Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/1241#discussion_r16759577
--- Diff: core/src/main/scala/org/apache/spark/storage/DiskStore.scala ---
@@ -89,25 +89,33 @@ private[spark] class DiskStore(blockManager:
BlockManager, diskManager: DiskBloc
}
}
- override def getBytes(blockId: BlockId): Option[ByteBuffer] = {
- val segment = diskManager.getBlockLocation(blockId)
- val channel = new RandomAccessFile(segment.file, "r").getChannel
+ private def getBytes(file: File, offset: Long, length: Long):
Option[ByteBuffer] = {
+ val channel = new RandomAccessFile(file, "r").getChannel
try {
// For small files, directly read rather than memory map
- if (segment.length < minMemoryMapBytes) {
- val buf = ByteBuffer.allocate(segment.length.toInt)
- channel.read(buf, segment.offset)
+ if (file.length < minMemoryMapBytes) {
+ val buf = ByteBuffer.allocate(length.toInt)
+ channel.read(buf, offset)
buf.flip()
Some(buf)
} else {
- Some(channel.map(MapMode.READ_ONLY, segment.offset,
segment.length))
+ Some(channel.map(MapMode.READ_ONLY, offset, length))
}
} finally {
channel.close()
}
}
+ override def getBytes(blockId: BlockId): Option[ByteBuffer] = {
+ val file = diskManager.getFile(blockId.name)
+ getBytes(file, 0, file.length)
+ }
+
+ def getBytes(segment: FileSegment): Option[ByteBuffer] = {
+ getBytes(segment.file, segment.offset, segment.length)
+ }
+
override def getValues(blockId: BlockId): Option[Iterator[Any]] = {
--- End diff --
can u add a todo here that getValues should bypass getBytes to use stream
based APIs? Otherwise this uses a lot of memory during external sort merge.
---
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.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
