Juliusz Sompolski created SPARK-21907:
-----------------------------------------
Summary: NullPointerException in UnsafeExternalSorter.spill()
Key: SPARK-21907
URL: https://issues.apache.org/jira/browse/SPARK-21907
Project: Spark
Issue Type: Bug
Components: Spark Core
Affects Versions: 2.2.0
Reporter: Juliusz Sompolski
I see NPE during sorting with the following stacktrace:
{code}
java.lang.NullPointerException
at
org.apache.spark.memory.TaskMemoryManager.getPage(TaskMemoryManager.java:383)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeInMemorySorter$SortComparator.compare(UnsafeInMemorySorter.java:63)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeInMemorySorter$SortComparator.compare(UnsafeInMemorySorter.java:43)
at
org.apache.spark.util.collection.TimSort.countRunAndMakeAscending(TimSort.java:270)
at org.apache.spark.util.collection.TimSort.sort(TimSort.java:142)
at org.apache.spark.util.collection.Sorter.sort(Sorter.scala:37)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeInMemorySorter.getSortedIterator(UnsafeInMemorySorter.java:345)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.spill(UnsafeExternalSorter.java:206)
at
org.apache.spark.memory.TaskMemoryManager.acquireExecutionMemory(TaskMemoryManager.java:203)
at
org.apache.spark.memory.TaskMemoryManager.allocatePage(TaskMemoryManager.java:281)
at
org.apache.spark.memory.MemoryConsumer.allocateArray(MemoryConsumer.java:90)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeInMemorySorter.reset(UnsafeInMemorySorter.java:173)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.spill(UnsafeExternalSorter.java:221)
at
org.apache.spark.memory.TaskMemoryManager.acquireExecutionMemory(TaskMemoryManager.java:203)
at
org.apache.spark.memory.TaskMemoryManager.allocatePage(TaskMemoryManager.java:281)
at
org.apache.spark.memory.MemoryConsumer.allocateArray(MemoryConsumer.java:90)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.growPointerArrayIfNecessary(UnsafeExternalSorter.java:349)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.insertRecord(UnsafeExternalSorter.java:400)
at
org.apache.spark.sql.execution.UnsafeExternalRowSorter.insertRow(UnsafeExternalRowSorter.java:109)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.sort_addToSorter$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
at
org.apache.spark.sql.execution.RowIteratorFromScala.advanceNext(RowIterator.scala:83)
at
org.apache.spark.sql.execution.joins.SortMergeJoinScanner.advancedStreamed(SortMergeJoinExec.scala:778)
at
org.apache.spark.sql.execution.joins.SortMergeJoinScanner.findNextInnerJoinRows(SortMergeJoinExec.scala:685)
at
org.apache.spark.sql.execution.joins.SortMergeJoinExec$$anonfun$doExecute$1$$anon$2.advanceNext(SortMergeJoinExec.scala:259)
at
org.apache.spark.sql.execution.RowIteratorToScala.hasNext(RowIterator.scala:68)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at
org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:346)
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:748)
{code}
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
