You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Joseph E. Gonzalez (JIRA)" <ji...@apache.org> on 2014/05/11 00:03:35 UTC
[jira] [Updated] (SPARK-1786) Kryo Serialization Error in GraphX
[ https://issues.apache.org/jira/browse/SPARK-1786?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Joseph E. Gonzalez updated SPARK-1786:
--------------------------------------
Description:
The following code block will generate a serialization error when run in the spark-shell with Kryo enabled:
{code}
import org.apache.spark.storage._
import org.apache.spark.graphx._
import org.apache.spark.graphx.util._
val g = GraphGenerators.gridGraph(sc, 100, 100)
val e = g.edges
e.persist(StorageLevel.MEMORY_ONLY_SER)
e.collect().foreach(println(_)) // <- Runs successfully the first time.
// The following line will fail:
e.collect().foreach(println(_))
{code}
The following error is generated:
{code}
scala> e.collect().foreach(println(_))
14/05/09 18:31:13 INFO SparkContext: Starting job: collect at EdgeRDD.scala:59
14/05/09 18:31:13 INFO DAGScheduler: Got job 1 (collect at EdgeRDD.scala:59) with 8 output partitions (allowLocal=false)
14/05/09 18:31:13 INFO DAGScheduler: Final stage: Stage 1(collect at EdgeRDD.scala:59)
14/05/09 18:31:13 INFO DAGScheduler: Parents of final stage: List()
14/05/09 18:31:13 INFO DAGScheduler: Missing parents: List()
14/05/09 18:31:13 INFO DAGScheduler: Submitting Stage 1 (MappedRDD[15] at map at EdgeRDD.scala:59), which has no missing parents
14/05/09 18:31:13 INFO DAGScheduler: Submitting 8 missing tasks from Stage 1 (MappedRDD[15] at map at EdgeRDD.scala:59)
14/05/09 18:31:13 INFO TaskSchedulerImpl: Adding task set 1.0 with 8 tasks
14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:0 as TID 8 on executor localhost: localhost (PROCESS_LOCAL)
14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:0 as 1779 bytes in 3 ms
14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:1 as TID 9 on executor localhost: localhost (PROCESS_LOCAL)
14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:1 as 1779 bytes in 4 ms
14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:2 as TID 10 on executor localhost: localhost (PROCESS_LOCAL)
14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:2 as 1779 bytes in 4 ms
14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:3 as TID 11 on executor localhost: localhost (PROCESS_LOCAL)
14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:3 as 1779 bytes in 4 ms
14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:4 as TID 12 on executor localhost: localhost (PROCESS_LOCAL)
14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:4 as 1779 bytes in 3 ms
14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:5 as TID 13 on executor localhost: localhost (PROCESS_LOCAL)
14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:5 as 1782 bytes in 4 ms
14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:6 as TID 14 on executor localhost: localhost (PROCESS_LOCAL)
14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:6 as 1783 bytes in 4 ms
14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:7 as TID 15 on executor localhost: localhost (PROCESS_LOCAL)
14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:7 as 1783 bytes in 4 ms
14/05/09 18:31:13 INFO Executor: Running task ID 9
14/05/09 18:31:13 INFO Executor: Running task ID 8
14/05/09 18:31:13 INFO Executor: Running task ID 11
14/05/09 18:31:13 INFO Executor: Running task ID 14
14/05/09 18:31:13 INFO Executor: Running task ID 10
14/05/09 18:31:13 INFO Executor: Running task ID 13
14/05/09 18:31:13 INFO Executor: Running task ID 15
14/05/09 18:31:13 INFO Executor: Running task ID 12
14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_6 locally
14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_4 locally
14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_2 locally
14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_7 locally
14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_1 locally
14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_3 locally
14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_0 locally
14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_5 locally
14/05/09 18:31:13 ERROR Executor: Exception in task ID 13
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 ERROR Executor: Exception in task ID 10
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 ERROR Executor: Exception in task ID 11
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 ERROR Executor: Exception in task ID 12
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 ERROR Executor: Exception in task ID 15
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 ERROR Executor: Exception in task ID 8
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 ERROR Executor: Exception in task ID 9
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 ERROR Executor: Exception in task ID 14
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 WARN TaskSetManager: Lost TID 11 (task 1.0:3)
14/05/09 18:31:13 WARN TaskSetManager: Loss was due to java.lang.NullPointerException
java.lang.NullPointerException
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
at org.apache.spark.scheduler.Task.run(Task.scala:51)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
