Xiao Li created SPARK-23195:
-------------------------------
Summary: Hint of cached data is lost
Key: SPARK-23195
URL: https://issues.apache.org/jira/browse/SPARK-23195
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 2.2.1, 2.3.0
Reporter: Xiao Li
Assignee: Xiao Li
{noformat}
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")
broadcast(df2).cache()
df2.collect()
val df3 = df1.join(df2, Seq("key"), "inner")
val numBroadCastHashJoin = df3.queryExecution.executedPlan.collect {
case b: BroadcastHashJoinExec => b
}.size
assert(numBroadCastHashJoin === 1)
}
{noformat}
The broadcast hint is not respected.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
