0
我想獲得一個用Scala編寫的Spark 1.1.0程序來工作，但我很難用它。我有一個蜂巢查詢很簡單：Spark提交失敗Hive
select json, score from data
當我運行從火花殼一切以下命令作品（我需要MYSQL_CONN在驅動程序類路徑，因爲我使用蜂巢與一個MySQL的元數據存儲）
bin/spark-shell --master $SPARK_URL --driver-class-path $MYSQL_CONN
import org.apache.spark.sql.hive.HiveContext
val sqlContext = new HiveContext(sc)
sqlContext.sql("select json from data").map(t => t.getString(0)).take(10).foreach(println)
我得到十行json就像我想要的。然而，當我運行這個火花提交如下，我得到一個問題
bin/spark-submit --master $SPARK_URL --class spark.Main --driver-class-path $MYSQL_CONN target/spark-testing-1.0-SNAPSHOT.jar
這裏是我的整個星火計劃
package spark
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.{SparkContext, SparkConf}
object Main {
def main(args: Array[String]) {
val sc = new SparkContext(new SparkConf().setAppName("Gathering Data"))
val sqlContext = new HiveContext(sc)
sqlContext.sql("select json from data").map(t => t.getString(0)).take(10).foreach(println)
}
}
，這裏是將所得疊層
14/12/01 21:30:04 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0, match1hd17.dc1): java.lang.ClassNotFoundException: spark.Main$$anonfun$main$1
java.net.URLClassLoader$1.run(URLClassLoader.java:200)
java.security.AccessController.doPrivileged(Native Method)
java.net.URLClassLoader.findClass(URLClassLoader.java:188)
java.lang.ClassLoader.loadClass(ClassLoader.java:307)
java.lang.ClassLoader.loadClass(ClassLoader.java:252)
java.lang.ClassLoader.loadClassInternal(ClassLoader.java:320)
java.lang.Class.forName0(Native Method)
java.lang.Class.forName(Class.java:247)
org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:59)
java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1575)
java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1496)
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1732)
java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1329)
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1947)
java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1871)
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1753)
java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1329)
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1947)
java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1871)
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1753)
java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1329)
java.io.ObjectInputStream.readObject(ObjectInputStream.java:351)
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:62)
org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:87)
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:57)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.java:886)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:908)
java.lang.Thread.run(Thread.java:619)
14/12/01 21:30:10 ERROR TaskSetManager: Task 0 in stage 0.0 failed 4 times; aborting job
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3, match1hd12.dc1m): java.lang.ClassNotFoundException: spark.Main$$anonfun$main$1
java.net.URLClassLoader$1.run(URLClassLoader.java:200)
java.security.AccessController.doPrivileged(Native Method)
java.net.URLClassLoader.findClass(URLClassLoader.java:188)
java.lang.ClassLoader.loadClass(ClassLoader.java:307)
java.lang.ClassLoader.loadClass(ClassLoader.java:252)
java.lang.ClassLoader.loadClassInternal(ClassLoader.java:320)
java.lang.Class.forName0(Native Method)
java.lang.Class.forName(Class.java:247)
org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:59)
java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1575)
java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1496)
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1732)
java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1329)
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1947)
java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1871)
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1753)
java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1329)
java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1947)
java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1871)
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1753)
java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1329)
java.io.ObjectInputStream.readObject(ObjectInputStream.java:351)
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:62)
org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:87)
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:57)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177)
java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.java:886)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:908)
java.lang.Thread.run(Thread.java:619)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1185)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1174)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1173)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1173)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:688)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1391)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
我已經花了幾個小時了，我不知道爲什麼這隻適用於spark-shell。我查看了單個節點上的stderr輸出，並且它們具有相同的隱藏錯誤消息。如果任何人可以闡明爲什麼這隻適用於spark-shell，而不是spark-submit，那將會很棒。
感謝
UPDATE：
我一直在玩周圍和下面的程序工作正常。
package spark
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.{SparkContext, SparkConf}
object Main {
def main(args: Array[String]) {
val sc = new SparkContext(new SparkConf().setAppName("Gathering Data"))
val sqlContext = new HiveContext(sc)
sqlContext.sql("select json from data").take(10).map(t => t.getString(0)).foreach(println)
}
}
顯然，這將不是一個大數據量的工作，但它表明，這個問題似乎是在ScehmaRDD.map（）函數。
這並沒有改變錯誤信息都沒有。 – Jon 2014-12-02 06:24:18
我遇到了類似的錯誤，它在spark-shell中執行得很好，但不是來自spark-submit。後來我發現spark上下文配置不正確。而在shell中，它的auto默認是初始化的。 – 2014-12-03 05:24:03
在錯誤消息中，我看到了ClassNotFoundException，我猜可能存在編譯錯誤，因此ClassNotFoundException。無論如何，我會嘗試在我的羣集中的代碼，並讓你知道。 – 2014-12-03 05:38:03