Github user tgravescs commented on a diff in the pull request:
https://github.com/apache/spark/pull/12113#discussion_r62117794
--- Diff: core/src/main/scala/org/apache/spark/MapOutputTracker.scala ---
@@ -428,40 +503,89 @@ private[spark] class MapOutputTrackerMaster(conf:
SparkConf)
}
}
+ private def removeBroadcast(bcast: Broadcast[_]): Unit = {
+ if (null != bcast) {
+ broadcastManager.unbroadcast(bcast.id,
+ removeFromDriver = true, blocking = false)
+ }
+ }
+
+ private def clearCachedBroadcast(): Unit = {
+ for (cached <- cachedSerializedBroadcast) removeBroadcast(cached._2)
+ cachedSerializedBroadcast.clear()
+ }
+
def getSerializedMapOutputStatuses(shuffleId: Int): Array[Byte] = {
var statuses: Array[MapStatus] = null
+ var retBytes: Array[Byte] = null
var epochGotten: Long = -1
- epochLock.synchronized {
- if (epoch > cacheEpoch) {
- cachedSerializedStatuses.clear()
- cacheEpoch = epoch
- }
- cachedSerializedStatuses.get(shuffleId) match {
- case Some(bytes) =>
- return bytes
- case None =>
- statuses = mapStatuses.getOrElse(shuffleId, Array[MapStatus]())
- epochGotten = epoch
+
+ // Check to see if we have a cached version, returns true if it does
+ // and has side effect of setting retBytes. If not returns false
+ // with side effect of setting statuses
+ def checkCachedStatuses(): Boolean = {
+ epochLock.synchronized {
+ if (epoch > cacheEpoch) {
+ cachedSerializedStatuses.clear()
+ clearCachedBroadcast()
+ cacheEpoch = epoch
+ }
+ cachedSerializedStatuses.get(shuffleId) match {
+ case Some(bytes) =>
+ retBytes = bytes
+ true
+ case None =>
+ logDebug("cached status not found for : " + shuffleId)
+ statuses = mapStatuses.getOrElse(shuffleId, Array[MapStatus]())
+ epochGotten = epoch
+ false
+ }
}
}
- // If we got here, we failed to find the serialized locations in the
cache, so we pulled
- // out a snapshot of the locations as "statuses"; let's serialize and
return that
- val bytes = MapOutputTracker.serializeMapStatuses(statuses)
- logInfo("Size of output statuses for shuffle %d is %d
bytes".format(shuffleId, bytes.length))
- // Add them into the table only if the epoch hasn't changed while we
were working
- epochLock.synchronized {
- if (epoch == epochGotten) {
- cachedSerializedStatuses(shuffleId) = bytes
+
+ if (checkCachedStatuses()) return retBytes
+ var shuffleIdLock = shuffleIdLocks.get(shuffleId)
+ if (null == shuffleIdLock) {
+ val newLock = new Object()
+ // in general, this condition should be false - but good to be
paranoid
+ val prevLock = shuffleIdLocks.putIfAbsent(shuffleId, newLock)
--- End diff --
as comment says its just being paranoid just in case something
weird/unexpected happens, that shouldn't be the norm since the register should
happen before anyone tries to fetch. A couple of lines of code that hardly
ever/never get called seems much cheaper then adding synchronize all the time.
---
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]
