[
https://issues.apache.org/jira/browse/SPARK-17450?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
cen yuhai updated SPARK-17450:
------------------------------
Description:
{code}
java.lang.OutOfMemoryError: Java heap space
at
org.apache.spark.sql.catalyst.expressions.UnsafeRow.copy(UnsafeRow.java:536)
at
org.apache.spark.sql.catalyst.expressions.UnsafeRow.copy(UnsafeRow.java:93)
at
org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.fetchNextPartition(Window.scala:278)
at
org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.next(Window.scala:304)
at
org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.next(Window.scala:246)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:512)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:74)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:104)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:247)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
{code}
was:
${code}
java.lang.OutOfMemoryError: Java heap space
at
org.apache.spark.sql.catalyst.expressions.UnsafeRow.copy(UnsafeRow.java:536)
at
org.apache.spark.sql.catalyst.expressions.UnsafeRow.copy(UnsafeRow.java:93)
at
org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.fetchNextPartition(Window.scala:278)
at
org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.next(Window.scala:304)
at
org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.next(Window.scala:246)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:512)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95)
at
org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:74)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:104)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:247)
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)
${code}
> spark sql rownumber OOM
> -----------------------
>
> Key: SPARK-17450
> URL: https://issues.apache.org/jira/browse/SPARK-17450
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.6.2
> Reporter: cen yuhai
>
> {code}
> java.lang.OutOfMemoryError: Java heap space
> at
> org.apache.spark.sql.catalyst.expressions.UnsafeRow.copy(UnsafeRow.java:536)
> at
> org.apache.spark.sql.catalyst.expressions.UnsafeRow.copy(UnsafeRow.java:93)
> at
> org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.fetchNextPartition(Window.scala:278)
> at
> org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.next(Window.scala:304)
> at
> org.apache.spark.sql.execution.Window$$anonfun$8$$anon$1.next(Window.scala:246)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:512)
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686)
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95)
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:74)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:104)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:247)
> 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)
> {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]
