[
https://issues.apache.org/jira/browse/SPARK-10929?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Naden Franciscus updated SPARK-10929:
-------------------------------------
Description:
We are executing 20 Spark SQL jobs in parallel using Spark Job Server and
hitting the following issue pretty routinely.
40GB heap x 6 nodes. Have tried adjusting shuffle.memoryFraction from 0.2 ->
0.1 with no difference.
{code}
.16): org.apache.spark.SparkException: Task failed while writing rows.
at
org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:250)
at
org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at
org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException: Unable to acquire 16777216 bytes of memory
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.acquireNewPage(UnsafeExternalSorter.java:351)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.<init>(UnsafeExternalSorter.java:138)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.create(UnsafeExternalSorter.java:106)
at
org.apache.spark.sql.execution.UnsafeExternalRowSorter.<init>(UnsafeExternalRowSorter.java:68)
at
org.apache.spark.sql.execution.TungstenSort.org$apache$spark$sql$execution$TungstenSort$$preparePartition$1(sort.scala:146)
at
org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$3.apply(sort.scala:169)
at
org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$3.apply(sort.scala:169)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.prepare(MapPartitionsWithPreparationRDD.scala:50)
at
org.apache.spark.rdd.ZippedPartitionsBaseRDD$$anonfun$tryPrepareParents$1.applyOrElse(ZippedPartitionsRDD.scala:83)
at
org.apache.spark.rdd.ZippedPartitionsBaseRDD$$anonfun$tryPrepareParents$1.applyOrElse(ZippedPartitionsRDD.scala:82)
at
scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
at
scala.collection.TraversableLike$$anonfun$collect$1.apply(TraversableLike.scala:278)
at scala.collection.immutable.List.foreach(List.scala:318)
at
scala.collection.TraversableLike$class.collect(TraversableLike.scala:278)
at scala.collection.AbstractTraversable.collect(Traversable.scala:105)
at
org.apache.spark.rdd.ZippedPartitionsBaseRDD.tryPrepareParents(ZippedPartitionsRDD.scala:82)
at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:97)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
{code}
I have tried setting spark.buffer.pageSize to both 1MB and 64MB (in
spark-defaults.conf) and it makes no difference.
It also tries to acquire 33554432 bytes of memory in both cases.
was:
We are executing 20 Spark SQL jobs in parallel using Spark Job Server and
hitting the following issue pretty routinely.
40GB heap x 6 nodes. Have tried adjusting shuffle.memoryFraction from 0.2 ->
0.1 with no difference.
{code}
.16): org.apache.spark.SparkException: Task failed while writing rows.
at
org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:250)
at
org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at
org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException: Unable to acquire 16777216 bytes of memory
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.acquireNewPage(UnsafeExternalSorter.java:351)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.<init>(UnsafeExternalSorter.java:138)
at
org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.create(UnsafeExternalSorter.java:106)
at
org.apache.spark.sql.execution.UnsafeExternalRowSorter.<init>(UnsafeExternalRowSorter.java:68)
at
org.apache.spark.sql.execution.TungstenSort.org$apache$spark$sql$execution$TungstenSort$$preparePartition$1(sort.scala:146)
at
org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$3.apply(sort.scala:169)
at
org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$3.apply(sort.scala:169)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.prepare(MapPartitionsWithPreparationRDD.scala:50)
at
org.apache.spark.rdd.ZippedPartitionsBaseRDD$$anonfun$tryPrepareParents$1.applyOrElse(ZippedPartitionsRDD.scala:83)
at
org.apache.spark.rdd.ZippedPartitionsBaseRDD$$anonfun$tryPrepareParents$1.applyOrElse(ZippedPartitionsRDD.scala:82)
at
scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
at
scala.collection.TraversableLike$$anonfun$collect$1.apply(TraversableLike.scala:278)
at scala.collection.immutable.List.foreach(List.scala:318)
at
scala.collection.TraversableLike$class.collect(TraversableLike.scala:278)
at scala.collection.AbstractTraversable.collect(Traversable.scala:105)
at
org.apache.spark.rdd.ZippedPartitionsBaseRDD.tryPrepareParents(ZippedPartitionsRDD.scala:82)
at
org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:97)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
{code}
> Tungsten fails to acquire memory writing to HDFS
> ------------------------------------------------
>
> Key: SPARK-10929
> URL: https://issues.apache.org/jira/browse/SPARK-10929
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.0, 1.5.1
> Reporter: Naden Franciscus
> Priority: Blocker
>
> We are executing 20 Spark SQL jobs in parallel using Spark Job Server and
> hitting the following issue pretty routinely.
> 40GB heap x 6 nodes. Have tried adjusting shuffle.memoryFraction from 0.2 ->
> 0.1 with no difference.
> {code}
> .16): org.apache.spark.SparkException: Task failed while writing rows.
> at
> org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:250)
> at
> org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at
> org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.io.IOException: Unable to acquire 16777216 bytes of memory
> at
> org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.acquireNewPage(UnsafeExternalSorter.java:351)
> at
> org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.<init>(UnsafeExternalSorter.java:138)
> at
> org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.create(UnsafeExternalSorter.java:106)
> at
> org.apache.spark.sql.execution.UnsafeExternalRowSorter.<init>(UnsafeExternalRowSorter.java:68)
> at
> org.apache.spark.sql.execution.TungstenSort.org$apache$spark$sql$execution$TungstenSort$$preparePartition$1(sort.scala:146)
> at
> org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$3.apply(sort.scala:169)
> at
> org.apache.spark.sql.execution.TungstenSort$$anonfun$doExecute$3.apply(sort.scala:169)
> at
> org.apache.spark.rdd.MapPartitionsWithPreparationRDD.prepare(MapPartitionsWithPreparationRDD.scala:50)
> at
> org.apache.spark.rdd.ZippedPartitionsBaseRDD$$anonfun$tryPrepareParents$1.applyOrElse(ZippedPartitionsRDD.scala:83)
> at
> org.apache.spark.rdd.ZippedPartitionsBaseRDD$$anonfun$tryPrepareParents$1.applyOrElse(ZippedPartitionsRDD.scala:82)
> at
> scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:33)
> at
> scala.collection.TraversableLike$$anonfun$collect$1.apply(TraversableLike.scala:278)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at
> scala.collection.TraversableLike$class.collect(TraversableLike.scala:278)
> at scala.collection.AbstractTraversable.collect(Traversable.scala:105)
> at
> org.apache.spark.rdd.ZippedPartitionsBaseRDD.tryPrepareParents(ZippedPartitionsRDD.scala:82)
> at
> org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:97)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> {code}
> I have tried setting spark.buffer.pageSize to both 1MB and 64MB (in
> spark-defaults.conf) and it makes no difference.
> It also tries to acquire 33554432 bytes of memory in both cases.
--
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
