Github user hvanhovell commented on a diff in the pull request: https://github.com/apache/spark/pull/14712#discussion_r76248746 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/command/AnalyzeTableCommand.scala --- @@ -88,14 +89,70 @@ 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) { + var needUpdate = false + val totalSize = if (newTotalSize > 0 && newTotalSize != oldTotalSize) { + needUpdate = true + newTotalSize + } else { + oldTotalSize + } + var numRows: Option[BigInt] = None + if (!noscan) { + val oldRowCount: Long = if (catalogTable.catalogStats.isDefined) { + catalogTable.catalogStats.get.rowCount.map(_.toLong).getOrElse(-1L) + } else { + -1L + } + val newRowCount = sparkSession.table(tableName).count() + if (newRowCount >= 0 && newRowCount != oldRowCount) { --- End diff -- `newRowCount` can be 0 right? What is the reason to keep the old statistic if the table is empty?
--- 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