viirya commented on a change in pull request #26614: [SPARK-29976] New conf for
single task stage speculation
URL: https://github.com/apache/spark/pull/26614#discussion_r350029398
##########
File path: core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala
##########
@@ -983,19 +1011,15 @@ private[spark] class TaskSetManager(
// bound based on that.
logDebug("Task length threshold for speculation: " + threshold)
for (tid <- runningTasksSet) {
- val info = taskInfos(tid)
- val index = info.index
- if (!successful(index) && copiesRunning(index) == 1 &&
info.timeRunning(time) > threshold &&
- !speculatableTasks.contains(index)) {
- addPendingTask(index, speculatable = true)
- logInfo(
- ("Marking task %d in stage %s (on %s) as speculatable because it
ran more" +
- " than %.0f ms(%d speculatable tasks in this taskset now)")
- .format(index, taskSet.id, info.host, threshold,
speculatableTasks.size + 1))
- speculatableTasks += index
- sched.dagScheduler.speculativeTaskSubmitted(tasks(index))
- foundTasks = true
- }
+ foundTasks |= checkAndSubmitSpeculatableTask(tid, time, threshold)
+ }
+ }
+ if (speculationTaskDurationThresOpt.isDefined) {
+ val time = clock.getTimeMillis()
+ val threshold = speculationTaskDurationThresOpt.get
+ logDebug("Checking tasks taking long time than provided speculation
threshold: " + threshold)
Review comment:
taking long time -> taking longer time
----------------------------------------------------------------
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]
