attilapiros commented on a change in pull request #33492:
URL: https://github.com/apache/spark/pull/33492#discussion_r679028868
##########
File path:
resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsAllocator.scala
##########
@@ -293,32 +302,49 @@ private[spark] class ExecutorPodsAllocator(
.withLabelIn(SPARK_EXECUTOR_ID_LABEL,
toDelete.sorted.map(_.toString): _*)
.delete()
newlyCreatedExecutors --= newlyCreatedToDelete
- knownPendingCount -= knownPendingToDelete.size
+ pendingCountForRpId -= pendingToDelete.size
+ notRunningPodCountForRpId -= toDelete.size
}
}
}
-
- if (newlyCreatedExecutorsForRpId.isEmpty
- && knownPodCount < targetNum) {
- requestNewExecutors(targetNum, knownPodCount, applicationId, rpId,
k8sKnownPVCNames)
- }
- totalPendingCount += knownPendingCount
+ totalPendingCount += pendingCountForRpId
+ totalNotRunningPodCount += notRunningPodCountForRpId
// The code below just prints debug messages, which are only useful when
there's a change
// in the snapshot state. Since the messages are a little spammy, avoid
them when we know
// there are no useful updates.
if (log.isDebugEnabled && snapshots.nonEmpty) {
- val outstanding = knownPendingCount + newlyCreatedExecutorsForRpId.size
+ val outstanding = pendingCountForRpId +
newlyCreatedExecutorsForRpId.size
if (currentRunningCount >= targetNum && !dynamicAllocationEnabled) {
logDebug(s"Current number of running executors for ResourceProfile
Id $rpId is " +
"equal to the number of requested executors. Not scaling up
further.")
} else {
- if (outstanding > 0) {
- logDebug(s"Still waiting for $outstanding executors for
ResourceProfile " +
- s"Id $rpId before requesting more.")
+ if (newlyCreatedExecutorsForRpId.nonEmpty) {
+ logDebug(s"Still waiting for ${newlyCreatedExecutorsForRpId.size}
executors for " +
+ s"ResourceProfile Id $rpId before requesting more.")
}
}
}
+ if (newlyCreatedExecutorsForRpId.isEmpty && podCountForRpId < targetNum)
{
+ Some(rpId, podCountForRpId, targetNum)
+ } else {
+ // for this resource profile we do not request more PODs
+ None
Review comment:
We could change this to logInfo:
https://github.com/apache/spark/blob/adc512d4e1837713713fefc6f64af3b0c6c8cdc8/resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsAllocator.scala#L323-L324
But for a higher batch allocation size this message could be annoying as
every POD status change will generate such a log line while it reaches 0.
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
