gengliangwang commented on a change in pull request #27129: [SPARK-30427][SQL]
Add config item for limiting partition number when calculating statistics
through File System
URL: https://github.com/apache/spark/pull/27129#discussion_r373314179
##########
File path:
sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/PruneHiveTablePartitions.scala
##########
@@ -73,19 +74,30 @@ private[sql] class PruneHiveTablePartitions(session:
SparkSession)
private def updateTableMeta(
tableMeta: CatalogTable,
prunedPartitions: Seq[CatalogTablePartition]): CatalogTable = {
- val sizeOfPartitions = prunedPartitions.map { partition =>
+ val partitionsWithSize = prunedPartitions.map { partition =>
val rawDataSize =
partition.parameters.get(StatsSetupConst.RAW_DATA_SIZE).map(_.toLong)
val totalSize =
partition.parameters.get(StatsSetupConst.TOTAL_SIZE).map(_.toLong)
if (rawDataSize.isDefined && rawDataSize.get > 0) {
- rawDataSize.get
+ (partition, rawDataSize.get)
} else if (totalSize.isDefined && totalSize.get > 0L) {
- totalSize.get
+ (partition, totalSize.get)
} else {
- 0L
+ (partition, 0L)
}
}
- if (sizeOfPartitions.forall(_ > 0)) {
- val sizeInBytes = sizeOfPartitions.sum
+ if (partitionsWithSize.forall(_._2 > 0)) {
+ val sizeInBytes = partitionsWithSize.map(_._2).sum
+ tableMeta.copy(stats = Some(CatalogStatistics(sizeInBytes =
BigInt(sizeInBytes))))
+ } else if (partitionsWithSize.count(_._2 == 0) <=
conf.maxPartNumForStatsCalculateViaFS) {
Review comment:
why do we need to do calculation here? I think it introduces extra cost.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
