嗨，伙计们，我在Drosream写在镶木地板文件时有问题。我有这样的结构
DStream.foreachRDD(
rdd => {
rdd.write.parquet("somepath/1.parquet")
}
)
}
它工作正常但在某些情况下我得到错误和镶嵌文件创建没有任何信息
这是我的日志信息：
15/07/22 10:14:09 ERROR InsertIntoHadoopFsRelation: Aborting job.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): java.lang.ClassCastException: org.apache.spark.rdd.UnionPartition cannot be cast to org.apache.spark.rdd.ParallelCollectionPartition
at org.apache.spark.rdd.ParallelCollectionRDD.compute(ParallelCollectionRDD.scala:102)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1266)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1257)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1256)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1256)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1450)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1411)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
15/07/22 10:14:09 ERROR DefaultWriterContainer: Job job_201507221014_0000 aborted.
15/07/22 10:14:09 ERROR JobScheduler: Error running job streaming job 1437538446000 ms.0
org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.sources.InsertIntoHadoopFsRelation.insert(commands.scala:138)
at org.apache.spark.sql.sources.InsertIntoHadoopFsRelation.run(commands.scala:114)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:68)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:87)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:939)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:939)
at org.apache.spark.sql.sources.ResolvedDataSource$.apply(ddl.scala:332)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:144)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:135)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:281)
at kafkaStreamReader$$anonfun$main$1.apply(kafkaStreamReader.scala:57)
at kafkaStreamReader$$anonfun$main$1.apply(kafkaStreamReader.scala:51)
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$sp(JobScheduler.scala:193)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:193)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:193)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:192)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): java.lang.ClassCastException: org.apache.spark.rdd.UnionPartition cannot be cast to org.apache.spark.rdd.ParallelCollectionPartition
at org.apache.spark.rdd.ParallelCollectionRDD.compute(ParallelCollectionRDD.scala:102)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1266)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1257)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1256)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1256)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1450)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1411)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
Exception in thread "main" org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.sources.InsertIntoHadoopFsRelation.insert(commands.scala:138)
at org.apache.spark.sql.sources.InsertIntoHadoopFsRelation.run(commands.scala:114)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:68)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:87)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:939)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:939)
at org.apache.spark.sql.sources.ResolvedDataSource$.apply(ddl.scala:332)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:144)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:135)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:281)
at kafkaStreamReader$$anonfun$main$1.apply(kafkaStreamReader.scala:57)
at kafkaStreamReader$$anonfun$main$1.apply(kafkaStreamReader.scala:51)
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$sp(JobScheduler.scala:193)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:193)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler$$anonfun$run$1.apply(JobScheduler.scala:193)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:192)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): java.lang.ClassCastException: org.apache.spark.rdd.UnionPartition cannot be cast to org.apache.spark.rdd.ParallelCollectionPartition
at org.apache.spark.rdd.ParallelCollectionRDD.compute(ParallelCollectionRDD.scala:102)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1266)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1257)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1256)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1256)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1450)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1411)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
但正如我在某些时候已经说过所有确定的镶木地板都是根据收到的信息创建的。另外我注意到，如果我将在这部分代码中进行大量计算
rdd => {
**here**
}
错误数量会增加。