Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/14712#discussion_r77301097 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/command/AnalyzeTableCommand.scala --- @@ -88,24 +85,54 @@ case class AnalyzeTableCommand(tableName: String) extends RunnableCommand { } }.getOrElse(0L) - // Update the Hive metastore if the total size of the table is different than the size - // recorded in the Hive metastore. - // This logic is based on org.apache.hadoop.hive.ql.exec.StatsTask.aggregateStats(). - if (newTotalSize > 0 && newTotalSize != oldTotalSize) { - sessionState.catalog.alterTable( - catalogTable.copy( - properties = relation.catalogTable.properties + - (AnalyzeTableCommand.TOTAL_SIZE_FIELD -> newTotalSize.toString))) - } + updateTableStats( + catalogTable, + oldTotalSize = catalogTable.stats.map(_.sizeInBytes.toLong).getOrElse(0L), + oldRowCount = catalogTable.stats.flatMap(_.rowCount.map(_.toLong)).getOrElse(-1L), + newTotalSize = newTotalSize) + + // data source tables have been converted into LogicalRelations + case logicalRel: LogicalRelation if logicalRel.catalogTable.isDefined => + val table = logicalRel.catalogTable.get + updateTableStats( + table, + oldTotalSize = table.stats.map(_.sizeInBytes.toLong).getOrElse(0L), + oldRowCount = table.stats.flatMap(_.rowCount.map(_.toLong)).getOrElse(-1L), --- End diff -- so we always calculate `oldTotalSize` and `oldRowCount` by reading the `stats` field in `CatalogTable`, I think `updateTableStats` only need to take one parameter, the `CatalogTable`, and we can calculate `oldTotalSize` and `oldRowCount` in the method.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org