[GitHub] spark pull request #20430: [SPARK-23263][SQL] Create table stored as parquet...

[wzhfy <gi...@git.apache.org>]

Github user wzhfy commented on a diff in the pull request:

    https://github.com/apache/spark/pull/20430#discussion_r165349231
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandUtils.scala ---
    @@ -34,16 +34,12 @@ object CommandUtils extends Logging {
     
       /** Change statistics after changing data by commands. */
       def updateTableStats(sparkSession: SparkSession, table: CatalogTable): Unit = {
    -    if (table.stats.nonEmpty) {
    +    if (sparkSession.sessionState.conf.autoSizeUpdateEnabled) {
           val catalog = sparkSession.sessionState.catalog
    -      if (sparkSession.sessionState.conf.autoSizeUpdateEnabled) {
    -        val newTable = catalog.getTableMetadata(table.identifier)
    -        val newSize = CommandUtils.calculateTotalSize(sparkSession.sessionState, newTable)
    -        val newStats = CatalogStatistics(sizeInBytes = newSize)
    -        catalog.alterTableStats(table.identifier, Some(newStats))
    -      } else {
    -        catalog.alterTableStats(table.identifier, None)
    --- End diff --
    
    @felixcheung if the data of a table has been changed and auto size update is disabled, the stats become inaccurate, so we should remove them.


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org