记Spark on Yarn集群错误汇总

我们经常使用Spark on yarn的模式进行开发和任务调度，但是常常会出现各种错误。

本文将这些问题汇总并提出解决：

先贴一个spark提交任务到yarn的脚本：

 nohup /data_dev/software/spark-2.2.0-bin-2.6.0-cdh5.14.0/bin/spark-submit \
 --class log_analysis.Ktr_Log \
--master yarn \
--deploy-mode cluster \
--driver-memory 1g \
--executor-memory 2g \
--executor-cores 2 \
/data_dev/software/kettle_log_analysis.jar \
  > /data_dev/software/logs/SparkTest.log 2>&1 &

1、spark找不到main类：

【ERROR yarn.ApplicationMaster: Uncaught exception: java.lang.ClassNotFoundException】

 20/06/29 09:24:21 ERROR yarn.ApplicationMaster: Uncaught exception: 
java.lang.ClassNotFoundException: src/main/scala/log_analysis/Ktr_Log
	at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
	at org.apache.spark.deploy.yarn.ApplicationMaster.startUserApplication(ApplicationMaster.scala:629)
	at org.apache.spark.deploy.yarn.ApplicationMaster.runDriver(ApplicationMaster.scala:394)
	at org.apache.spark.deploy.yarn.ApplicationMaster.run(ApplicationMaster.scala:254)
	at org.apache.spark.deploy.yarn.ApplicationMaster$$anonfun$main$1.apply$mcV$sp(ApplicationMaster.scala:764)
	at org.apache.spark.deploy.SparkHadoopUtil$$anon$2.run(SparkHadoopUtil.scala:67)
	at org.apache.spark.deploy.SparkHadoopUtil$$anon$2.run(SparkHadoopUtil.scala:66)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:422)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1917)
	at org.apache.spark.deploy.SparkHadoopUtil.runAsSparkUser(SparkHadoopUtil.scala:66)
	at org.apache.spark.deploy.yarn.ApplicationMaster$.main(ApplicationMaster.scala:762)
	at org.apache.spark.deploy.yarn.ApplicationMaster.main(ApplicationMaster.scala)
20/06/29 09:24:21 INFO yarn.ApplicationMaster: Final app status: FAILED, exitCode: 10, (reason: Uncaught exception: java.lang.ClassNotFoundException: src/main/scala/log_analysis/Ktr_Log)
20/06/29 09:24:21 INFO util.ShutdownHookManager: Shutdown hook called

解决：

该问题抛出找不到main类，是因为代码中的master在提交到yarn的时候，没有把.master(“local[20]”)注释掉。导致提交不成功。解决如下：

 lazy val spark = SparkSession.builder()
//    .master("local[20]")
    .appName("ReadKettleKjb")
    .config("spark.debug.maxToStringFields", "400")
    .getOrCreate()

2、找不到读取的文件：

【ERROR yarn.ApplicationMaster: User class threw exception: java.lang.ExceptionInInitializerError
java.lang.ExceptionInInitializerError
   at log_analysis.Ktr_Log.main(Ktr_Log.scala)
   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:635)
Caused by: org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: hdfs://192.168.21.30:8020/data_dev/software/kettle_dev_1.log】

 20/06/29 09:31:12 ERROR yarn.ApplicationMaster: User class threw exception: java.lang.ExceptionInInitializerError
java.lang.ExceptionInInitializerError
	at log_analysis.Ktr_Log.main(Ktr_Log.scala)
	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$$anon$2.run(ApplicationMaster.scala:635)
Caused by: org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: hdfs://192.168.21.30:8020/data_dev/software/kettle_dev_1.log
	at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:287)
	at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
	at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
	at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:194)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.ZippedWithIndexRDD.<init>(ZippedWithIndexRDD.scala:44)
	at org.apache.spark.rdd.RDD$$anonfun$zipWithIndex$1.apply(RDD.scala:1294)
	at org.apache.spark.rdd.RDD$$anonfun$zipWithIndex$1.apply(RDD.scala:1294)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
	at org.apache.spark.rdd.RDD.zipWithIndex(RDD.scala:1293)
	at utils.DataFrameUtils$.withLineNOColumn(DataFrameUtils.scala:24)
	at log_analysis.Ktr_Log$.<init>(Ktr_Log.scala:60)
	at log_analysis.Ktr_Log$.<clinit>(Ktr_Log.scala)
	... 6 more

