Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/11505#discussion_r54973858
--- Diff: core/src/main/scala/org/apache/spark/MapOutputTracker.scala ---
@@ -386,28 +384,32 @@ private[spark] class MapOutputTrackerMaster(conf:
SparkConf)
fractionThreshold: Double)
: Option[Array[BlockManagerId]] = {
- if (mapStatuses.contains(shuffleId)) {
- val statuses = mapStatuses(shuffleId)
- if (statuses.nonEmpty) {
- // HashMap to add up sizes of all blocks at the same location
- val locs = new HashMap[BlockManagerId, Long]
- var totalOutputSize = 0L
- var mapIdx = 0
- while (mapIdx < statuses.length) {
- val status = statuses(mapIdx)
- val blockSize = status.getSizeForBlock(reducerId)
- if (blockSize > 0) {
- locs(status.location) = locs.getOrElse(status.location, 0L) +
blockSize
- totalOutputSize += blockSize
+ val statuses = mapStatuses.get(shuffleId).orNull
+ if (statuses != null) {
+ statuses.synchronized {
--- End diff --
nice catch
---
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]
