Github user dhruve commented on a diff in the pull request:
https://github.com/apache/spark/pull/18950#discussion_r133547780
--- Diff:
core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala ---
@@ -454,64 +477,68 @@ private[spark] class TaskSetManager(
}
}
- dequeueTask(execId, host, allowedLocality).map { case ((index,
taskLocality, speculative)) =>
- // Found a task; do some bookkeeping and return a task description
- val task = tasks(index)
- val taskId = sched.newTaskId()
- // Do various bookkeeping
- copiesRunning(index) += 1
- val attemptNum = taskAttempts(index).size
- val info = new TaskInfo(taskId, index, attemptNum, curTime,
- execId, host, taskLocality, speculative)
- taskInfos(taskId) = info
- taskAttempts(index) = info :: taskAttempts(index)
- // Update our locality level for delay scheduling
- // NO_PREF will not affect the variables related to delay
scheduling
- if (maxLocality != TaskLocality.NO_PREF) {
- currentLocalityIndex = getLocalityIndex(taskLocality)
- lastLaunchTime = curTime
- }
- // Serialize and return the task
- val serializedTask: ByteBuffer = try {
- ser.serialize(task)
- } catch {
- // If the task cannot be serialized, then there's no point to
re-attempt the task,
- // as it will always fail. So just abort the whole task-set.
- case NonFatal(e) =>
- val msg = s"Failed to serialize task $taskId, not attempting
to retry it."
- logError(msg, e)
- abort(s"$msg Exception during serialization: $e")
- throw new TaskNotSerializableException(e)
- }
- if (serializedTask.limit > TaskSetManager.TASK_SIZE_TO_WARN_KB *
1024 &&
- !emittedTaskSizeWarning) {
- emittedTaskSizeWarning = true
- logWarning(s"Stage ${task.stageId} contains a task of very large
size " +
- s"(${serializedTask.limit / 1024} KB). The maximum recommended
task size is " +
- s"${TaskSetManager.TASK_SIZE_TO_WARN_KB} KB.")
- }
- addRunningTask(taskId)
-
- // We used to log the time it takes to serialize the task, but
task size is already
- // a good proxy to task serialization time.
- // val timeTaken = clock.getTime() - startTime
- val taskName = s"task ${info.id} in stage ${taskSet.id}"
- logInfo(s"Starting $taskName (TID $taskId, $host, executor
${info.executorId}, " +
- s"partition ${task.partitionId}, $taskLocality,
${serializedTask.limit} bytes)")
-
- sched.dagScheduler.taskStarted(task, info)
- new TaskDescription(
- taskId,
- attemptNum,
- execId,
- taskName,
- index,
- addedFiles,
- addedJars,
- task.localProperties,
- serializedTask)
+ dequeueTask(execId, host, allowedLocality).map {
--- End diff --
yes. Will fix it.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