解决：

指定服务器文件的时候，要指定绝对路径。

如果是读取hdfs文件，需要检查服务器ip和端口号、文件路径等。

3、找不到对应的jar包依赖：

【java.lang.ClassNotFoundException: Failed to find data source: com.databricks.spark.xml. Please find packages at http://spark.apache.org/third-party-projects.html
at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:549)】

 java.lang.ClassNotFoundException: Failed to find data source: com.databricks.spark.xml. Please find packages at http://spark.apache.org/third-party-projects.html
	at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:549)
	at org.apache.spark.sql.execution.datasources.DataSource.providingClass$lzycompute(DataSource.scala:86)
	at org.apache.spark.sql.execution.datasources.DataSource.providingClass(DataSource.scala:86)
	at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:301)
	at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178)
	at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:156)
	at log_analysis.ReadKettleKjb$.analysis_kjb(ReadKettleKjb.scala:117)
	at log_analysis.ReadKettleKjb$.get_kjb_result(ReadKettleKjb.scala:41)
	at log_analysis.Ktr_Log$.main(Ktr_Log.scala:77)
	at log_analysis.Ktr_Log.main(Ktr_Log.scala)
	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$$anon$2.run(ApplicationMaster.scala:635)
Caused by: java.lang.ClassNotFoundException: com.databricks.spark.xml.DefaultSource
	at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
	at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$21$$anonfun$apply$12.apply(DataSource.scala:533)
	at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$21$$anonfun$apply$12.apply(DataSource.scala:533)
	at scala.util.Try$.apply(Try.scala:192)
	at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$21.apply(DataSource.scala:533)
	at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$21.apply(DataSource.scala:533)
	at scala.util.Try.orElse(Try.scala:84)
	at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:533)
	... 14 more

由于我在代码中指定了spark读取xml的文件方式，是用databricks下面的依赖包，故需要将依赖的jar包同时在idea打包过程中加入。

 val df = spark.sqlContext
      .read
      .format("com.databricks.spark.xml")
      .option("rowTag", "book")
      .schema(customSchema)
      .load("data/books_complex.xml")

4、没有指定master地址

【WARN scheduler.TaskSetManager: Lost task 0.0 in stage 10.0 (TID 14, node01, executor 1): java.lang.ExceptionInInitializerError

Caused by: org.apache.spark.SparkException: A master URL must be set in your configuration
at org.apache.spark.SparkContext.<init>(SparkContext.scala:376)
at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2509)】

 20/06/29 09:54:40 WARN scheduler.TaskSetManager: Lost task 0.0 in stage 10.0 (TID 14, node01, executor 1): java.lang.ExceptionInInitializerError
	at log_analysis.ReadKettleKjb$$anonfun$get_kjb_result$1.apply(ReadKettleKjb.scala:73)
	at log_analysis.ReadKettleKjb$$anonfun$get_kjb_result$1.apply(ReadKettleKjb.scala:64)
	at scala.collection.Iterator$class.foreach(Iterator.scala:893)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
	at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:918)
	at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:918)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:108)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
	at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: A master URL must be set in your configuration
	at org.apache.spark.SparkContext.<init>(SparkContext.scala:376)
	at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2509)
	at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:909)
	at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:901)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:901)
	at log_analysis.ReadKettleKjb$.spark$lzycompute(ReadKettleKjb.scala:27)
	at log_analysis.ReadKettleKjb$.spark(ReadKettleKjb.scala:23)
	at log_analysis.ReadKettleKjb$.context$lzycompute(ReadKettleKjb.scala:29)
	at log_analysis.ReadKettleKjb$.context(ReadKettleKjb.scala:29)
	at log_analysis.ReadKettleKjb$.<init>(ReadKettleKjb.scala:30)
	at log_analysis.ReadKettleKjb$.<clinit>(ReadKettleKjb.scala)

