Github user mccheah commented on a diff in the pull request: https://github.com/apache/spark/pull/3638#discussion_r22486217 --- Diff: core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala --- @@ -256,15 +256,21 @@ private[spark] class TaskSchedulerImpl( val execId = shuffledOffers(i).executorId val host = shuffledOffers(i).host if (availableCpus(i) >= CPUS_PER_TASK) { - for (task <- taskSet.resourceOffer(execId, host, maxLocality)) { - tasks(i) += task - val tid = task.taskId - taskIdToTaskSetId(tid) = taskSet.taskSet.id - taskIdToExecutorId(tid) = execId - executorsByHost(host) += execId - availableCpus(i) -= CPUS_PER_TASK - assert(availableCpus(i) >= 0) - launchedTask = true + try { + for (task <- taskSet.resourceOffer(execId, host, maxLocality)) { + tasks(i) += task + val tid = task.taskId + taskIdToTaskSetId(tid) = taskSet.taskSet.id + taskIdToExecutorId(tid) = execId + executorsByHost(host) += execId + availableCpus(i) -= CPUS_PER_TASK + assert(availableCpus(i) >= 0) + launchedTask = true + } + } catch { + case e: TaskNotSerializableException => { --- End diff -- My understanding was that if this task set fails, even if other task sets can be executed, this task set would prevent being able to complete the whole job. Again however this is new territory to me, so I'll follow this lead and test 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