sunchao commented on code in PR #36067:
URL: https://github.com/apache/spark/pull/36067#discussion_r850832716
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandUtils.scala:
##########
@@ -71,22 +74,29 @@ object CommandUtils extends Logging {
}
}
- def calculateTotalSize(spark: SparkSession, catalogTable: CatalogTable):
BigInt = {
+ def calculateTotalSize(
+ spark: SparkSession,
+ catalogTable: CatalogTable): (BigInt, Seq[CatalogTablePartition]) = {
val sessionState = spark.sessionState
val startTime = System.nanoTime()
- val totalSize = if (catalogTable.partitionColumnNames.isEmpty) {
- calculateSingleLocationSize(sessionState, catalogTable.identifier,
- catalogTable.storage.locationUri)
+ val (totalSize, newPartitions) = if
(catalogTable.partitionColumnNames.isEmpty) {
+ (calculateSingleLocationSize(sessionState, catalogTable.identifier,
+ catalogTable.storage.locationUri), Seq())
} else {
// Calculate table size as a sum of the visible partitions. See
SPARK-21079
val partitions =
sessionState.catalog.listPartitions(catalogTable.identifier)
logInfo(s"Starting to calculate sizes for ${partitions.length}
partitions.")
val paths = partitions.map(_.storage.locationUri)
- calculateMultipleLocationSizes(spark, catalogTable.identifier, paths).sum
+ val sizes = calculateMultipleLocationSizes(spark,
catalogTable.identifier, paths)
+ val newPartitions = partitions.zipWithIndex.flatMap { case (p, idx) =>
Review Comment:
👍
--
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]