报错说在sparkContext对象初始化的时候必须设置一个master URL。但是我明明在提交应用的时候设置了–master呀，为什么说我没有？

其实这是初学者很容易犯的错误，原因在于没有真正理解spark分布式或伪分布式的运行原理。出错的小伙伴往往把创建spark实例，或者sc.textFile读取数据等放在了main函数的外面。

如果检查代码中没有指定master，需要特别注意的是，创建sparkSession对象必须在main方法里面，否则driver无法分发。

在伪分布式中，一个spark 应用对应了一个main函数，放在一个driver里，driver里有一个对应的实例（spark context).driver 负责向各个节点分发资源以及数据。那么如果你把创建实例放在了main函数的外面，driver就没法分发了。所以如果这样写在local模式下是可以成功的，在分布式就会报错。

正确姿势如下：

 def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder()
      .config("spark.sql.shuffle.partitions", 300)
      //    .master("yarn-cluster")
 
      //      .master("local[10]")
      .appName("ktr")
      //      .enableHiveSupport()
      .getOrCreate()
 
    val context = spark.sparkContext
    context.setLogLevel("WARN")
 
 
    xxx...(业务代码)
}

4、scala环境没有生效

【WARN scheduler.TaskSetManager: Lost task 0.0 in stage 10.0 (TID 14, node01, executor 2): java.lang.ExceptionInInitializerError

Caused by: java.lang.IllegalStateException: Library directory ‘/data_dev/software/hadoop-2.6.0-cdh5.14.0/hadoopDatas/tempDatas/nm-local-dir/usercache/root/appcache/application_1593315523377_0017/container_1593315523377_0017_01_000003/assembly/target/scala-2.11/jars’ does not exist; make sure Spark is built.
at …】

 20/06/29 10:15:20 WARN scheduler.TaskSetManager: Lost task 0.0 in stage 10.0 (TID 14, node01, executor 2): java.lang.ExceptionInInitializerError
	at log_analysis.ReadKettleKjb$$anonfun$get_kjb_result$1.apply(ReadKettleKjb.scala:74)
	at log_analysis.ReadKettleKjb$$anonfun$get_kjb_result$1.apply(ReadKettleKjb.scala:65)
	at scala.collection.Iterator$class.foreach(Iterator.scala:893)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
	at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:918)
	at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:918)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:108)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
	at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.IllegalStateException: Library directory '/data_dev/software/hadoop-2.6.0-cdh5.14.0/hadoopDatas/tempDatas/nm-local-dir/usercache/root/appcache/application_1593315523377_0017/container_1593315523377_0017_01_000003/assembly/target/scala-2.11/jars' does not exist; make sure Spark is built.
	at org.apache.spark.launcher.CommandBuilderUtils.checkState(CommandBuilderUtils.java:248)
	at org.apache.spark.launcher.CommandBuilderUtils.findJarsDir(CommandBuilderUtils.java:347)
	at org.apache.spark.launcher.YarnCommandBuilderUtils$.findJarsDir(YarnCommandBuilderUtils.scala:38)
	at org.apache.spark.deploy.yarn.Client.prepareLocalResources(Client.scala:526)
	at org.apache.spark.deploy.yarn.Client.createContainerLaunchContext(Client.scala:814)
	at org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:169)
	at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.start(YarnClientSchedulerBackend.scala:56)
	at org.apache.spark.scheduler.TaskSchedulerImpl.start(TaskSchedulerImpl.scala:173)
	at org.apache.spark.SparkContext.<init>(SparkContext.scala:509)
	at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2509)
	at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:909)
	at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:901)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:901)
	at log_analysis.ReadKettleKjb$.spark$lzycompute(ReadKettleKjb.scala:28)
	at log_analysis.ReadKettleKjb$.spark(ReadKettleKjb.scala:23)
	at log_analysis.ReadKettleKjb$.context$lzycompute(ReadKettleKjb.scala:30)
	at log_analysis.ReadKettleKjb$.context(ReadKettleKjb.scala:30)
	at log_analysis.ReadKettleKjb$.<init>(ReadKettleKjb.scala:31)
	at log_analysis.ReadKettleKjb$.<clinit>(ReadKettleKjb.scala)
	... 14 more

