))
- oos.writeObject(bcast)
- oos.close()
- val outArr = out.toByteArray
+ val oos = new ObjectOutputStream(out)
+ Utils.tryWithSafeFinally {
+ oos.writeObject(bcast)
+ } {
+ oos.close()
+ }
+ val outArr = {
+ compressedOut.reset()
+ val zos = new ZstdOutputStream(compressedOut)
Review comment:
Thanks for your clarification. It's indeed not including the compressed data.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
