bin/spark-submit --class spark.KafkaAccountReport --master yarn --deploy-mode cluster --driver-memory 2g --executor-memory 2g --executor-cores 3 –-total-executor-cores 5 ./jSpark-jar-with-dependencies.jar
集群模式提交任务到yarn,但是状态一直是ACTIVED或者FAILED,并且报如下错误
Application application_1557392692629_0008 failed 2 times due to AM Container for appattempt_1557392692629_0008_000002 exited with exitCode: 13
Failing this attempt.Diagnostics: [2019-05-29 20:51:14.623]Exception from container-launch.
Container id: container_e01_1557392692629_0008_02_000001
Exit code: 13
[2019-05-29 20:51:14.624]Container exited with a non-zero exit code 13. Error file: prelaunch.err.
Last 4096 bytes of prelaunch.err :
Last 4096 bytes of stderr :
onfun$run$1(ApplicationMaster.scala:245)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$3.run(ApplicationMaster.scala:779)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698)
at org.apache.spark.deploy.yarn.ApplicationMaster.doAsUser(ApplicationMaster.scala:778)
at org.apache.spark.deploy.yarn.ApplicationMaster.run(ApplicationMaster.scala:245)
at org.apache.spark.deploy.yarn.ApplicationMaster$.main(ApplicationMaster.scala:803)
at org.apache.spark.deploy.yarn.ApplicationMaster.main(ApplicationMaster.scala)
)
java.lang.InterruptedException
at java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.reportInterruptAfterWait(AbstractQueuedSynchronizer.java:2014)
at java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:2048)
at org.apache.spark.streaming.ContextWaiter.waitForStopOrError(ContextWaiter.scala:63)
at org.apache.spark.streaming.StreamingContext.awaitTermination(StreamingContext.scala:618)
at org.apache.spark.streaming.api.java.JavaStreamingContext.awaitTermination(JavaStreamingContext.scala:565)
at spark.KafkaAccountReport.main(KafkaAccountReport.java:113)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:684)
2019-05-29 20:51:14,103 INFO streaming.StreamingContext: Invoking stop(stopGracefully=false) from shutdown hook
2019-05-29 20:51:14,104 INFO scheduler.ReceiverTracker: ReceiverTracker stopped
2019-05-29 20:51:14,104 INFO scheduler.JobGenerator: Stopping JobGenerator immediately
2019-05-29 20:51:14,105 INFO util.RecurringTimer: Stopped timer for JobGenerator after time 1559134270000
2019-05-29 20:51:14,109 INFO scheduler.JobGenerator: Stopped JobGenerator
2019-05-29 20:51:14,111 INFO scheduler.JobScheduler: Stopped JobScheduler
2019-05-29 20:51:14,114 INFO handler.ContextHandler: Stopped o.s.j.s.ServletContextHandler@76543490{/streaming,null,UNAVAILABLE,@Spark}
2019-05-29 20:51:14,114 INFO handler.ContextHandler: Stopped o.s.j.s.ServletContextHandler@5c31fedc{/streaming/batch,null,UNAVAILABLE,@Spark}
2019-05-29 20:51:14,115 INFO handler.ContextHandler: Stopped o.s.j.s.ServletContextHandler@72e54550{/static/streaming,null,UNAVAILABLE,@Spark}
2019-05-29 20:51:14,115 INFO streaming.StreamingContext: StreamingContext stopped successfully
2019-05-29 20:51:14,116 INFO spark.SparkContext: Invoking stop() from shutdown hook
2019-05-29 20:51:14,119 INFO server.AbstractConnector: Stopped Spark@7037120f{HTTP/1.1,[http/1.1]}{0.0.0.0:0}
2019-05-29 20:51:14,119 INFO ui.SparkUI: Stopped Spark web UI at http://dw-10-10-10-22.haisu.com:46730
2019-05-29 20:51:14,124 INFO spark.MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped!
2019-05-29 20:51:14,130 INFO memory.MemoryStore: MemoryStore cleared
2019-05-29 20:51:14,131 INFO storage.BlockManager: BlockManager stopped
2019-05-29 20:51:14,131 INFO storage.BlockManagerMaster: BlockManagerMaster stopped
2019-05-29 20:51:14,135 INFO scheduler.OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped!
2019-05-29 20:51:14,139 INFO spark.SparkContext: Successfully stopped SparkContext
2019-05-29 20:51:14,139 INFO yarn.ApplicationMaster: Deleting staging directory hdfs://haisu-v2/user/dw/.sparkStaging/application_1557392692629_0008
2019-05-29 20:51:14,174 INFO util.ShutdownHookManager: Shutdown hook called
2019-05-29 20:51:14,174 INFO util.ShutdownHookManager: Deleting directory /data/hdfs/data/tmp/nm-local-dir/usercache/dw/appcache/application_1557392692629_0008/spark-cc902437-f2b1-45bc-a450-ab6d0aa991db
[2019-05-29 20:51:14.624]Container exited with a non-zero exit code 13. Error file: prelaunch.err.
Last 4096 bytes of prelaunch.err :
Last 4096 bytes of stderr :
onfun$run$1(ApplicationMaster.scala:245)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$3.run(ApplicationMaster.scala:779)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698)
at org.apache.spark.deploy.yarn.ApplicationMaster.doAsUser(ApplicationMaster.scala:778)
at org.apache.spark.deploy.yarn.ApplicationMaster.run(ApplicationMaster.scala:245)
at org.apache.spark.deploy.yarn.ApplicationMaster$.main(ApplicationMaster.scala:803)
at org.apache.spark.deploy.yarn.ApplicationMaster.main(ApplicationMaster.scala)
)
解决方法:在Java程序中把setMaster("local[4]")去掉,因为它会覆盖命令行中的yarn模式而以本地模式执行,导致一直等待