14/05/09 18:31:13 ERROR TaskSetManager: Task 1.0:3 failed 1 times; aborting job
14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 1]
14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 2]
14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 3]
14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 4]
14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
14/05/09 18:31:13 INFO DAGScheduler: Failed to run collect at EdgeRDD.scala:59
14/05/09 18:31:13 INFO TaskSchedulerImpl: Cancelling stage 1
14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 5]
14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 6]
14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 7]
14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
org.apache.spark.SparkException: Job aborted due to stage failure: Task 1.0:3 failed 1 times, most recent failure: Exception failure in TID 11 on host localhost: java.lang.NullPointerException
org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
scala.collection.Iterator$class.foreach(Iterator.scala:727)
scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
scala.collection.AbstractIterator.to(Iterator.scala:1157)
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
org.apache.spark.scheduler.Task.run(Task.scala:51)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:744)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1033)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1017)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1015)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1015)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:633)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1207)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107
{code}
We believe the error is associated with serialization of the EdgePartition.
was:
The following code block will generate a serialization error when run in the spark-shell with Kryo enabled:
import org.apache.spark.storage._
import org.apache.spark.graphx._
import org.apache.spark.graphx.util._
val g = GraphGenerators.gridGraph(sc, 100, 100)
val e = g.edges
e.persist(StorageLevel.MEMORY_ONLY_SER)
e.collect().foreach(println(_))
e.collect().foreach(println(_))
> Kryo Serialization Error in GraphX
> ----------------------------------
>
> Key: SPARK-1786
> URL: https://issues.apache.org/jira/browse/SPARK-1786
> Project: Spark
> Issue Type: Bug
> Components: GraphX
> Affects Versions: 1.0.0
> Reporter: Joseph E. Gonzalez
>
> The following code block will generate a serialization error when run in the spark-shell with Kryo enabled:
> {code}
> import org.apache.spark.storage._
> import org.apache.spark.graphx._
> import org.apache.spark.graphx.util._
> val g = GraphGenerators.gridGraph(sc, 100, 100)
> val e = g.edges
> e.persist(StorageLevel.MEMORY_ONLY_SER)
> e.collect().foreach(println(_)) // <- Runs successfully the first time.
> // The following line will fail:
> e.collect().foreach(println(_))
> {code}
> The following error is generated:
> {code}
> scala> e.collect().foreach(println(_))
> 14/05/09 18:31:13 INFO SparkContext: Starting job: collect at EdgeRDD.scala:59
> 14/05/09 18:31:13 INFO DAGScheduler: Got job 1 (collect at EdgeRDD.scala:59) with 8 output partitions (allowLocal=false)
> 14/05/09 18:31:13 INFO DAGScheduler: Final stage: Stage 1(collect at EdgeRDD.scala:59)
> 14/05/09 18:31:13 INFO DAGScheduler: Parents of final stage: List()
> 14/05/09 18:31:13 INFO DAGScheduler: Missing parents: List()
> 14/05/09 18:31:13 INFO DAGScheduler: Submitting Stage 1 (MappedRDD[15] at map at EdgeRDD.scala:59), which has no missing parents
> 14/05/09 18:31:13 INFO DAGScheduler: Submitting 8 missing tasks from Stage 1 (MappedRDD[15] at map at EdgeRDD.scala:59)
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Adding task set 1.0 with 8 tasks
> 14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:0 as TID 8 on executor localhost: localhost (PROCESS_LOCAL)
> 14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:0 as 1779 bytes in 3 ms
> 14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:1 as TID 9 on executor localhost: localhost (PROCESS_LOCAL)
> 14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:1 as 1779 bytes in 4 ms
> 14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:2 as TID 10 on executor localhost: localhost (PROCESS_LOCAL)
> 14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:2 as 1779 bytes in 4 ms
> 14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:3 as TID 11 on executor localhost: localhost (PROCESS_LOCAL)
> 14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:3 as 1779 bytes in 4 ms
> 14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:4 as TID 12 on executor localhost: localhost (PROCESS_LOCAL)
> 14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:4 as 1779 bytes in 3 ms
> 14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:5 as TID 13 on executor localhost: localhost (PROCESS_LOCAL)
> 14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:5 as 1782 bytes in 4 ms
> 14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:6 as TID 14 on executor localhost: localhost (PROCESS_LOCAL)
> 14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:6 as 1783 bytes in 4 ms
> 14/05/09 18:31:13 INFO TaskSetManager: Starting task 1.0:7 as TID 15 on executor localhost: localhost (PROCESS_LOCAL)
