Github user mridulm commented on a diff in the pull request:
https://github.com/apache/spark/pull/1678#discussion_r15701250
--- Diff:
core/src/main/scala/org/apache/spark/storage/BlockObjectWriter.scala ---
@@ -147,28 +147,36 @@ private[spark] class DiskBlockObjectWriter(
override def isOpen: Boolean = objOut != null
- override def commit(): Long = {
+ override def commitAndClose(): Unit = {
if (initialized) {
// NOTE: Because Kryo doesn't flush the underlying stream we
explicitly flush both the
// serializer stream and the lower level stream.
objOut.flush()
bs.flush()
- val prevPos = lastValidPosition
- lastValidPosition = channel.position()
- lastValidPosition - prevPos
- } else {
- // lastValidPosition is zero if stream is uninitialized
- lastValidPosition
+ close()
}
+ finalPosition = file.length()
}
- override def revertPartialWrites() {
- if (initialized) {
- // Discard current writes. We do this by flushing the outstanding
writes and
- // truncate the file to the last valid position.
- objOut.flush()
- bs.flush()
- channel.truncate(lastValidPosition)
+ // Discard current writes. We do this by flushing the outstanding writes
and then
+ // truncating the file to its initial position.
+ override def revertPartialWritesAndClose() {
+ try {
+ if (initialized) {
+ objOut.flush()
+ bs.flush()
+ close()
+ }
+
+ val truncateStream = new FileOutputStream(file, true)
+ try {
+ truncateStream.getChannel.truncate(initialPosition)
+ } finally {
+ truncateStream.close()
+ }
+ } catch {
+ case e: Exception =>
+ logError("Uncaught exception while reverting partial writes to
file " + file, e)
--- End diff --
Ah, did not notice that the "if (initialized)" did not include the truncate
call !
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
