[
https://issues.apache.org/jira/browse/SPARK-11979?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Shixiong Zhu resolved SPARK-11979.
----------------------------------
Resolution: Fixed
Fix Version/s: 1.6.0
> Empty TrackStateRDD cannot be checkpointed and recovered from checkpoint file
> ------------------------------------------------------------------------------
>
> Key: SPARK-11979
> URL: https://issues.apache.org/jira/browse/SPARK-11979
> Project: Spark
> Issue Type: Bug
> Components: Streaming
> Reporter: Tathagata Das
> Assignee: Tathagata Das
> Priority: Critical
> Fix For: 1.6.0
>
>
> {code}
> Job aborted due to stage failure: Task 0 in stage 6.0 failed 1 times, most
> recent failure: Lost task 0.0 in stage 6.0 (TID 20, localhost):
> java.lang.IllegalArgumentException: requirement failed: Invalid initial
> capacity
> at scala.Predef$.require(Predef.scala:233)
> at
> org.apache.spark.streaming.util.OpenHashMapBasedStateMap.<init>(StateMap.scala:96)
> at
> org.apache.spark.streaming.util.OpenHashMapBasedStateMap.<init>(StateMap.scala:86)
> at
> org.apache.spark.streaming.util.OpenHashMapBasedStateMap.readObject(StateMap.scala:291)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> java.io.ObjectStreamClass.invokeReadObject(ObjectStreamClass.java:1017)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1893)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
> at
> java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
> at
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:76)
> at
> org.apache.spark.serializer.DeserializationStream$$anon$1.getNext(Serializer.scala:181)
> at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$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$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:921)
> at
> org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:921)
> at
> org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
> at
> org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> Driver stacktrace:
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in
> stage 6.0 failed 1 times, most recent failure: Lost task 0.0 in stage 6.0
> (TID 20, localhost): java.lang.IllegalArgumentException: requirement failed:
> Invalid initial capacity
> at scala.Predef$.require(Predef.scala:233)
> at
> org.apache.spark.streaming.util.OpenHashMapBasedStateMap.<init>(StateMap.scala:96)
> at
> org.apache.spark.streaming.util.OpenHashMapBasedStateMap.<init>(StateMap.scala:86)
> at
> org.apache.spark.streaming.util.OpenHashMapBasedStateMap.readObject(StateMap.scala:291)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> java.io.ObjectStreamClass.invokeReadObject(ObjectStreamClass.java:1017)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1893)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
> at
> java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990)
> at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
> at
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:76)
> at
> org.apache.spark.serializer.DeserializationStream$$anon$1.getNext(Serializer.scala:181)
> at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$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$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:921)
> at
> org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:921)
> at
> org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
> at
> org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> 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)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
