Skip to content
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.

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

[SPARK-32381][CORE][FOLLOWUP][test-hadoop2.7] Don't remove SerializableFileStatus and SerializableBlockLocation for Hadoop 2.7 #30447

Closed
wants to merge 3 commits into from
Closed
Changes from all commits
Commits
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
61 changes: 60 additions & 1 deletion core/src/main/scala/org/apache/spark/util/HadoopFSUtils.scala
Original file line number Diff line number Diff line change
Expand Up @@ -136,12 +136,53 @@ private[spark] object HadoopFSUtils extends Logging {
parallelismMax = 0)
(path, leafFiles)
}.iterator
}.map { case (path, statuses) =>
val serializableStatuses = statuses.map { status =>
// Turn FileStatus into SerializableFileStatus so we can send it back to the driver
val blockLocations = status match {
case f: LocatedFileStatus =>
f.getBlockLocations.map { loc =>
SerializableBlockLocation(
loc.getNames,
loc.getHosts,
loc.getOffset,
loc.getLength)
}

case _ =>
Array.empty[SerializableBlockLocation]
}

SerializableFileStatus(
status.getPath.toString,
status.getLen,
status.isDirectory,
status.getReplication,
status.getBlockSize,
status.getModificationTime,
status.getAccessTime,
blockLocations)
}
(path.toString, serializableStatuses)
}.collect()
} finally {
sc.setJobDescription(previousJobDescription)
}

statusMap.toSeq
// turn SerializableFileStatus back to Status
statusMap.map { case (path, serializableStatuses) =>
val statuses = serializableStatuses.map { f =>
val blockLocations = f.blockLocations.map { loc =>
new BlockLocation(loc.names, loc.hosts, loc.offset, loc.length)
}
new LocatedFileStatus(
new FileStatus(
f.length, f.isDir, f.blockReplication, f.blockSize, f.modificationTime,
new Path(f.path)),
blockLocations)
}
(new Path(path), statuses)
}
}

// scalastyle:off argcount
Expand Down Expand Up @@ -291,4 +332,22 @@ private[spark] object HadoopFSUtils extends Logging {
resolvedLeafStatuses
}
// scalastyle:on argcount

/** A serializable variant of HDFS's BlockLocation. This is required by Hadoop 2.7. */
private case class SerializableBlockLocation(
names: Array[String],
hosts: Array[String],
offset: Long,
length: Long)

/** A serializable variant of HDFS's FileStatus. This is required by Hadoop 2.7. */
private case class SerializableFileStatus(
path: String,
length: Long,
isDir: Boolean,
blockReplication: Short,
blockSize: Long,
modificationTime: Long,
accessTime: Long,
blockLocations: Array[SerializableBlockLocation])
}