[
https://issues.apache.org/jira/browse/SPARK-15822?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15325159#comment-15325159
]
Pete Robbins commented on SPARK-15822:
--------------------------------------
I am forcing a system dump when I detect a corrupt UTF8String is being created.
This is using IBM JVM because I can analyse the dump and see the stacks and
object contents using Eclipse Memory Analyzer.
So... with whole stage codegen enabled we get a stack of:
java.lang.Thread @ 0x835f9838
|- at com.ibm.jvm.Dump.SystemDumpImpl()I (Native Method)
|- at com.ibm.jvm.Dump.SystemDump()V (Dump.java:139)
|- at org.apache.spark.unsafe.types.UTF8String.<init>(Ljava/lang/Object;JI)V
(UTF8String.java:125(Compiled Code))
|- at
org.apache.spark.unsafe.types.UTF8String.fromAddress(Ljava/lang/Object;JI)Lorg/apache/spark/unsafe/types/UTF8String;
(UTF8String.java:102(Compiled Code))
|- at
org.apache.spark.sql.catalyst.expressions.UnsafeRow.getUTF8String(I)Lorg/apache/spark/unsafe/types/UTF8String;
(UnsafeRow.java:414(Compiled Code))
|- at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.sort_addToSorter$(Lorg/apache/spark/sql/catalyst/expressions/GeneratedClass$GeneratedIterator;)V
(null)
|- at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext()V
(null)
|- at org.apache.spark.sql.execution.BufferedRowIterator.hasNext()Z
(BufferedRowIterator.java:43(Compiled Code))
|- at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext()Z
(WholeStageCodegenExec.scala:361(Compiled Code))
|- at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.findNextInnerJoinRows$(Lorg/apache/spark/sql/catalyst/expressions/GeneratedClass$GeneratedIterator;Lscala/collection/Iterator;Lscala/collection/Iterator;)Z
(null)
|- at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext()V
(null)
|- at org.apache.spark.sql.execution.BufferedRowIterator.hasNext()Z
(BufferedRowIterator.java:43(Compiled Code))
|- at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$doExecute$2$$anon$2.hasNext()Z
(WholeStageCodegenExec.scala:377)
|- at scala.collection.Iterator$$anon$11.hasNext()Z
(Iterator.scala:408(Compiled Code))
|- at scala.collection.convert.Wrappers$IteratorWrapper.hasNext()Z
(Wrappers.scala:30)
|- at
org.spark_project.guava.collect.Ordering.leastOf(Ljava/util/Iterator;I)Ljava/util/List;
(Ordering.java:628)
|- at
org.apache.spark.util.collection.Utils$.takeOrdered(Lscala/collection/Iterator;ILscala/math/Ordering;)Lscala/collection/Iterator;
(Utils.scala:37)
|- at
org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1$$anonfun$30.apply(Lscala/collection/Iterator;)Lscala/collection/Iterator;
(RDD.scala:1365)
|- at
org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1$$anonfun$30.apply(Ljava/lang/Object;)Ljava/lang/Object;
(RDD.scala:1362)
|- at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(Lorg/apache/spark/TaskContext;ILscala/collection/Iterator;)Lscala/collection/Iterator;
(RDD.scala:757) |
|- at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(Ljava/lang/Object;Ljava/lang/Object;Ljava/lang/Object;)Ljava/lang/Object;
(RDD.scala:757)
|
|- at
org.apache.spark.rdd.MapPartitionsRDD.compute(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(MapPartitionsRDD.scala:38)
|
|- at
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(RDD.scala:318)
|
|- at
org.apache.spark.rdd.RDD.iterator(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(RDD.scala:282)
|
|- at
org.apache.spark.scheduler.ResultTask.runTask(Lorg/apache/spark/TaskContext;)Ljava/lang/Object;
(ResultTask.scala:70)
and disabled it still fails:
java.lang.Thread @ 0x835ffd60
|- at com.ibm.jvm.Dump.SystemDumpImpl()I (Native Method)
|- at com.ibm.jvm.Dump.SystemDump()V (Dump.java:139)
|- at org.apache.spark.unsafe.types.UTF8String.<init>(Ljava/lang/Object;JI)V
(UTF8String.java:125(Compiled Code))
|- at
org.apache.spark.unsafe.types.UTF8String.fromAddress(Ljava/lang/Object;JI)Lorg/apache/spark/unsafe/types/UTF8String;
(UTF8String.java:102(Compiled Code))
|- at
org.apache.spark.sql.catalyst.expressions.UnsafeRow.getUTF8String(I)Lorg/apache/spark/unsafe/types/UTF8String;
(UnsafeRow.java:414(Compiled Code))
|- at
org.apache.spark.sql.catalyst.expressions.JoinedRow.getUTF8String(I)Lorg/apache/spark/unsafe/types/UTF8String;
(JoinedRow.scala:102(Compiled Code))
|- at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Lorg/apache/spark/sql/catalyst/InternalRow;)Lorg/apache/spark/sql/catalyst/expressions/UnsafeRow;
(null)
|- at
org.apache.spark.sql.execution.aggregate.AggregationIterator$$anonfun$generateResultProjection$1.apply(Lorg/apache/spark/sql/catalyst/expressions/UnsafeRow;Lorg/apache/spark/sql/catalyst/expressions/MutableRow;)Lorg/apache/spark/sql/catalyst/expressions/UnsafeRow;
(AggregationIterator.scala:231)
|- at
org.apache.spark.sql.execution.aggregate.AggregationIterator$$anonfun$generateResultProjection$1.apply(Ljava/lang/Object;Ljava/lang/Object;)Ljava/lang/Object;