该错误提示没有scala相关的jar包，此时应该检查服务器上是否安装了scala的sdk：

 [root@node01 XXF_EDW_SS_1]# scala -version
Scala code runner version 2.11.12 -- Copyright 2002-2017, LAMP/EPFL

显示以上版本说明scala安装成功，且环境变量配置生效。

如果没有安装，在idea对代码进行打包的时候，应该将scala相关的jar包集成到目标jar包中，如下：

5、Exception from container-launch.Exit code: 1 Stack trace: ExitCodeException exitCode=1:

Yarn错误日志如下：

 yarn主界面状态显示failed，显示如下：
 
Diagnostics: Exception from container-launch.
Container id: container_1574829788169_0011_02_000001
Exit code: 1
Stack trace: ExitCodeException exitCode=1: 
    at org.apache.hadoop.util.Shell.runCommand(Shell.java:604)
    at org.apache.hadoop.util.Shell.run(Shell.java:507)
    at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:789)
    at org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor.launchContainer(DefaultContainerExecutor.java:213)
    at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:302)
    at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:82)
    at java.util.concurrent.FutureTask.run(FutureTask.java:266)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
    at java.lang.Thread.run(Thread.java:748)
 
 
Container exited with a non-zero exit code 1
Failing this attempt. Failing the application.

但是在yarn界面点进去查看job日志详情，发现状态为successed。

查看很多文档都不能解决这个问题，最后查看代码，发现：

 SparkConf sparkConf = new SparkConf()
//                .setMaster("local[2]")
                .setAppName("javaSparkWordcount");

将setmaster（“local[2]”）注释掉，完美解决。

转自：https://blog.csdn.net/u010051036/article/details/107017429

	nohup /data_dev/software/spark-2.2.0-bin-2.6.0-cdh5.14.0/bin/spark-submit \
	--class log_analysis.Ktr_Log \
	--master yarn \
	--deploy-mode cluster \
	--driver-memory 1g \
	--executor-memory 2g \
	--executor-cores 2 \
	/data_dev/software/kettle_log_analysis.jar \
	> /data_dev/software/logs/SparkTest.log 2>&1 &

	20/06/29 09:24:21 ERROR yarn.ApplicationMaster: Uncaught exception:
	java.lang.ClassNotFoundException: src/main/scala/log_analysis/Ktr_Log
	at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
	at org.apache.spark.deploy.yarn.ApplicationMaster.startUserApplication(ApplicationMaster.scala:629)
	at org.apache.spark.deploy.yarn.ApplicationMaster.runDriver(ApplicationMaster.scala:394)
	at org.apache.spark.deploy.yarn.ApplicationMaster.run(ApplicationMaster.scala:254)
	at org.apache.spark.deploy.yarn.ApplicationMaster$$anonfun$main$1.apply$mcV$sp(ApplicationMaster.scala:764)
	at org.apache.spark.deploy.SparkHadoopUtil$$anon$2.run(SparkHadoopUtil.scala:67)
	at org.apache.spark.deploy.SparkHadoopUtil$$anon$2.run(SparkHadoopUtil.scala:66)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:422)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1917)
	at org.apache.spark.deploy.SparkHadoopUtil.runAsSparkUser(SparkHadoopUtil.scala:66)
	at org.apache.spark.deploy.yarn.ApplicationMaster$.main(ApplicationMaster.scala:762)
	at org.apache.spark.deploy.yarn.ApplicationMaster.main(ApplicationMaster.scala)
	20/06/29 09:24:21 INFO yarn.ApplicationMaster: Final app status: FAILED, exitCode: 10, (reason: Uncaught exception: java.lang.ClassNotFoundException: src/main/scala/log_analysis/Ktr_Log)
	20/06/29 09:24:21 INFO util.ShutdownHookManager: Shutdown hook called

	lazy val spark = SparkSession.builder()
	// .master("local[20]")
	.appName("ReadKettleKjb")
	.config("spark.debug.maxToStringFields", "400")
	.getOrCreate()

