Skip to content

[SPARK-18294][CORE] Implement commit protocol to support mapred package's committer #15861

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
jiangxb1987 wants to merge 6 commits into from
Closed

[SPARK-18294][CORE] Implement commit protocol to support mapred package's committer #15861

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ac7ca2a
commit protocol support mapred API
jiangxb1987 Nov 10, 2016
3d64595
refactor.
jiangxb1987 Nov 12, 2016
4dffc34
clean code.
jiangxb1987 Nov 12, 2016
6d68b4f
bugfix - should update JobConf on JobContext/TaskContext creation.
jiangxb1987 Nov 12, 2016
7134e55
create SparkHadoopWriterConfig directly in PairRDDFunctions.
jiangxb1987 Nov 14, 2016
bedcd10
rename SparkHadoopWriterConfig to HadoopWriteConfigUtil
jiangxb1987 Nov 17, 2016
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
Prev Previous commit
Next Next commit
create SparkHadoopWriterConfig directly in PairRDDFunctions.
  • Loading branch information
@jiangxb1987
jiangxb1987 committed Nov 19, 2016
commit 7134e55c5802bbac9cf176833591491a3d4cac11
24 changes: 0 additions & 24 deletions core/src/main/scala/org/apache/spark/internal/io/SparkHadoopWriterConfig.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,27 +82,3 @@ abstract class SparkHadoopWriterConfig[K, V: ClassTag] extends Serializable {
def checkOutputSpecs(jobContext: JobContext): Unit

}

object SparkHadoopWriterConfig {

/**
* Instantiates a SparkHadoopWriterConfig using the given configuration.
*/
def instantiate[K, V](className: String, conf: Configuration)(
implicit ctorArgTag: ClassTag[(K, V)]): SparkHadoopWriterConfig[K, V] = {
val clazz = Utils.classForName(className).asInstanceOf[Class[SparkHadoopWriterConfig[K, V]]]

// First try the one with argument (conf: SerializableConfiguration).
// If that doesn't exist, try the one with (conf: SerializableJobConf).
try {
val ctor = clazz.getDeclaredConstructor(
classOf[SerializableConfiguration], classOf[ClassTag[(K, V)]])
ctor.newInstance(new SerializableConfiguration(conf), ctorArgTag)
} catch {
case _: NoSuchMethodException =>
val ctor = clazz.getDeclaredConstructor(
classOf[SerializableJobConf], classOf[ClassTag[(K, V)]])
ctor.newInstance(new SerializableJobConf(conf.asInstanceOf[JobConf]), ctorArgTag)
}
}
}
10 changes: 3 additions & 7 deletions core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ import org.apache.spark.internal.io._
import org.apache.spark.internal.Logging
import org.apache.spark.partial.{BoundedDouble, PartialResult}
import org.apache.spark.serializer.Serializer
import org.apache.spark.util.Utils
import org.apache.spark.util.{SerializableConfiguration, SerializableJobConf, Utils}
import org.apache.spark.util.collection.CompactBuffer
import org.apache.spark.util.random.StratifiedSamplingUtils

Expand Down Expand Up @@ -1051,9 +1051,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
* configured for a Hadoop MapReduce job.
*/
def saveAsNewAPIHadoopDataset(conf: Configuration): Unit = self.withScope {
val config = SparkHadoopWriterConfig.instantiate[K, V](
className = classOf[SparkHadoopMapReduceWriterConfig[K, V]].getName,
conf = conf)
val config = new SparkHadoopMapReduceWriterConfig[K, V](new SerializableConfiguration(conf))
SparkHadoopWriter.write(
rdd = self,
config = config)
Expand All @@ -1066,9 +1064,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
* MapReduce job.
*/
def saveAsHadoopDataset(conf: JobConf): Unit = self.withScope {
val config = SparkHadoopWriterConfig.instantiate[K, V](
className = classOf[SparkHadoopMapRedWriterConfig[K, V]].getName,
conf = conf)
val config = new SparkHadoopMapRedWriterConfig[K, V](new SerializableJobConf(conf))
SparkHadoopWriter.write(
rdd = self,
config = config)
Expand Down