[ https://issues.apache.org/jira/browse/SPARK-3710?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14158326#comment-14158326 ]
Andrew Or commented on SPARK-3710: ---------------------------------- https://github.com/apache/spark/pull/2605 > YARN integration test is flaky > ------------------------------ > > Key: SPARK-3710 > URL: https://issues.apache.org/jira/browse/SPARK-3710 > Project: Spark > Issue Type: Bug > Components: YARN > Affects Versions: 1.2.0 > Reporter: Patrick Wendell > Assignee: Marcelo Vanzin > Priority: Blocker > Fix For: 1.2.0 > > > This has been regularly failing the master build: > Example failure: > https://amplab.cs.berkeley.edu/jenkins/job/Spark-Master-SBT/738/AMPLAB_JENKINS_BUILD_PROFILE=hadoop2.2,label=centos/#showFailuresLink > One thing to look at is whether the YARN mini cluster makes assumptions about > being able to bind to specific ports. > {code} > sbt.ForkMain$ForkError: Call From test04.amplab/10.123.1.2 to test04.amplab:0 > failed on connection exception: java.net.ConnectException: Connection > refused; For more details see: > http://wiki.apache.org/hadoop/ConnectionRefused > at sun.reflect.GeneratedConstructorAccessor5.newInstance(Unknown Source) > at > sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) > at java.lang.reflect.Constructor.newInstance(Constructor.java:526) > at org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:783) > at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:730) > at org.apache.hadoop.ipc.Client.call(Client.java:1351) > at org.apache.hadoop.ipc.Client.call(Client.java:1300) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:206) > at com.sun.proxy.$Proxy11.getClusterMetrics(Unknown Source) > at > org.apache.hadoop.yarn.api.impl.pb.client.ApplicationClientProtocolPBClientImpl.getClusterMetrics(ApplicationClientProtocolPBClientImpl.java:152) > at sun.reflect.GeneratedMethodAccessor2.invoke(Unknown Source) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at > org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:186) > at > org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) > at com.sun.proxy.$Proxy12.getClusterMetrics(Unknown Source) > at > org.apache.hadoop.yarn.client.api.impl.YarnClientImpl.getYarnClusterMetrics(YarnClientImpl.java:246) > at > org.apache.spark.deploy.yarn.Client$$anonfun$submitApplication$1.apply(Client.scala:69) > at > org.apache.spark.deploy.yarn.Client$$anonfun$submitApplication$1.apply(Client.scala:69) > at org.apache.spark.Logging$class.logInfo(Logging.scala:59) > at org.apache.spark.deploy.yarn.Client.logInfo(Client.scala:35) > at > org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:68) > at > org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.start(YarnClientSchedulerBackend.scala:61) > at > org.apache.spark.scheduler.TaskSchedulerImpl.start(TaskSchedulerImpl.scala:141) > at org.apache.spark.SparkContext.<init>(SparkContext.scala:310) > at > org.apache.spark.deploy.yarn.YarnClusterDriver$.main(YarnClusterSuite.scala:140) > at > org.apache.spark.deploy.yarn.YarnClusterSuite$$anonfun$1.apply$mcV$sp(YarnClusterSuite.scala:91) > at > org.apache.spark.deploy.yarn.YarnClusterSuite$$anonfun$1.apply(YarnClusterSuite.scala:89) > at > org.apache.spark.deploy.yarn.YarnClusterSuite$$anonfun$1.apply(YarnClusterSuite.scala:89) > at > org.scalatest.Transformer$$anonfun$apply$1.apply(Transformer.scala:22) > at > org.scalatest.Transformer$$anonfun$apply$1.apply(Transformer.scala:22) > at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85) > at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104) > at org.scalatest.Transformer.apply(Transformer.scala:22) > at org.scalatest.Transformer.apply(Transformer.scala:20) > at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:158) > at org.scalatest.Suite$class.withFixture(Suite.scala:1121) > at org.scalatest.FunSuite.withFixture(FunSuite.scala:1559) > at > org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:155) > at > org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:167) > at > org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:167) > at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306) > at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:167) > at org.scalatest.FunSuite.runTest(FunSuite.scala:1559) > at > org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:200) > at > org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:200) > at > org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:413) > at > org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:401) > at scala.collection.immutable.List.foreach(List.scala:318) > at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401) > at > org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:396) > at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:483) > at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:200) > at org.scalatest.FunSuite.runTests(FunSuite.scala:1559) > at org.scalatest.Suite$class.run(Suite.scala:1423) > at > org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1559) > at > org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:204) > at > org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:204) > at org.scalatest.SuperEngine.runImpl(Engine.scala:545) > at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:204) > at > org.apache.spark.deploy.yarn.YarnClusterSuite.org$scalatest$BeforeAndAfterAll$$super$run(YarnClusterSuite.scala:35) > at > org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257) > at > org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256) > at > org.apache.spark.deploy.yarn.YarnClusterSuite.run(YarnClusterSuite.scala:35) > at > org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:444) > at > org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:651) > at sbt.ForkMain$Run$2.call(ForkMain.java:294) > at sbt.ForkMain$Run$2.call(ForkMain.java:284) > at java.util.concurrent.FutureTask.run(FutureTask.java:262) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > Caused by: sbt.ForkMain$ForkError: Connection refused > at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method) > at > sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:739) > at > org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:206) > at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:529) > at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:493) > at > org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:547) > at > org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:642) > at org.apache.hadoop.ipc.Client$Connection.access$2600(Client.java:314) > at org.apache.hadoop.ipc.Client.getConnection(Client.java:1399) > at org.apache.hadoop.ipc.Client.call(Client.java:1318) > ... 66 more > {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