Github user squito commented on a diff in the pull request:
https://github.com/apache/spark/pull/11105#discussion_r55434879
--- Diff: core/src/main/scala/org/apache/spark/Accumulable.scala ---
@@ -146,6 +198,32 @@ class Accumulable[R, T] private (
def merge(term: R) { value_ = param.addInPlace(value_, term)}
/**
+ * Merge in pending updates for ac consistent accumulators or merge
accumulated values for
+ * regular accumulators.
+ */
+ private[spark] def internalMerge(term: Any) {
+ if (!consistent) {
+ merge(term.asInstanceOf[R])
+ } else {
+ mergePending(term.asInstanceOf[mutable.HashMap[(Int, Int), R]])
+ }
+ }
+
+ /**
+ * Merge another pending updates, checks to make sure that each pending
update has not
+ * already been processed before updating.
+ */
+ private[spark] def mergePending(term: mutable.HashMap[(Int, Int), R]) = {
+ term.foreach{case ((rddId, splitId), v) =>
+ val splits = processed.getOrElseUpdate(rddId, new mutable.BitSet())
+ if (!splits.contains(splitId)) {
--- End diff --
add a doc saying that this isn't thread safe, but its ok b/c its only
called w/in the dag scheduler event loop
---
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]
