exmy commented on a change in pull request #32733:
URL: https://github.com/apache/spark/pull/32733#discussion_r643774365
##########
File path: core/src/main/scala/org/apache/spark/internal/config/package.scala
##########
@@ -1178,6 +1178,16 @@ package object config {
.bytesConf(ByteUnit.BYTE)
.createWithDefault(100 * 1024 * 1024)
+ private[spark] val SHUFFLE_ACCURATE_SKEWED_BLOCK_THRESHOLD =
+ ConfigBuilder("spark.shuffle.accurateSkewedBlockThreshold")
+ .doc("Threshold in bytes above which the size and five times non-empty
average size, " +
+ "the skewed shuffle blocks in HighlyCompressedMapStatus is accurately
recorded. " +
+ "This helps to prevent OOM by avoiding underestimating skewed shuffle
block size " +
+ "when fetch shuffle blocks.")
+ .version("3.2.0")
+ .bytesConf(ByteUnit.BYTE)
+ .createWithDefault(350 * 1024)
Review comment:
> Could you describe the background of this value?
Thanks for review. Described in the reply to @mridulm below, hopes to get
your opinion.
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
