maropu commented on a change in pull request #24715: [SPARK-25474][SQL] Data source tables support fallback to HDFS for size estimation URL: https://github.com/apache/spark/pull/24715#discussion_r314964437
########## File path: sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala ########## @@ -650,4 +650,46 @@ class StatisticsCollectionSuite extends StatisticsCollectionTestBase with Shared } } } + + test("Non-partitioned data source table support fallback to HDFS for size estimation") { + withTempDir { dir => + Seq(false, true).foreach { fallBackToHDFS => + withSQLConf(SQLConf.ENABLE_FALL_BACK_TO_HDFS_FOR_STATS.key -> s"$fallBackToHDFS") { + withTable("spark_25474") { + sql(s"CREATE TABLE spark_25474 (c1 BIGINT) USING PARQUET LOCATION '${dir.toURI}'") + spark.range(5).write.mode(SaveMode.Overwrite).parquet(dir.getCanonicalPath) + + assert(getCatalogTable("spark_25474").stats.isEmpty) + val relation = spark.table("spark_25474").queryExecution.analyzed.children.head + // fallBackToHDFS = true: The table stats will be recalculated by DetermineTableStats + // fallBackToHDFS = false: The table stats will be recalculated by FileIndex + assert(relation.stats.sizeInBytes === getDataSize(dir)) + } + } + } + } + } + + test("Partitioned data source table support fallback to HDFS for size estimation") { + Seq(false, true).foreach { fallBackToHDFS => + withSQLConf(SQLConf.ENABLE_FALL_BACK_TO_HDFS_FOR_STATS.key -> s"$fallBackToHDFS") { + withTempDir { dir => + withTable("spark_25474") { + sql("CREATE TABLE spark_25474(a int, b int) USING parquet " + + s"PARTITIONED BY(a) LOCATION '${dir.toURI}'") + sql("INSERT INTO TABLE spark_25474 PARTITION(a=1) SELECT 2") + + assert(getCatalogTable("spark_25474").stats.isEmpty) + val relation = spark.table("spark_25474").queryExecution.analyzed.children.head + if (fallBackToHDFS) { + assert(relation.stats.sizeInBytes > 0) + assert(relation.stats.sizeInBytes < conf.defaultSizeInBytes) Review comment: We cannot use `getDataSize` here? ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org