(AggregationIterator.scala:220)
|- at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.next()Lorg/apache/spark/sql/catalyst/expressions/UnsafeRow;
(TungstenAggregationIterator.scala:392)
|- at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.next()Ljava/lang/Object;
(TungstenAggregationIterator.scala:79)
|- at
org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(Lscala/collection/Iterator;)Lscala/collection/Iterator;
(UnsafeExternalRowSorter.java:173)
|- at
org.apache.spark.sql.execution.SortExec$$anonfun$1.apply(Lscala/collection/Iterator;)Lscala/collection/Iterator;
(SortExec.scala:100)
|- at
org.apache.spark.sql.execution.SortExec$$anonfun$1.apply(Ljava/lang/Object;)Ljava/lang/Object;
(SortExec.scala:93)
|- at
org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(Lorg/apache/spark/TaskContext;ILscala/collection/Iterator;)Lscala/collection/Iterator;
(RDD.scala:775)
|- at
org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(Ljava/lang/Object;Ljava/lang/Object;Ljava/lang/Object;)Ljava/lang/Object;
(RDD.scala:775)
|- at
org.apache.spark.rdd.MapPartitionsRDD.compute(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(MapPartitionsRDD.scala:38)
|- at
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(RDD.scala:318)
|- at
org.apache.spark.rdd.RDD.iterator(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(RDD.scala:282)
|- at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(ZippedPartitionsRDD.scala:89)
|- at
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(RDD.scala:318)
|- at
org.apache.spark.rdd.RDD.iterator(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(RDD.scala:282)
|- at
org.apache.spark.rdd.MapPartitionsRDD.compute(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(MapPartitionsRDD.scala:38)
|- at
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(RDD.scala:318)
|- at
org.apache.spark.rdd.RDD.iterator(Lorg/apache/spark/Partition;Lorg/apache/spark/TaskContext;)Lscala/collection/Iterator;
(RDD.scala:282)
> segmentation violation in o.a.s.unsafe.types.UTF8String
> --------------------------------------------------------
>
> Key: SPARK-15822
> URL: https://issues.apache.org/jira/browse/SPARK-15822
> Project: Spark
> Issue Type: Bug
> Affects Versions: 2.0.0
> Environment: linux amd64
> openjdk version "1.8.0_91"
> OpenJDK Runtime Environment (build 1.8.0_91-b14)
> OpenJDK 64-Bit Server VM (build 25.91-b14, mixed mode)
> Reporter: Pete Robbins
> Assignee: Herman van Hovell
> Priority: Blocker
>
> Executors fail with segmentation violation while running application with
> spark.memory.offHeap.enabled true
> spark.memory.offHeap.size 512m
> Also now reproduced with
> spark.memory.offHeap.enabled false
> {noformat}
> #
> # A fatal error has been detected by the Java Runtime Environment:
> #
> # SIGSEGV (0xb) at pc=0x00007f4559b4d4bd, pid=14182, tid=139935319750400
> #
> # JRE version: OpenJDK Runtime Environment (8.0_91-b14) (build 1.8.0_91-b14)
> # Java VM: OpenJDK 64-Bit Server VM (25.91-b14 mixed mode linux-amd64
> compressed oops)
> # Problematic frame:
> # J 4816 C2
> org.apache.spark.unsafe.types.UTF8String.compareTo(Lorg/apache/spark/unsafe/types/UTF8String;)I
> (64 bytes) @ 0x00007f4559b4d4bd [0x00007f4559b4d460+0x5d]
> {noformat}
> We initially saw this on IBM java on PowerPC box but is recreatable on linux
> with OpenJDK. On linux with IBM Java 8 we see a null pointer exception at the
> same code point:
> {noformat}
> 16/06/08 11:14:58 ERROR Executor: Exception in task 1.0 in stage 5.0 (TID 48)
> java.lang.NullPointerException
> at
> org.apache.spark.unsafe.types.UTF8String.compareTo(UTF8String.java:831)
> at org.apache.spark.unsafe.types.UTF8String.compare(UTF8String.java:844)
> at
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.findNextInnerJoinRows$(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$doExecute$2$$anon$2.hasNext(WholeStageCodegenExec.scala:377)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
> at
> scala.collection.convert.Wrappers$IteratorWrapper.hasNext(Wrappers.scala:30)
> at org.spark_project.guava.collect.Ordering.leastOf(Ordering.java:664)
> at org.apache.spark.util.collection.Utils$.takeOrdered(Utils.scala:37)
> at
> org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1$$anonfun$30.apply(RDD.scala:1365)
> at
> org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1$$anonfun$30.apply(RDD.scala:1362)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:757)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:757)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:318)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:282)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
> at org.apache.spark.scheduler.Task.run(Task.scala:85)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1153)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.lang.Thread.run(Thread.java:785)
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
