Github user lianhuiwang commented on a diff in the pull request:
https://github.com/apache/spark/pull/6508#discussion_r31493564
--- Diff:
core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala ---
@@ -443,9 +466,27 @@ private[spark] class ExecutorAllocationManager(
private def onExecutorIdle(executorId: String): Unit = synchronized {
if (executorIds.contains(executorId)) {
if (!removeTimes.contains(executorId) &&
!executorsPendingToRemove.contains(executorId)) {
+
+ val hasCachedBlocks =
+ executorsWithCachedBlocks.contains(executorId) ||
+
executorEndpoints.get(executorId).exists(_.askWithRetry[Boolean](HasCachedBlocks))
+
+ if (hasCachedBlocks) executorsWithCachedBlocks += executorId
--- End diff --
i donot know why we should have an RPC for every executor? I have read
codes of BlockManager carefully and find that blocks except BroadcastBlockId
can tell BlockMaster immediately when cached or unpersist. maybe i have some
mistakes?
if we cannot read blockStatus from BlockManager, i think executor can
report hasCachedBlocks to Driver when Heartbeat. so we donot need to have an
RPC for every executor because that is very expensive.
@andrewor14 @harishreedharan
---
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]
