wangyum commented on code in PR #41545:
URL: https://github.com/apache/spark/pull/41545#discussion_r1227758305
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FilePartition.scala:
##########
@@ -83,6 +83,24 @@ object FilePartition extends Logging {
partitions.toSeq
}
+ def getFilePartitions(
+ sparkSession: SparkSession,
+ partitionedFiles: Seq[PartitionedFile],
+ maxSplitBytes: Long): Seq[FilePartition] = {
+ val openCostBytes = sparkSession.sessionState.conf.filesOpenCostInBytes
+ val maxPartitionNum = sparkSession.sessionState.conf.filesMaxPartitionNum
+ val partitions = getFilePartitions(partitionedFiles, maxSplitBytes,
openCostBytes)
Review Comment:
fixed.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala:
##########
@@ -1749,6 +1749,16 @@ object SQLConf {
.checkValue(v => v > 0, "The min partition number must be a positive
integer.")
.createOptional
+ val FILES_MAX_PARTITION_NUM = buildConf("spark.sql.files.maxPartitionNum")
Review Comment:
+1
--
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]
