Skip to content

[SPARK-3559][SQL] Remove unnecessary columns from List of needed Column Ids in Hive Conf #2713

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
gvramana wants to merge 2 commits into from
Closed

[SPARK-3559][SQL] Remove unnecessary columns from List of needed Column Ids in Hive Conf #2713

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6a93459
cloned hiveconf for each TableScanOperators so that only required col…
gvramana Oct 8, 2014
b7ba768
Added comment and checkstyle fix
gvramana Oct 8, 2014
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ package org.apache.spark.sql.hive

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{Path, PathFilter}
import org.apache.hadoop.hive.conf.HiveConf
import org.apache.hadoop.hive.metastore.api.hive_metastoreConstants._
import org.apache.hadoop.hive.ql.exec.Utilities
import org.apache.hadoop.hive.ql.metadata.{Partition => HivePartition, Table => HiveTable}
Expand Down Expand Up @@ -52,7 +53,8 @@ private[hive]
class HadoopTableReader(
@transient attributes: Seq[Attribute],
@transient relation: MetastoreRelation,
@transient sc: HiveContext)
@transient sc: HiveContext,
@transient hiveExtraConf: HiveConf)
extends TableReader {

// Choose the minimum number of splits. If mapred.map.tasks is set, then use that unless
Expand All @@ -63,7 +65,7 @@ class HadoopTableReader(
// TODO: set aws s3 credentials.

private val _broadcastedHiveConf =
sc.sparkContext.broadcast(new SerializableWritable(sc.hiveconf))
sc.sparkContext.broadcast(new SerializableWritable(hiveExtraConf))

def broadcastedHiveConf = _broadcastedHiveConf

Expand Down
10 changes: 8 additions & 2 deletions sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,8 +64,14 @@ case class HiveTableScan(
BindReferences.bindReference(pred, relation.partitionKeys)
}

// Create a local copy of hiveconf,so that scan specific modifications should not impact
// other queries
@transient
private[this] val hadoopReader = new HadoopTableReader(attributes, relation, context)
private[this] val hiveExtraConf = new HiveConf(context.hiveconf)

@transient
private[this] val hadoopReader =
new HadoopTableReader(attributes, relation, context, hiveExtraConf)

private[this] def castFromString(value: String, dataType: DataType) = {
Cast(Literal(value), dataType).eval(null)
Expand Down Expand Up @@ -97,7 +103,7 @@ case class HiveTableScan(
hiveConf.set(serdeConstants.LIST_COLUMNS, relation.attributes.map(_.name).mkString(","))
}

addColumnMetadataToConf(context.hiveconf)
addColumnMetadataToConf(hiveExtraConf)

/**
* Prunes partitions not involve the query plan.
Expand Down