wForget commented on code in PR #1379:
URL: https://github.com/apache/datafusion-comet/pull/1379#discussion_r1951890219
##########
spark/src/main/scala/org/apache/comet/CometSparkSessionExtensions.scala:
##########
@@ -1354,9 +1354,14 @@ object CometSparkSessionExtensions extends Logging {
/** Calculates required memory overhead in MB per executor process for
Comet. */
def getCometMemoryOverheadInMiB(sparkConf: SparkConf): Long = {
- // `spark.executor.memory` default value is 1g
- val executorMemoryMiB = ConfigHelpers
- .byteFromString(sparkConf.get("spark.executor.memory", "1024MB"),
ByteUnit.MiB)
+ val executorMemoryMiB = if (cometUnifiedMemoryManagerEnabled(sparkConf)) {
Review Comment:
I noticed this behavior from your previous PR, after this PR we don't need
to configure manual `COMET_MEMORY_OVERHEAD` when using unified memory manager.
https://github.com/apache/datafusion-comet/pull/1369/files#diff-c104036e91cd748933259320a8d86535e5f6fccae24875daf0f18e6c5ca0ab64L96-L97
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
