[
https://issues.apache.org/jira/browse/SPARK-16757?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15531056#comment-15531056
]
Thomas Graves commented on SPARK-16757:
---------------------------------------
we are seeing issues with ReplSuite after adding the callercontext to Task.java
where it uses the class loader.
Error:
scala> accum: org.apache.spark.util.LongAccumulator = LongAccumulator(id: 0,
name: None, value: 0)
scala> org.apache.spark.SparkException: Job aborted due to stage failure: Task
0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0
(TID 0, localhost): java.lang.ClassCircularityError:
io/netty/util/internal/__matchers__/org/apache/spark/network/protocol/MessageMatcher
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at
io.netty.util.internal.JavassistTypeParameterMatcherGenerator.generate(JavassistTypeParameterMatcherGenerator.java:62)
at
io.netty.util.internal.JavassistTypeParameterMatcherGenerator.generate(JavassistTypeParameterMatcherGenerator.java:54)
at
io.netty.util.internal.TypeParameterMatcher.get(TypeParameterMatcher.java:42)
at
io.netty.util.internal.TypeParameterMatcher.find(TypeParameterMatcher.java:78)
at
io.netty.handler.codec.MessageToMessageEncoder.<init>(MessageToMessageEncoder.java:59)
at
org.apache.spark.network.protocol.MessageEncoder.<init>(MessageEncoder.java:34)
at
org.apache.spark.network.TransportContext.<init>(TransportContext.java:78)
at
org.apache.spark.rpc.netty.NettyRpcEnv.downloadClient(NettyRpcEnv.scala:354)
at
org.apache.spark.rpc.netty.NettyRpcEnv.openChannel(NettyRpcEnv.scala:324)
at
org.apache.spark.repl.ExecutorClassLoader.org$apache$spark$repl$ExecutorClassLoader$$getClassFileInputStreamFromSparkRPC(ExecutorClassLoader.scala:90)
at
org.apache.spark.repl.ExecutorClassLoader$$anonfun$1.apply(ExecutorClassLoader.scala:57)
at
org.apache.spark.repl.ExecutorClassLoader$$anonfun$1.apply(ExecutorClassLoader.scala:57)
at
org.apache.spark.repl.ExecutorClassLoader.findClassLocally(ExecutorClassLoader.scala:162)
at
org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:80)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at
io.netty.util.internal.JavassistTypeParameterMatcherGenerator.generate(JavassistTypeParameterMatcherGenerator.java:62)
at
io.netty.util.internal.JavassistTypeParameterMatcherGenerator.generate(JavassistTypeParameterMatcherGenerator.java:54)
at
io.netty.util.internal.TypeParameterMatcher.get(TypeParameterMatcher.java:42)
at
io.netty.util.internal.TypeParameterMatcher.find(TypeParameterMatcher.java:78)
at
io.netty.handler.codec.MessageToMessageEncoder.<init>(MessageToMessageEncoder.java:59)
at
org.apache.spark.network.protocol.MessageEncoder.<init>(MessageEncoder.java:34)
at
org.apache.spark.network.TransportContext.<init>(TransportContext.java:78)
at
org.apache.spark.rpc.netty.NettyRpcEnv.downloadClient(NettyRpcEnv.scala:354)
at
org.apache.spark.rpc.netty.NettyRpcEnv.openChannel(NettyRpcEnv.scala:324)
at
org.apache.spark.repl.ExecutorClassLoader.org$apache$spark$repl$ExecutorClassLoader$$getClassFileInputStreamFromSparkRPC(ExecutorClassLoader.scala:90)
at
org.apache.spark.repl.ExecutorClassLoader$$anonfun$1.apply(ExecutorClassLoader.scala:57)
at
org.apache.spark.repl.ExecutorClassLoader$$anonfun$1.apply(ExecutorClassLoader.scala:57)
at
org.apache.spark.repl.ExecutorClassLoader.findClassLocally(ExecutorClassLoader.scala:162)
at
org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:80)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.util.Utils$.classForName(Utils.scala:225)
at
org.apache.spark.util.CallerContext.setCurrentContext(Utils.scala:2492)
at org.apache.spark.scheduler.Task.run(Task.scala:96)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1433)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1421)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1420)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1420)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1648)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1603)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1592)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1901)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1914)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1927)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1941)
