pgandhi999 commented on a change in pull request #23677:
[SPARK-26755][SCHEDULER] : Optimize Spark Scheduler to dequeue speculative
tasks…
URL: https://github.com/apache/spark/pull/23677#discussion_r305971698
##########
File path: core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala
##########
@@ -234,63 +214,41 @@ private[spark] class TaskSetManager(
/** Add a task to all the pending-task lists that it should be on. */
private[spark] def addPendingTask(
index: Int,
- resolveRacks: Boolean = true): Unit = {
+ resolveRacks: Boolean = true,
+ speculatable: Boolean = false): Unit = {
+ val pendingTaskSetToAddTo = if (speculatable) pendingSpeculatableTasks
else pendingTasks
for (loc <- tasks(index).preferredLocations) {
loc match {
case e: ExecutorCacheTaskLocation =>
- pendingTasksForExecutor.getOrElseUpdate(e.executorId, new
ArrayBuffer) += index
+ pendingTaskSetToAddTo.forExecutor.getOrElseUpdate(e.executorId, new
ArrayBuffer) += index
case e: HDFSCacheTaskLocation =>
val exe = sched.getExecutorsAliveOnHost(loc.host)
exe match {
case Some(set) =>
for (e <- set) {
- pendingTasksForExecutor.getOrElseUpdate(e, new ArrayBuffer) +=
index
+ pendingTaskSetToAddTo.forExecutor.getOrElseUpdate(e, new
ArrayBuffer) += index
}
logInfo(s"Pending task $index has a cached location at ${e.host}
" +
", where there are executors " + set.mkString(","))
case None => logDebug(s"Pending task $index has a cached location
at ${e.host} " +
- ", but there are no executors alive there.")
+ ", but there are no executors alive there.")
}
case _ =>
}
- pendingTasksForHost.getOrElseUpdate(loc.host, new ArrayBuffer) += index
+ pendingTaskSetToAddTo.forHost.getOrElseUpdate(loc.host, new ArrayBuffer)
+= index
if (resolveRacks) {
sched.getRackForHost(loc.host).foreach { rack =>
- pendingTasksForRack.getOrElseUpdate(rack, new ArrayBuffer) += index
+ pendingTaskSetToAddTo.forRack.getOrElseUpdate(rack, new ArrayBuffer)
+= index
}
}
}
if (tasks(index).preferredLocations == Nil) {
- pendingTasksWithNoPrefs += index
+ pendingTaskSetToAddTo.noPrefs += index
}
- allPendingTasks += index // No point scanning this whole list to find the
old task there
- }
-
- /**
- * Return the pending tasks list for a given executor ID, or an empty list if
- * there is no map entry for that host
Review comment:
Not sure if we really need those three helper methods anymore, might lead to
unnecessary code duplication.
----------------------------------------------------------------
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]
