Revert "[SPARK-15392][SQL] fix default value of size estimation of lo…

…gical plan" This reverts commit fc29b89. (cherry picked from commit 84b2345) Signed-off-by: Reynold Xin <rxin@databricks.com>
apache · May 20, 2016 · f8d0177 · f8d0177
1 parent dd0c7fb
commit f8d0177
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 10 deletions.
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
@@ -595,7 +595,8 @@ 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, Long.MaxValue)
+  def defaultSizeInBytes: Long =
+    getConf(DEFAULT_SIZE_IN_BYTES, autoBroadcastJoinThreshold + 1L)
 
   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
@@ -1476,13 +1476,4 @@ 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)
-  }
 }