最近寫了一個從Kafka讀取資料，處理之后通過saveAsNewAPIHadoopDataset方法寫入到hbase中，正常運行的時候沒有報錯，寫入也正常，但是當手動停止應用，再次執行（通過Checkpoint恢復）的時候就會報錯，跪求大神們解答！！報錯資訊如下：
15/12/22 16:26:52 WARN VerifiableProperties: Property serializer.class is not valid
15/12/22 16:26:57 WARN FileOutputCommitter: Output Path is null in setupJob()
15/12/22 16:26:58 WARN TaskSetManager: Lost task 0.0 in stage 1.0 (TID 1, 10.4.120.183): java.lang.NullPointerException
at org.apache.hadoop.fs.Path.<init>(Path.java:105)
at org.apache.hadoop.fs.Path.<init>(Path.java:94)
at org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.getDefaultWorkFile(FileOutputFormat.java:286)
at org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.getRecordWriter(TextOutputFormat.java:129)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1030)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1014)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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:722)
^C15/12/22 16:26:59 ERROR TaskSetManager: Task 0 in stage 1.0 failed 4 times; aborting job
15/12/22 16:26:59 ERROR JobScheduler: Error running job streaming job 1450772680000 ms.0
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 4 times, most recent failure: Lost task 0.3 in stage 1.0 (TID 4, 10.4.120.183): java.lang.NullPointerException
at org.apache.hadoop.fs.Path.<init>(Path.java:105)
at org.apache.hadoop.fs.Path.<init>(Path.java:94)
at org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.getDefaultWorkFile(FileOutputFormat.java:286)
at org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.getRecordWriter(TextOutputFormat.java:129)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1030)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1014)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:722)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1055)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:998)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:998)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
at org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopDataset(PairRDDFunctions.scala:998)
at com.neusoft.cn.TEST02$$anonfun$createContext$2.apply(TEST02.scala:142)
at com.neusoft.cn.TEST02$$anonfun$createContext$2.apply(TEST02.scala:139)
at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:631)
at org.apache.spark.streaming.dstream.DStream$$anonfun$foreachRDD$1$$anonfun$apply$mcV$sp$3.apply(DStream.scala:631)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ForEachDStream.scala:42)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:40)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1$$anonfun$apply$mcV$sp$1.apply(ForEachDStream.scala:40)
at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:399)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply$mcV$sp(ForEachDStream.scala:40)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:40)
at org.apache.spark.streaming.dstream.ForEachDStream$$anonfun$1.apply(ForEachDStream.scala:40)
at scala.util.Try$.apply(Try.scala:161)
at org.apache.spark.streaming.scheduler.Job.run(Job.scala:34)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply$mcV$sp(JobScheduler.scala:207)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:207)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:207)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:206)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:722)
Caused by: java.lang.NullPointerException
at org.apache.hadoop.fs.Path.<init>(Path.java:105)
at org.apache.hadoop.fs.Path.<init>(Path.java:94)
at org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.getDefaultWorkFile(FileOutputFormat.java:286)
at org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.getRecordWriter(TextOutputFormat.java:129)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1030)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1$$anonfun$12.apply(PairRDDFunctions.scala:1014)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
uj5u.com熱心網友回復：
樓主問題解決了嗎？我也遇到同樣的例外，現在還沒有解決。
uj5u.com熱心網友回復：
幫頂，我也想知道，最近也在學習這些uj5u.com熱心網友回復：
lz可以貼一下代碼嗎，我想在foreachrdd中寫但是沒效果，謝了轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/80937.html
標籤：Spark
上一篇：MapReduce問題
下一篇：內外網資料庫資料同步問題