Davies Liu created SPARK-15260:
----------------------------------
Summary: UnifiedMemoryManager could be in bad state if any
exception happen while evicting blocks
Key: SPARK-15260
URL: https://issues.apache.org/jira/browse/SPARK-15260
Project: Spark
Issue Type: Bug
Components: Spark Core
Affects Versions: 1.6.1, 1.6.0, 2.0.0
Reporter: Davies Liu
Assignee: Andrew Or
{code}
Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task
62 in stage 19.0 failed 4 times, most
recent failure: Lost task 62.3 in stage 19.0 (TID 2841,
ip-10-109-240-229.ec2.internal): java.io.IOException:
java.lang.AssertionError: assertion failed at
org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1223) at
org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(
TorrentBroadcast.scala:165) at
org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(
TorrentBroadcast.scala:64) at
org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast. scala:64)
at
org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.
scala:88) at
org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70) at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala: 71) at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala: 46) at
org.apache.spark.scheduler.Task.run(Task.scala:96) at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:222) at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.
java:1142) at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.
java:617) at
java.lang.Thread.run(Thread.java:745) Caused by: java.lang.AssertionError:
assertion failed at
scala.Predef$.assert(Predef.scala:165) at
org.apache.spark.memory.UnifiedMemoryManager.acquireStorageMemory(
UnifiedMemoryManager.scala:140) at
org.apache.spark.storage.MemoryStore.tryToPut(MemoryStore.scala:387) at
org.apache.spark.storage.MemoryStore.tryToPut(MemoryStore.scala:346) at
org.apache.spark.storage.MemoryStore.putBytes(MemoryStore.scala:99) at
org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:803) at
org.apache.spark.storage.BlockManager.putBytes(BlockManager.scala:690) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$or$$$$
1c5ab38dcb7d9b112f54b116debbe7f$$$$cast$$anonfun$$getRemote$1$1.apply(
TorrentBroadcast.scala:130) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$or$$$$
1c5ab38dcb7d9b112f54b116debbe7f$$$$cast$$anonfun$$getRemote$1$1.apply(
TorrentBroadcast.scala:127) at
scala.Option.map(Option.scala:145) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1.org$apache$spark$broadcast$
TorrentBroadcast$$anonfun$$getRemote$1(TorrentBroadcast.scala:127) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$1.apply(
TorrentBroadcast.scala:137) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$1.apply(
TorrentBroadcast.scala:137) at
scala.Option.orElse(Option.scala:257) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1.apply$mcVI$sp(TorrentBroadcast.
scala:137) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala: 120) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala: 120) at
scala.collection.immutable.List.foreach(List.scala:318) at
org.apache.spark.broadcast.TorrentBroadcast.org$apache$spark$broadcast$
TorrentBroadcast$$readBlocks(TorrentBroadcast.scala:120) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$
1.apply(TorrentBroadcast.scala:175) at
org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1220) ... 12 more
Driver stacktrace: at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$
DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431) at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(
DAGScheduler.scala:1419) at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(
DAGScheduler.scala:1418) at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray. scala:59)
at
scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala: 1418) at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.
apply(DAGScheduler.scala:799) at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.
apply(DAGScheduler.scala:799) at
scala.Option.foreach(Option.scala:236) at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler
.scala:799) at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(
DAGScheduler.scala:1640) at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(
DAGScheduler.scala:1599) at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(
DAGScheduler.scala:1588) at
org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620) at
org.apache.spark.SparkContext.runJob(SparkContext.scala:1837) at
org.apache.spark.SparkContext.runJob(SparkContext.scala:1850) at
org.apache.spark.SparkContext.runJob(SparkContext.scala:1863) at
org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:212 ) at
org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala
:165) at
org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.
scala:174) at
org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$
execute$1$1.apply(DataFrame.scala:1499) at
org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$
execute$1$1.apply(DataFrame.scala:1499) at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(
SQLExecution.scala:56) at
org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086) at
org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1
(DataFrame.scala:1498) at
org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(
DataFrame.scala:1505) at
org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala: 1375) at
org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala: 1374) at
org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2099) at
org.apache.spark.sql.DataFrame.head(DataFrame.scala:1374) at
org.apache.spark.sql.DataFrame.take(DataFrame.scala:1456)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:170) at
org.apache.spark.sql.DataFrame.show(DataFrame.scala:350) at
org.apache.spark.sql.DataFrame.show(DataFrame.scala:311) at
org.apache.spark.sql.DataFrame.show(DataFrame.scala:319) Caused by:
java.io.IOException: java.lang.AssertionError:
assertion failed at
org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1223) at
org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(
TorrentBroadcast.scala:165) at
org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(
TorrentBroadcast.scala:64) at
org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast. scala:64)
at
org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.
scala:88) at
org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70) at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala: 71) at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala: 46) at
org.apache.spark.scheduler.Task.run(Task.scala:96) at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:222) 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.lang.AssertionError:
assertion failed at
scala.Predef$.assert(Predef.scala:165) at
org.apache.spark.memory.UnifiedMemoryManager.acquireStorageMemory(
UnifiedMemoryManager.scala:140) at
org.apache.spark.storage.MemoryStore.tryToPut(MemoryStore.scala:387) at
org.apache.spark.storage.MemoryStore.tryToPut(MemoryStore.scala:346) at
org.apache.spark.storage.MemoryStore.putBytes(MemoryStore.scala:99) at
org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:803) at
org.apache.spark.storage.BlockManager.putBytes(BlockManager.scala:690) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$or$$$$
1c5ab38dcb7d9b112f54b116debbe7f$$$$cast$$anonfun$$getRemote$1$1.apply(
TorrentBroadcast.scala:130) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$or$$$$
1c5ab38dcb7d9b112f54b116debbe7f$$$$cast$$anonfun$$getRemote$1$1.apply(
TorrentBroadcast.scala:127) at
scala.Option.map(Option.scala:145) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1.org$apache$spark$broadcast$
TorrentBroadcast$$anonfun$$getRemote$1(TorrentBroadcast.scala:127) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$1.apply(
TorrentBroadcast.scala:137) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$1.apply(
TorrentBroadcast.scala:137) at
scala.Option.orElse(Option.scala:257) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1.apply$mcVI$sp(TorrentBroadcast.
scala:137) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala: 120) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$
broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala: 120) at
scala.collection.immutable.List.foreach(List.scala:318) at
org.apache.spark.broadcast.TorrentBroadcast.org$apache$spark$broadcast$
TorrentBroadcast$$readBlocks(TorrentBroadcast.scala:120) at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$
1.apply(TorrentBroadcast.scala:175) at
org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1220) at
org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(
TorrentBroadcast.scala:165) at
org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(
TorrentBroadcast.scala:64) at
org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast. scala:64)
at
org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.
scala:88) at
org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70) at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala: 71) at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala: 46) at
org.apache.spark.scheduler.Task.run(Task.scala:96) at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:222) at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.
java:1142) at
java.util.concurrent.ThreadPoolExecutor$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: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
