tgravescs commented on a change in pull request #27223: 
[SPARK-30511][SPARK-28403][CORE] Don't treat failed/killed speculative tasks as 
pending in Spark scheduler
URL: https://github.com/apache/spark/pull/27223#discussion_r370674267
 
 

 ##########
 File path: core/src/main/scala/org/apache/spark/ExecutorAllocationManager.scala
 ##########
 @@ -614,18 +614,24 @@ private[spark] class ExecutorAllocationManager(
             stageAttemptToNumRunningTask -= stageAttempt
           }
         }
-        // If the task failed, we expect it to be resubmitted later. To ensure 
we have
-        // enough resources to run the resubmitted task, we need to mark the 
scheduler
-        // as backlogged again if it's not already marked as such (SPARK-8366)
-        if (taskEnd.reason != Success) {
-          if (totalPendingTasks() == 0) {
-            allocationManager.onSchedulerBacklogged()
-          }
-          if (taskEnd.taskInfo.speculative) {
-            stageAttemptToSpeculativeTaskIndices.get(stageAttempt).foreach 
{_.remove(taskIndex)}
-          } else {
-            stageAttemptToTaskIndices.get(stageAttempt).foreach 
{_.remove(taskIndex)}
-          }
+
+        if (taskEnd.taskInfo.speculative) {
+          stageAttemptToSpeculativeTaskIndices.get(stageAttempt).foreach 
{_.remove{taskIndex}}
+          stageAttemptToNumSpeculativeTasks(stageAttempt) -= 1
 
 Review comment:
   thanks for the explanation, its been a while since I looked at the 
speculative handling in the scheduler.   I think the failed task case with 
speculative is ok. I think the problem is the scheduler isn't  tracking those 
task as speculative or not after the initial launch.  I would rather error on 
the side of asking for to many and the failure case should be less frequent.  
that is a lot more complex case along with making the dynamic allocation 
manager smarter about it.  If you can file that other jira I mentioned above to 
follow up, if you could put those details in there as well that would be great.

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to