andygrove commented on code in PR #1021:
URL: https://github.com/apache/datafusion-comet/pull/1021#discussion_r1901409389
##########
spark/src/main/scala/org/apache/comet/CometExecIterator.scala:
##########
@@ -84,6 +87,30 @@ class CometExecIterator(
private var currentBatch: ColumnarBatch = null
private var closed: Boolean = false
+ private def getMemoryLimitPerTask(conf: SparkConf): Long = {
+ val numCores = numDriverOrExecutorCores(conf).toFloat
+ val maxMemory = CometSparkSessionExtensions.getCometMemoryOverhead(conf)
Review Comment:
That's a good point. The default overhead amount was way too low for the
benchmarks to run. Using the executor amount is probably overkill. I'll give
this some more thought.
--
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]
