Speed up task scheduling in standalone mode by reusing serializer

instead of creating a new one for each task.
apache · May 21, 2015 · fe530cd · fe530cd
1 parent a25c1ab
commit fe530cd
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala
@@ -183,8 +183,8 @@ class CoarseGrainedSchedulerBackend(scheduler: TaskSchedulerImpl, val rpcEnv: Rp
 
     // Launch tasks returned by a set of resource offers
     def launchTasks(tasks: Seq[Seq[TaskDescription]]) {
+      val ser = SparkEnv.get.closureSerializer.newInstance()
       for (task <- tasks.flatten) {
-        val ser = SparkEnv.get.closureSerializer.newInstance()
         val serializedTask = ser.serialize(task)
         if (serializedTask.limit >= akkaFrameSize - AkkaUtils.reservedSizeBytes) {
           val taskSetId = scheduler.taskIdToTaskSetId(task.taskId)