Github user pwendell commented on a diff in the pull request:
https://github.com/apache/spark/pull/126#discussion_r11374624
--- Diff:
core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala ---
@@ -54,7 +85,15 @@ private[spark] class HttpBroadcast[T](@transient var
value_ : T, isLocal: Boolea
logInfo("Started reading broadcast variable " + id)
val start = System.nanoTime
value_ = HttpBroadcast.read[T](id)
- SparkEnv.get.blockManager.putSingle(blockId, value_,
StorageLevel.MEMORY_AND_DISK, false)
+ /*
+ * Storing the broadcast data in BlockManager so that all
--- End diff --
/*
* We cache broadcast data in the BlockManager so that subsequent tasks
using it
* do not need to re-fetch. This data is only used locally, so we don't
notify the master.
*/
---
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.
---
