From ab4a6bfd11b870428eb2a96aa213f7d34c0aa622 Mon Sep 17 00:00:00 2001
From: Rajesh Balamohan <rbalamohan@apache.org>
Date: Wed, 20 Jan 2016 11:30:03 -0800
Subject: [PATCH] [SPARK-12898] Consider having dummyCallSite for HiveTableScan
Currently, HiveTableScan runs with getCallSite which is really expensive and shows up when scanning through large table with partitions (e.g TPC-DS) which slows down the overall runtime of the job. It would be good to consider having dummyCallSite in HiveTableScan.
Author: Rajesh Balamohan <rbalamohan@apache.org>
Closes #10825 from rajeshbalamohan/SPARK-12898.
---
.../spark/sql/hive/execution/HiveTableScan.scala | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala
index 1588728bdb..eff8833e92 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala
@@ -32,6 +32,7 @@ import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.execution._
import org.apache.spark.sql.hive._
import org.apache.spark.sql.types.{BooleanType, DataType}
+import org.apache.spark.util.Utils
/**
* The Hive table scan operator. Column and partition pruning are both handled.
@@ -133,11 +134,17 @@ case class HiveTableScan(
}
protected override def doExecute(): RDD[InternalRow] = {
+ // Using dummyCallSite, as getCallSite can turn out to be expensive with
+ // with multiple partitions.
val rdd = if (!relation.hiveQlTable.isPartitioned) {
- hadoopReader.makeRDDForTable(relation.hiveQlTable)
+ Utils.withDummyCallSite(sqlContext.sparkContext) {
+ hadoopReader.makeRDDForTable(relation.hiveQlTable)
+ }
} else {
- hadoopReader.makeRDDForPartitionedTable(
- prunePartitions(relation.getHiveQlPartitions(partitionPruningPred)))
+ Utils.withDummyCallSite(sqlContext.sparkContext) {
+ hadoopReader.makeRDDForPartitionedTable(
+ prunePartitions(relation.getHiveQlPartitions(partitionPruningPred)))
+ }
}
rdd.mapPartitionsInternal { iter =>
val proj = UnsafeProjection.create(schema)
--
GitLab