fix

Author: gatorsmile

sql/core/src/main/scala/org/apache/spark/sql/execution/CacheManager.scala

@@ -26,7 +26,7 @@ import org.apache.hadoop.fs.{FileSystem, Path}
 import org.apache.spark.internal.Logging
 import org.apache.spark.sql.{Dataset, SparkSession}
 import org.apache.spark.sql.catalyst.expressions.SubqueryExpression
-import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, Statistics}
+import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, ResolvedHint}
 import org.apache.spark.sql.execution.columnar.InMemoryRelation
 import org.apache.spark.sql.execution.datasources.{HadoopFsRelation, LogicalRelation}
 import org.apache.spark.storage.StorageLevel
@@ -170,9 +170,13 @@ class CacheManager extends Logging {
   def useCachedData(plan: LogicalPlan): LogicalPlan = {
     val newPlan = plan transformDown {
       case currentFragment =>
-        lookupCachedData(currentFragment)
-          .map(_.cachedRepresentation.withOutput(currentFragment.output))
-          .getOrElse(currentFragment)
+        lookupCachedData(currentFragment).map { cached =>
+          val cachedPlan = cached.cachedRepresentation.withOutput(currentFragment.output)
+          currentFragment match {
+            case hint: ResolvedHint => ResolvedHint(cachedPlan, hint.hints)
+            case _ => cachedPlan
+          }
+        }.getOrElse(currentFragment)
     }
 
     newPlan transformAllExpressions {

sql/core/src/test/scala/org/apache/spark/sql/execution/joins/BroadcastJoinSuite.scala

@@ -109,6 +109,19 @@ class BroadcastJoinSuite extends QueryTest with SQLTestUtils {
     }
   }
 
+  test("broadcast hint is lost") {
+    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)
+    }
+  }
+
   test("broadcast hint isn't propagated after a join") {
     withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1") {
       val df1 = spark.createDataFrame(Seq((1, "4"), (2, "2"))).toDF("key", "value")