[SPARK-6286][Mesos][minor] Handle missing Mesos case TASK_ERROR

- Made TaskState.isFailed for handling TASK_LOST and TASK_ERROR and synchronizing CoarseMesosSchedulerBackend and MesosSchedulerBackend - This is related apache#5000 Author: Jongyoul Lee <[email protected]> Closes apache#5088 from jongyoul/SPARK-6286-1 and squashes the following commits: 4f2362f [Jongyoul Lee] [SPARK-6286][Mesos][minor] Handle missing Mesos case TASK_ERROR - Fixed scalastyle ac4336a [Jongyoul Lee] [SPARK-6286][Mesos][minor] Handle missing Mesos case TASK_ERROR - Made TaskState.isFailed for handling TASK_LOST and TASK_ERROR and synchronizing CoarseMesosSchedulerBackend and MesosSchedulerBackend
mrares · Mar 20, 2015 · 116c553 · 116c553
1 parent 0745a30
commit 116c553
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 2 deletions.
diff --git 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/...src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala b/...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
@@ -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")
         }