zaynt4606 commented on code in PR #3059:
URL: https://github.com/apache/celeborn/pull/3059#discussion_r1914449317
##########
worker/src/main/scala/org/apache/celeborn/service/deploy/worker/Controller.scala:
##########
@@ -730,6 +738,41 @@ private[deploy] class Controller(
}
}
+ def checkCommitTimeout(shuffleCommitTime: ConcurrentHashMap[
+ String,
+ ConcurrentHashMap[Long, (Int, RpcCallContext)]]): Unit = {
+ val delta = 100
+
+ shuffleCommitTime.asScala.foreach {
+ case (shuffleKey, epochWaitTimeMap) =>
+ epochWaitTimeMap.asScala.foreach { case (epoch, (waitTime, context)) =>
+ val commitInfo = shuffleCommitInfos.get(shuffleKey).get(epoch)
+ commitInfo.synchronized {
+ if (commitInfo.status == CommitInfo.COMMIT_FINISHED) {
+ context.reply(commitInfo.response)
+ epochWaitTimeMap.remove(epoch)
+ } else {
+ if (waitTime * delta < shuffleCommitTimeout) {
+ shuffleCommitTime.get(shuffleKey).put(epoch, (waitTime + 1,
context))
Review Comment:
has been updated~
##########
worker/src/main/scala/org/apache/celeborn/service/deploy/worker/Controller.scala:
##########
@@ -730,6 +738,41 @@ private[deploy] class Controller(
}
}
+ def checkCommitTimeout(shuffleCommitTime: ConcurrentHashMap[
+ String,
+ ConcurrentHashMap[Long, (Int, RpcCallContext)]]): Unit = {
+ val delta = 100
+
+ shuffleCommitTime.asScala.foreach {
+ case (shuffleKey, epochWaitTimeMap) =>
+ epochWaitTimeMap.asScala.foreach { case (epoch, (waitTime, context)) =>
+ val commitInfo = shuffleCommitInfos.get(shuffleKey).get(epoch)
Review Comment:
Done
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
