cloud-fan commented on code in PR #52190:
URL: https://github.com/apache/spark/pull/52190#discussion_r2317713815
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/ExternalAppendOnlyUnsafeRowArray.scala:
##########
@@ -116,19 +121,24 @@ private[sql] class ExternalAppendOnlyUnsafeRowArray(
spillableArray = null
} else if (inMemoryBuffer != null) {
inMemoryBuffer.clear()
+ inMemoryBufferSizeInBytes = 0;
}
numFieldsPerRow = 0
numRows = 0
modificationsCount += 1
}
def add(unsafeRow: UnsafeRow): Unit = {
- if (numRows < numRowsInMemoryBufferThreshold) {
+ // Once spills, we will switch to UnsafeExternalSorter permanently.
+ if (spillableArray == null && numRows < numRowsInMemoryBufferThreshold &&
+ inMemoryBufferSizeInBytes < sizeInBytesSpillThreshold) {
Review Comment:
```suggestion
inMemoryBufferSizeInBytes < sizeInBytesInMemoryBufferThreshold) {
```
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
