Github user mallman commented on a diff in the pull request: https://github.com/apache/spark/pull/16514#discussion_r95489960 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala --- @@ -119,7 +119,30 @@ private[hive] class HiveMetastoreCatalog(sparkSession: SparkSession) extends Log qualifiedTableName.database, qualifiedTableName.name) if (DDLUtils.isDatasourceTable(table)) { - val dataSourceTable = cachedDataSourceTables(qualifiedTableName) + val dataSourceTable = + cachedDataSourceTables(qualifiedTableName) match { + case l @ LogicalRelation(relation: HadoopFsRelation, _, _) => + // Ignore the scheme difference when comparing the paths + val isSamePath = + table.storage.locationUri.isDefined && relation.location.rootPaths.size == 1 && + table.storage.locationUri.get == relation.location.rootPaths.head.toUri.getPath + // If we have the same paths, same schema, and same partition spec, + // we will use the cached relation. + val useCached = + isSamePath && + l.schema == table.schema && + relation.bucketSpec == table.bucketSpec && + relation.partitionSchema == table.partitionSchema + if (useCached) { + l + } else { + // If the cached relation is not updated, we invalidate it right away. + cachedDataSourceTables.invalidate(qualifiedTableName) + // Reload it from the external catalog + cachedDataSourceTables(qualifiedTableName) + } + case o => o + } --- End diff -- Understood.
--- 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