> 14/05/09 18:31:13 INFO TaskSetManager: Serialized task 1.0:7 as 1783 bytes in 4 ms
> 14/05/09 18:31:13 INFO Executor: Running task ID 9
> 14/05/09 18:31:13 INFO Executor: Running task ID 8
> 14/05/09 18:31:13 INFO Executor: Running task ID 11
> 14/05/09 18:31:13 INFO Executor: Running task ID 14
> 14/05/09 18:31:13 INFO Executor: Running task ID 10
> 14/05/09 18:31:13 INFO Executor: Running task ID 13
> 14/05/09 18:31:13 INFO Executor: Running task ID 15
> 14/05/09 18:31:13 INFO Executor: Running task ID 12
> 14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_6 locally
> 14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_4 locally
> 14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_2 locally
> 14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_7 locally
> 14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_1 locally
> 14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_3 locally
> 14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_0 locally
> 14/05/09 18:31:13 INFO BlockManager: Found block rdd_12_5 locally
> 14/05/09 18:31:13 ERROR Executor: Exception in task ID 13
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 ERROR Executor: Exception in task ID 10
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 ERROR Executor: Exception in task ID 11
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 ERROR Executor: Exception in task ID 12
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 ERROR Executor: Exception in task ID 15
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 ERROR Executor: Exception in task ID 8
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 ERROR Executor: Exception in task ID 9
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 ERROR Executor: Exception in task ID 14
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 WARN TaskSetManager: Lost TID 11 (task 1.0:3)
> 14/05/09 18:31:13 WARN TaskSetManager: Loss was due to java.lang.NullPointerException
> java.lang.NullPointerException
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> at org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> at org.apache.spark.scheduler.Task.run(Task.scala:51)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 14/05/09 18:31:13 ERROR TaskSetManager: Task 1.0:3 failed 1 times; aborting job
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
> 14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 1]
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
> 14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 2]
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
> 14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 3]
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
> 14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 4]
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
> 14/05/09 18:31:13 INFO DAGScheduler: Failed to run collect at EdgeRDD.scala:59
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Cancelling stage 1
> 14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 5]
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
> 14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 6]
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
> 14/05/09 18:31:13 INFO TaskSetManager: Loss was due to java.lang.NullPointerException [duplicate 7]
> 14/05/09 18:31:13 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 1.0:3 failed 1 times, most recent failure: Exception failure in TID 11 on host localhost: java.lang.NullPointerException
> org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:269)
> org.apache.spark.graphx.impl.EdgePartition$$anon$1.next(EdgePartition.scala:262)
> scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> scala.collection.Iterator$class.foreach(Iterator.scala:727)
> scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> scala.collection.AbstractIterator.to(Iterator.scala:1157)
> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> org.apache.spark.rdd.RDD$$anonfun$15.apply(RDD.scala:706)
> org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> org.apache.spark.SparkContext$$anonfun$runJob$4.apply(SparkContext.scala:1071)
> org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
> org.apache.spark.scheduler.Task.run(Task.scala:51)
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:208)
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> java.lang.Thread.run(Thread.java:744)
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1033)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1017)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1015)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1015)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633)
> at scala.Option.foreach(Option.scala:236)
> at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:633)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1207)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
> at akka.actor.ActorCell.invoke(ActorCell.scala:456)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
> at akka.dispatch.Mailbox.run(Mailbox.scala:219)
> at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
> at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107
> {code}
> We believe the error is associated with serialization of the EdgePartition.
--
This message was sent by Atlassian JIRA
(v6.2#6252)