diff --git a/core/src/main/scala/org/apache/spark/TaskState.scala b/core/src/main/scala/org/apache/spark/TaskState.scala index d85a6d683427db8abd490a3e4c33ee73d23b0ec0..c415fe99b105ecdab89a44a9a231e24433fb6aa0 100644 --- a/core/src/main/scala/org/apache/spark/TaskState.scala +++ b/core/src/main/scala/org/apache/spark/TaskState.scala @@ -27,6 +27,8 @@ private[spark] object TaskState extends Enumeration { type TaskState = Value + def isFailed(state: TaskState) = (LOST == state) || (FAILED == state) + def isFinished(state: TaskState) = FINISHED_STATES.contains(state) def toMesos(state: TaskState): MesosTaskState = state match { diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala index fc92b9c35c3a361c8e38555998827573db318f4e..e13de0f46ef89b91588a467e42935c666e08e31d 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala @@ -277,7 +277,7 @@ private[spark] class CoarseMesosSchedulerBackend( coresByTaskId -= taskId } // If it was a failure, mark the slave as failed for blacklisting purposes - if (state == MesosTaskState.TASK_FAILED || state == MesosTaskState.TASK_LOST) { + if (TaskState.isFailed(TaskState.fromMesos(state))) { failuresBySlaveId(slaveId) = failuresBySlaveId.getOrElse(slaveId, 0) + 1 if (failuresBySlaveId(slaveId) >= MAX_SLAVE_FAILURES) { logInfo("Blacklisting Mesos slave " + slaveId + " due to too many failures; " + diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala index df8f4306b88a8063f3ccdbc0ad755c6a1f6206fc..06bb52752214156bba0ecc530dd136dd2581c5f7 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala @@ -318,7 +318,8 @@ private[spark] class MesosSchedulerBackend( val tid = status.getTaskId.getValue.toLong val state = TaskState.fromMesos(status.getState) synchronized { - if (status.getState == MesosTaskState.TASK_LOST && taskIdToSlaveId.contains(tid)) { + if (TaskState.isFailed(TaskState.fromMesos(status.getState)) + && taskIdToSlaveId.contains(tid)) { // We lost the executor on this slave, so remember that it's gone removeExecutor(taskIdToSlaveId(tid), "Lost executor") }