Github user Dooyoung-Hwang commented on a diff in the pull request:
https://github.com/apache/spark/pull/22219#discussion_r213682460
--- Diff:
sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkExecuteStatementOperation.scala
---
@@ -289,6 +289,14 @@ private[hive] class SparkExecuteStatementOperation(
sqlContext.sparkContext.cancelJobGroup(statementId)
}
}
+
+ private def getResultIterator(): Iterator[SparkRow] = {
+ val (totalRowCount, iterResult) = result.collectCountAndIterator()
+ val batchCollectLimit =
+
sqlContext.getConf(SQLConf.THRIFTSERVER_BATCH_COLLECTION_LIMIT.key).toLong
+ resultList = if (totalRowCount < batchCollectLimit)
Some(iterResult.toArray) else None
+ if (resultList.isDefined) resultList.get.iterator else iterResult
--- End diff --
I will try to cache it. Thank you for reply.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