at org.apache.spark.rdd.RDD$$anonfun$foreach$1.apply(RDD.scala:894)
at org.apache.spark.rdd.RDD$$anonfun$foreach$1.apply(RDD.scala:892)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.foreach(RDD.scala:892)
... 94 elided
Caused by: java.lang.ClassCircularityError:
io/netty/util/internal/__matchers__/org/apache/spark/network/protocol/MessageMatcher
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at
io.netty.util.internal.JavassistTypeParameterMatcherGenerator.generate(JavassistTypeParameterMatcherGenerator.java:62)
at
io.netty.util.internal.JavassistTypeParameterMatcherGenerator.generate(JavassistTypeParameterMatcherGenerator.java:54)
at
io.netty.util.internal.TypeParameterMatcher.get(TypeParameterMatcher.java:42)
at
io.netty.util.internal.TypeParameterMatcher.find(TypeParameterMatcher.java:78)
at
io.netty.handler.codec.MessageToMessageEncoder.<init>(MessageToMessageEncoder.java:59)
at
org.apache.spark.network.protocol.MessageEncoder.<init>(MessageEncoder.java:34)
at org.apache.spark.network.TransportContext.<init>(TransportContext.java:78)
at
org.apache.spark.rpc.netty.NettyRpcEnv.downloadClient(NettyRpcEnv.scala:354)
at org.apache.spark.rpc.netty.NettyRpcEnv.openChannel(NettyRpcEnv.scala:324)
at
org.apache.spark.repl.ExecutorClassLoader.org$apache$spark$repl$ExecutorClassLoader$$getClassFileInputStreamFromSparkRPC(ExecutorClassLoader.scala:90)
at
org.apache.spark.repl.ExecutorClassLoader$$anonfun$1.apply(ExecutorClassLoader.scala:57)
at
org.apache.spark.repl.ExecutorClassLoader$$anonfun$1.apply(ExecutorClassLoader.scala:57)
at
org.apache.spark.repl.ExecutorClassLoader.findClassLocally(ExecutorClassLoader.scala:162)
at
org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:80)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at
io.netty.util.internal.JavassistTypeParameterMatcherGenerator.generate(JavassistTypeParameterMatcherGenerator.java:62)
at
io.netty.util.internal.JavassistTypeParameterMatcherGenerator.generate(JavassistTypeParameterMatcherGenerator.java:54)
at
io.netty.util.internal.TypeParameterMatcher.get(TypeParameterMatcher.java:42)
at
io.netty.util.internal.TypeParameterMatcher.find(TypeParameterMatcher.java:78)
at
io.netty.handler.codec.MessageToMessageEncoder.<init>(MessageToMessageEncoder.java:59)
at
org.apache.spark.network.protocol.MessageEncoder.<init>(MessageEncoder.java:34)
at org.apache.spark.network.TransportContext.<init>(TransportContext.java:78)
at
org.apache.spark.rpc.netty.NettyRpcEnv.downloadClient(NettyRpcEnv.scala:354)
at org.apache.spark.rpc.netty.NettyRpcEnv.openChannel(NettyRpcEnv.scala:324)
at
org.apache.spark.repl.ExecutorClassLoader.org$apache$spark$repl$ExecutorClassLoader$$getClassFileInputStreamFromSparkRPC(ExecutorClassLoader.scala:90)
at
org.apache.spark.repl.ExecutorClassLoader$$anonfun$1.apply(ExecutorClassLoader.scala:57)
at
org.apache.spark.repl.ExecutorClassLoader$$anonfun$1.apply(ExecutorClassLoader.scala:57)
at
org.apache.spark.repl.ExecutorClassLoader.findClassLocally(ExecutorClassLoader.scala:162)
at
org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:80)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.util.Utils$.classForName(Utils.scala:225)
at org.apache.spark.util.CallerContext.setCurrentContext(Utils.scala:2492)
at org.apache.spark.scheduler.Task.run(Task.scala:96)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
scala> res1: Long = 0
https://amplab.cs.berkeley.edu/jenkins/view/Spark%20QA%20Test%20(Dashboard)/job/spark-master-test-maven-hadoop-2.3/2000/testReport/junit/org.apache.spark.repl/ReplSuite/simple_foreach_with_accumulator/
Temporarily change to use Class.forName
> Set up caller context to HDFS and Yarn
> --------------------------------------
>
> Key: SPARK-16757
> URL: https://issues.apache.org/jira/browse/SPARK-16757
> Project: Spark
> Issue Type: Sub-task
> Reporter: Weiqing Yang
> Assignee: Weiqing Yang
> Fix For: 2.1.0
>
>
> In this jira, Spark will invoke hadoop caller context api to set up its
> caller context to HDFS.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