	20/06/29 09:31:12 ERROR yarn.ApplicationMaster: User class threw exception: java.lang.ExceptionInInitializerError
	java.lang.ExceptionInInitializerError
	at log_analysis.Ktr_Log.main(Ktr_Log.scala)
	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$$anon$2.run(ApplicationMaster.scala:635)
	Caused by: org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: hdfs://192.168.21.30:8020/data_dev/software/kettle_dev_1.log
	at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:287)
	at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
	at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
	at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:194)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
	at org.apache.spark.rdd.ZippedWithIndexRDD.<init>(ZippedWithIndexRDD.scala:44)
	at org.apache.spark.rdd.RDD$$anonfun$zipWithIndex$1.apply(RDD.scala:1294)
	at org.apache.spark.rdd.RDD$$anonfun$zipWithIndex$1.apply(RDD.scala:1294)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
	at org.apache.spark.rdd.RDD.zipWithIndex(RDD.scala:1293)
	at utils.DataFrameUtils$.withLineNOColumn(DataFrameUtils.scala:24)
	at log_analysis.Ktr_Log$.<init>(Ktr_Log.scala:60)
	at log_analysis.Ktr_Log$.<clinit>(Ktr_Log.scala)
	... 6 more

	java.lang.ClassNotFoundException: Failed to find data source: com.databricks.spark.xml. Please find packages at http://spark.apache.org/third-party-projects.html
	at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:549)
	at org.apache.spark.sql.execution.datasources.DataSource.providingClass$lzycompute(DataSource.scala:86)
	at org.apache.spark.sql.execution.datasources.DataSource.providingClass(DataSource.scala:86)
	at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:301)
	at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178)
	at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:156)
	at log_analysis.ReadKettleKjb$.analysis_kjb(ReadKettleKjb.scala:117)
	at log_analysis.ReadKettleKjb$.get_kjb_result(ReadKettleKjb.scala:41)
	at log_analysis.Ktr_Log$.main(Ktr_Log.scala:77)
	at log_analysis.Ktr_Log.main(Ktr_Log.scala)
	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$$anon$2.run(ApplicationMaster.scala:635)
	Caused by: java.lang.ClassNotFoundException: com.databricks.spark.xml.DefaultSource
	at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
	at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$21$$anonfun$apply$12.apply(DataSource.scala:533)
	at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$21$$anonfun$apply$12.apply(DataSource.scala:533)
	at scala.util.Try$.apply(Try.scala:192)
	at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$21.apply(DataSource.scala:533)
	at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$21.apply(DataSource.scala:533)
	at scala.util.Try.orElse(Try.scala:84)
	at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:533)
	... 14 more

	val df = spark.sqlContext
	.read
	.format("com.databricks.spark.xml")
	.option("rowTag", "book")
	.schema(customSchema)
	.load("data/books_complex.xml")

	20/06/29 09:54:40 WARN scheduler.TaskSetManager: Lost task 0.0 in stage 10.0 (TID 14, node01, executor 1): java.lang.ExceptionInInitializerError
	at log_analysis.ReadKettleKjb$$anonfun$get_kjb_result$1.apply(ReadKettleKjb.scala:73)
	at log_analysis.ReadKettleKjb$$anonfun$get_kjb_result$1.apply(ReadKettleKjb.scala:64)
	at scala.collection.Iterator$class.foreach(Iterator.scala:893)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
	at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:918)
	at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:918)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:108)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
	at java.lang.Thread.run(Thread.java:748)
	Caused by: org.apache.spark.SparkException: A master URL must be set in your configuration
	at org.apache.spark.SparkContext.<init>(SparkContext.scala:376)
	at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2509)
	at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:909)
	at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:901)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:901)
	at log_analysis.ReadKettleKjb$.spark$lzycompute(ReadKettleKjb.scala:27)
	at log_analysis.ReadKettleKjb$.spark(ReadKettleKjb.scala:23)
	at log_analysis.ReadKettleKjb$.context$lzycompute(ReadKettleKjb.scala:29)
	at log_analysis.ReadKettleKjb$.context(ReadKettleKjb.scala:29)
	at log_analysis.ReadKettleKjb$.<init>(ReadKettleKjb.scala:30)
	at log_analysis.ReadKettleKjb$.<clinit>(ReadKettleKjb.scala)

	def main(args: Array[String]): Unit = {
	val spark = SparkSession
	.builder()
	.config("spark.sql.shuffle.partitions", 300)
	// .master("yarn-cluster")

