Github user mridulm commented on a diff in the pull request:
https://github.com/apache/spark/pull/43#discussion_r10192379
--- Diff: core/src/main/scala/org/apache/spark/storage/DiskStore.scala ---
@@ -84,12 +84,27 @@ private class DiskStore(blockManager: BlockManager,
diskManager: DiskBlockManage
override def getBytes(blockId: BlockId): Option[ByteBuffer] = {
val segment = diskManager.getBlockLocation(blockId)
val channel = new RandomAccessFile(segment.file, "r").getChannel()
- val buffer = try {
- channel.map(MapMode.READ_ONLY, segment.offset, segment.length)
- } finally {
- channel.close()
+
+ val buffer =
+ // For small files, directly read rather than memory map
+ if (segment.length < 2 * 4096) {
--- End diff --
There are performance implication between reading to vanilla buffer (note,
this is not a direct buffer) and using memory mapped buffers - with added cost
of some wastage for the 'last page'.
In addition, you always leave the option open for zero copy enhancement in
spark.
---
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.
---
