Github user aarondav commented on a diff in the pull request: https://github.com/apache/spark/pull/1678#discussion_r15682590 --- 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 -- Closed streams should not inherently throw (since we check `initialized` before flushing and closing). However, we may be left with leftover data, as you said. I don't see a way to prevent the possibility of that occurring, but it should be possible to recover if users only rely on the returned fileSegment().
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---