wangyum commented on a change in pull request #24523: [SPARK-27631][SQL] Avoid
repeating calculate table statistics
URL: https://github.com/apache/spark/pull/24523#discussion_r284729116
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandUtils.scala
##########
@@ -43,13 +43,17 @@ object CommandUtils extends Logging {
/** Change statistics after changing data by commands. */
def updateTableStats(sparkSession: SparkSession, table: CatalogTable): Unit
= {
val catalog = sparkSession.sessionState.catalog
- if (sparkSession.sessionState.conf.autoSizeUpdateEnabled) {
- val newTable = catalog.getTableMetadata(table.identifier)
- val newSize = CommandUtils.calculateTotalSize(sparkSession, newTable)
- val newStats = CatalogStatistics(sizeInBytes = newSize)
- catalog.alterTableStats(table.identifier, Some(newStats))
- } else if (table.stats.nonEmpty) {
- catalog.alterTableStats(table.identifier, None)
+ val statsMaybeUpdatedByHive = catalog.getTableMetadata(table.identifier)
Review comment:
How about:
```scala
def updateTableStats(sparkSession: SparkSession, table: CatalogTable):
Unit = {
val catalog = sparkSession.sessionState.catalog
val statsMaybeUpdatedByExternalCatalog =
catalog.getTableMetadata(table.identifier)
if (statsMaybeUpdatedByExternalCatalog.stats == table.stats) {
if (sparkSession.sessionState.conf.autoSizeUpdateEnabled) {
val newSize =
CommandUtils.calculateTotalSize(sparkSession,
statsMaybeUpdatedByExternalCatalog)
val newStats = CatalogStatistics(sizeInBytes = newSize)
catalog.alterTableStats(table.identifier, Some(newStats))
} else if (table.stats.nonEmpty) {
catalog.alterTableStats(table.identifier, None)
}
} else {
logInfo(
s"Skip to update statistics for ${table.qualifiedName} as it updated
by external catalog.")
}
}
```
----------------------------------------------------------------
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]
