diff --git a/sql/core/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala b/sql/core/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala index 7933d12e284f17716806b4cf1ee043d33e513690..a7f461381b5059e6bbbae31e86140e9f246a4a20 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala @@ -605,8 +605,7 @@ private[sql] class SQLConf extends Serializable with CatalystConf with Logging { def enableRadixSort: Boolean = getConf(RADIX_SORT_ENABLED) - def defaultSizeInBytes: Long = - getConf(DEFAULT_SIZE_IN_BYTES, autoBroadcastJoinThreshold + 1L) + def defaultSizeInBytes: Long = getConf(DEFAULT_SIZE_IN_BYTES, Long.MaxValue) def isParquetBinaryAsString: Boolean = getConf(PARQUET_BINARY_AS_STRING) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala index f573abf859610c2b125a149e05a911ecc174880a..df029e44c54e5c937e89222726d0c89e0c420991 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala @@ -1476,4 +1476,13 @@ class DataFrameSuite extends QueryTest with SharedSQLContext { getMessage() assert(e1.startsWith("Path does not exist")) } + + test("SPARK-15392: DataFrame created from RDD should not be broadcasted") { + val rdd = sparkContext.range(1, 100).map(i => Row(i, i)) + val df = spark.createDataFrame(rdd, new StructType().add("a", LongType).add("b", LongType)) + assert(df.queryExecution.analyzed.statistics.sizeInBytes > + spark.wrapped.conf.autoBroadcastJoinThreshold) + assert(df.selectExpr("a").queryExecution.analyzed.statistics.sizeInBytes > + spark.wrapped.conf.autoBroadcastJoinThreshold) + } }