	// .master("local[10]")
	.appName("ktr")
	// .enableHiveSupport()
	.getOrCreate()

	val context = spark.sparkContext
	context.setLogLevel("WARN")


	xxx...(业务代码)
	}

	20/06/29 10:15:20 WARN scheduler.TaskSetManager: Lost task 0.0 in stage 10.0 (TID 14, node01, executor 2): java.lang.ExceptionInInitializerError
	at log_analysis.ReadKettleKjb$$anonfun$get_kjb_result$1.apply(ReadKettleKjb.scala:74)
	at log_analysis.ReadKettleKjb$$anonfun$get_kjb_result$1.apply(ReadKettleKjb.scala:65)
	at scala.collection.Iterator$class.foreach(Iterator.scala:893)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
	at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:918)
	at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:918)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2062)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:108)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
	at java.lang.Thread.run(Thread.java:748)
	Caused by: java.lang.IllegalStateException: Library directory '/data_dev/software/hadoop-2.6.0-cdh5.14.0/hadoopDatas/tempDatas/nm-local-dir/usercache/root/appcache/application_1593315523377_0017/container_1593315523377_0017_01_000003/assembly/target/scala-2.11/jars' does not exist; make sure Spark is built.
	at org.apache.spark.launcher.CommandBuilderUtils.checkState(CommandBuilderUtils.java:248)
	at org.apache.spark.launcher.CommandBuilderUtils.findJarsDir(CommandBuilderUtils.java:347)
	at org.apache.spark.launcher.YarnCommandBuilderUtils$.findJarsDir(YarnCommandBuilderUtils.scala:38)
	at org.apache.spark.deploy.yarn.Client.prepareLocalResources(Client.scala:526)
	at org.apache.spark.deploy.yarn.Client.createContainerLaunchContext(Client.scala:814)
	at org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:169)
	at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.start(YarnClientSchedulerBackend.scala:56)
	at org.apache.spark.scheduler.TaskSchedulerImpl.start(TaskSchedulerImpl.scala:173)
	at org.apache.spark.SparkContext.<init>(SparkContext.scala:509)
	at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2509)
	at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:909)
	at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:901)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:901)
	at log_analysis.ReadKettleKjb$.spark$lzycompute(ReadKettleKjb.scala:28)
	at log_analysis.ReadKettleKjb$.spark(ReadKettleKjb.scala:23)
	at log_analysis.ReadKettleKjb$.context$lzycompute(ReadKettleKjb.scala:30)
	at log_analysis.ReadKettleKjb$.context(ReadKettleKjb.scala:30)
	at log_analysis.ReadKettleKjb$.<init>(ReadKettleKjb.scala:31)
	at log_analysis.ReadKettleKjb$.<clinit>(ReadKettleKjb.scala)
	... 14 more

	[root@node01 XXF_EDW_SS_1]# scala -version
	Scala code runner version 2.11.12 -- Copyright 2002-2017, LAMP/EPFL

	yarn主界面状态显示failed，显示如下：

	Diagnostics: Exception from container-launch.
	Container id: container_1574829788169_0011_02_000001
	Exit code: 1
	Stack trace: ExitCodeException exitCode=1:
	at org.apache.hadoop.util.Shell.runCommand(Shell.java:604)
	at org.apache.hadoop.util.Shell.run(Shell.java:507)
	at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:789)
	at org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor.launchContainer(DefaultContainerExecutor.java:213)
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:302)
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:82)
	at java.util.concurrent.FutureTask.run(FutureTask.java:266)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
	at java.lang.Thread.run(Thread.java:748)


	Container exited with a non-zero exit code 1
	Failing this attempt. Failing the application.

	SparkConf sparkConf = new SparkConf()
	// .setMaster("local[2]")
	.setAppName("javaSparkWordcount");