Skip to content

[SPARK-26673][FollowUp][SQL] File source V2: remove duplicated broadcast object in FileWriterFactory #23800

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
gengliangwang wants to merge 1 commit into from
Closed

[SPARK-26673][FollowUp][SQL] File source V2: remove duplicated broadcast object in FileWriterFactory #23800

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 1 addition & 2 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileBatchWrite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,8 +46,7 @@ class FileBatchWrite(
}

override def createBatchWriterFactory(): DataWriterFactory = {
val conf = new SerializableConfiguration(job.getConfiguration)
FileWriterFactory(description, committer, conf)
FileWriterFactory(description, committer)
}
}

5 changes: 2 additions & 3 deletions ...core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileWriterFactory.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,7 @@ import org.apache.spark.util.SerializableConfiguration

case class FileWriterFactory (
description: WriteJobDescription,
committer: FileCommitProtocol,
conf: SerializableConfiguration) extends DataWriterFactory {
committer: FileCommitProtocol) extends DataWriterFactory {
override def createWriter(partitionId: Int, realTaskId: Long): DataWriter[InternalRow] = {
val taskAttemptContext = createTaskAttemptContext(partitionId)
committer.setupTask(taskAttemptContext)
Expand All @@ -46,7 +45,7 @@ case class FileWriterFactory (
val taskId = new TaskID(jobId, TaskType.MAP, partitionId)
val taskAttemptId = new TaskAttemptID(taskId, 0)
// Set up the configuration object
val hadoopConf = conf.value
val hadoopConf = description.serializableHadoopConf.value
hadoopConf.set("mapreduce.job.id", jobId.toString)
hadoopConf.set("mapreduce.task.id", taskId.toString)
hadoopConf.set("mapreduce.task.attempt.id", taskAttemptId.toString)
Expand Down
5 changes: 4 additions & 1 deletion ...est/scala/org/apache/spark/sql/execution/datasources/orc/OrcPartitionDiscoverySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -232,5 +232,8 @@ class OrcPartitionDiscoverySuite extends OrcPartitionDiscoveryTest with SharedSQ

class OrcV1PartitionDiscoverySuite extends OrcPartitionDiscoveryTest with SharedSQLContext {
override protected def sparkConf: SparkConf =
super.sparkConf.set(SQLConf.USE_V1_SOURCE_READER_LIST, "orc")
super
.sparkConf
.set(SQLConf.USE_V1_SOURCE_READER_LIST, "orc")
.set(SQLConf.USE_V1_SOURCE_WRITER_LIST, "orc")
}
5 changes: 4 additions & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/orc/OrcQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -690,5 +690,8 @@ class OrcQuerySuite extends OrcQueryTest with SharedSQLContext {

class OrcV1QuerySuite extends OrcQuerySuite {
override protected def sparkConf: SparkConf =
super.sparkConf.set(SQLConf.USE_V1_SOURCE_READER_LIST, "orc")
super
.sparkConf
.set(SQLConf.USE_V1_SOURCE_READER_LIST, "orc")
.set(SQLConf.USE_V1_SOURCE_WRITER_LIST, "orc")
}
5 changes: 4 additions & 1 deletion ...core/src/test/scala/org/apache/spark/sql/execution/datasources/orc/OrcV1FilterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,10 @@ import org.apache.spark.sql.internal.SQLConf
class OrcV1FilterSuite extends OrcFilterSuite {

override protected def sparkConf: SparkConf =
super.sparkConf.set(SQLConf.USE_V1_SOURCE_READER_LIST, "orc")
super
.sparkConf
.set(SQLConf.USE_V1_SOURCE_READER_LIST, "orc")
.set(SQLConf.USE_V1_SOURCE_WRITER_LIST, "orc")

override def checkFilterPredicate(
df: DataFrame,
Expand Down