Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/20384#discussion_r163755332
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/joins/BroadcastJoinSuite.scala
---
@@ -110,15 +110,39 @@ class BroadcastJoinSuite extends QueryTest with
SQLTestUtils {
}
test("broadcast hint is retained after using the cached data") {
- withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1") {
- val df1 = spark.createDataFrame(Seq((1, "4"), (2, "2"))).toDF("key",
"value")
- val df2 = spark.createDataFrame(Seq((1, "1"), (2, "2"))).toDF("key",
"value")
- df2.cache()
- val df3 = df1.join(broadcast(df2), Seq("key"), "inner")
- val numBroadCastHashJoin = df3.queryExecution.executedPlan.collect {
- case b: BroadcastHashJoinExec => b
- }.size
- assert(numBroadCastHashJoin === 1)
+ try {
+ withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1") {
+ val df1 = spark.createDataFrame(Seq((1, "4"), (2,
"2"))).toDF("key", "value")
+ val df2 = spark.createDataFrame(Seq((1, "1"), (2,
"2"))).toDF("key", "value")
+ df2.cache()
+ val df3 = df1.join(broadcast(df2), Seq("key"), "inner")
+ val numBroadCastHashJoin = df3.queryExecution.executedPlan.collect
{
+ case b: BroadcastHashJoinExec => b
+ }.size
+ assert(numBroadCastHashJoin === 1)
+ }
+ } finally {
+ spark.catalog.clearCache()
--- End diff --
Yeah. That should be a separate bug.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
