Details
-
Bug
-
Status: Resolved
-
Major
-
Resolution: Incomplete
-
2.0.2
-
None
-
None
-
2.0.2 snapshot
Description
I am getting this error when i store the estimates from Julia output to a DF and then i do df.cache()
py4j.protocol.Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.runJob.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 177.0 failed 4 times, most recent failure: Lost task 0.3 in stage 177.0 (TID 9722, 10.63.136.108): java.lang.AssertionError: assertion failed
at scala.Predef$.assert(Predef.scala:156)
at org.apache.spark.storage.BlockInfo.checkInvariants(BlockInfoManager.scala:84)
at org.apache.spark.storage.BlockInfo.readerCount_$eq(BlockInfoManager.scala:66)
at org.apache.spark.storage.BlockInfoManager$$anonfun$releaseAllLocksForTask$2$$anonfun$apply$2.apply(BlockInfoManager.scala:362)
at org.apache.spark.storage.BlockInfoManager$$anonfun$releaseAllLocksForTask$2$$anonfun$apply$2.apply(BlockInfoManager.scala:361)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.storage.BlockInfoManager$$anonfun$releaseAllLocksForTask$2.apply(BlockInfoManager.scala:361)
at org.apache.spark.storage.BlockInfoManager$$anonfun$releaseAllLocksForTask$2.apply(BlockInfoManager.scala:356)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at org.apache.spark.storage.BlockInfoManager.releaseAllLocksForTask(BlockInfoManager.scala:356)
at org.apache.spark.storage.BlockManager.releaseAllLocksForTask(BlockManager.scala:646)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:281)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1454)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1442)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1441)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1441)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1667)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1622)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1611)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1890)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1916)
at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:441)
at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala)
at sun.reflect.GeneratedMethodAccessor37.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.AssertionError: assertion failed
at scala.Predef$.assert(Predef.scala:156)
at org.apache.spark.storage.BlockInfo.checkInvariants(BlockInfoManager.scala:84)
at org.apache.spark.storage.BlockInfo.readerCount_$eq(BlockInfoManager.scala:66)
at org.apache.spark.storage.BlockInfoManager$$anonfun$releaseAllLocksForTask$2$$anonfun$apply$2.apply(BlockInfoManager.scala:362)
at org.apache.spark.storage.BlockInfoManager$$anonfun$releaseAllLocksForTask$2$$anonfun$apply$2.apply(BlockInfoManager.scala:361)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.storage.BlockInfoManager$$anonfun$releaseAllLocksForTask$2.apply(BlockInfoManager.scala:361)
at org.apache.spark.storage.BlockInfoManager$$anonfun$releaseAllLocksForTask$2.apply(BlockInfoManager.scala:356)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at org.apache.spark.storage.BlockInfoManager.releaseAllLocksForTask(BlockInfoManager.scala:356)
at org.apache.spark.storage.BlockManager.releaseAllLocksForTask(BlockManager.scala:646)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:281)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)