Exception in thread "stdout writer for /home/hduser/anaconda2/bin/python" java.lang.AssertionError:_error utils: uncaught exception in thread stdout w-优快云博客

本文记录了一次使用Apache Spark过程中遇到的Block RDD未被正确锁定导致的错误，并详细分析了该问题的原因及可能的解决方案。

18/08/03 15:39:27 ERROR Utils: Uncaught exception in thread stdout writer for /home/hduser/anaconda2/bin/python
java.lang.AssertionError: assertion failed: Block rdd_25_0 is not locked for reading
    at scala.Predef$.assert(Predef.scala:170)
    at org.apache.spark.storage.BlockInfoManager.unlock(BlockInfoManager.scala:299)
    at org.apache.spark.storage.BlockManager.releaseLock(BlockManager.scala:769)
    at org.apache.spark.storage.BlockManager$$anonfun$1.apply$mcV$sp(BlockManager.scala:540)
	at org.apache.spark.util.CompletionIterator$$anon$1.completion(CompletionIterator.scala:46)
    at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:35)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at scala.collection.Iterator$class.foreach(Iterator.scala:893)
    at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
    at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:204)
    at org.apache.spark.api.python.PythonRunner$$anon$2.writeIteratorToStream(PythonRunner.scala:407)
	at org.apache.spark.api.python.BasePythonRunner$WriterThread$$anonfun$run$1.apply(PythonRunner.scala:215)
    at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1988)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:170)
Exception in thread "stdout writer for /home/hduser/anaconda2/bin/python" java.lang.AssertionError: assertion failed: Block rdd_25_0 is not locked for reading
    at scala.Predef$.assert(Predef.scala:170)
    at org.apache.spark.storage.BlockInfoManager.unlock(BlockInfoManager.scala:299)
    at org.apache.spark.storage.BlockManager.releaseLock(BlockManager.scala:769)
    at org.apache.spark.storage.BlockManager$$anonfun$1.apply$mcV$sp(BlockManager.scala:540)
	at org.apache.spark.util.CompletionIterator$$anon$1.completion(CompletionIterator.scala:46)
    at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:35)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at scala.collection.Iterator$class.foreach(Iterator.scala:893)
    at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
    at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:204)
    at org.apache.spark.api.python.PythonRunner$$anon$2.writeIteratorToStream(PythonRunner.scala:407)
	at org.apache.spark.api.python.BasePythonRunner$WriterThread$$anonfun$run$1.apply(PythonRunner.scala:215)
    at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1988)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:170)