从远程scala程序,使用Spark 1.3,如何初始化sparkContext
以便我可以连接到在YARN上运行的Spark?即,我在哪里放置YARN节点的地址?
目前我的程序包含:
val conf = new SparkConf().setMaster("yarn-client").setAppName("MyApp")
val sc = new SparkContext(conf)
它产生
[error] (run-main-0) java.lang.ExceptionInInitializerError
java.lang.ExceptionInInitializerError
at org.apache.spark.util.Utils$.getSparkOrYarnConfig(Utils.scala:1959)
at org.apache.spark.storage.BlockManager.<init>(BlockManager.scala:104)
at org.apache.spark.storage.BlockManager.<init>(BlockManager.scala:179)
at org.apache.spark.SparkEnv$.create(SparkEnv.scala:310)
at org.apache.spark.SparkEnv$.createDriverEnv(SparkEnv.scala:163)
at org.apache.spark.SparkContext.createSparkEnv(SparkContext.scala:269)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:272)
at SparkExampleLocalDriver$.main(SparkExample.scala:9)
at SparkExampleLocalDriver.main(SparkExample.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
Caused by: org.apache.spark.SparkException: Unable to load YARN support
at org.apache.spark.deploy.SparkHadoopUtil$.liftedTree1$1(SparkHadoopUtil.scala:217)
at org.apache.spark.deploy.SparkHadoopUtil$.<init>(SparkHadoopUtil.scala:212)
at org.apache.spark.deploy.SparkHadoopUtil$.<clinit>(SparkHadoopUtil.scala)
at org.apache.spark.util.Utils$.getSparkOrYarnConfig(Utils.scala:1959)
at org.apache.spark.storage.BlockManager.<init>(BlockManager.scala:104)
at org.apache.spark.storage.BlockManager.<init>(BlockManager.scala:179)
at org.apache.spark.SparkEnv$.create(SparkEnv.scala:310)
at org.apache.spark.SparkEnv$.createDriverEnv(SparkEnv.scala:163)
at org.apache.spark.SparkContext.createSparkEnv(SparkContext.scala:269)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:272)
at SparkExampleLocalDriver$.main(SparkExample.scala:9)
at SparkExampleLocalDriver.main(SparkExample.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
Caused by: java.lang.ClassNotFoundException: org.apache.spark.deploy.yarn.YarnSparkHadoopUtil
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:195)
at org.apache.spark.deploy.SparkHadoopUtil$.liftedTree1$1(SparkHadoopUtil.scala:213)
at org.apache.spark.deploy.SparkHadoopUtil$.<init>(SparkHadoopUtil.scala:212)
at org.apache.spark.deploy.SparkHadoopUtil$.<clinit>(SparkHadoopUtil.scala)
at org.apache.spark.util.Utils$.getSparkOrYarnConfig(Utils.scala:1959)
at org.apache.spark.storage.BlockManager.<init>(BlockManager.scala:104)
at org.apache.spark.storage.BlockManager.<init>(BlockManager.scala:179)
at org.apache.spark.SparkEnv$.create(SparkEnv.scala:310)
at org.apache.spark.SparkEnv$.createDriverEnv(SparkEnv.scala:163)
at org.apache.spark.SparkContext.createSparkEnv(SparkContext.scala:269)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:272)
at SparkExampleLocalDriver$.main(SparkExample.scala:9)
at SparkExampleLocalDriver.main(SparkExample.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
答案 0 :(得分:1)
您的Spark二进制文件不包含与YARN相关的类
为hadoop使用预先构建的二进制文件
http://www.apache.org/dyn/closer.cgi/spark/spark-1.3.1/spark-1.3.1-bin-hadoop2.4.tgz
如果您正在编译来源,请添加纱线和hadoop配置文件
./make-distribution.sh --tgz --skip-java-test -Pyarn -Phadoop-2.4 -Dhadoop.version=2.4.0