我的Spark作业在写入实木复合地板文件时被中止。仅当我尝试在大型数据集上运行时才会发生。在精简数据集上运行时，作业将完成。
我一直在浏览日志，但是找不到任何原因导致此作业失败。也许有人可以给我一个提示，在哪里寻找更多的线索。这是作业的输出：
INFO:de_etl.smart_meters.data_processing:Save intermediate to "smart_meters_full_reload/stage1"
18/07/14 13:38:24 WARN AzureFileSystemThreadPoolExecutor: Disabling threads for Delete operation as thread count 0 is <= 1
18/07/14 15:48:50 WARN AzureFileSystemThreadPoolExecutor: Disabling threads for Delete operation as thread count 0 is <= 1
18/07/14 15:48:51 WARN NativeAzureFileSystem: Attempt to delete non-existent file user/a7adu31/.sparkStaging/application_1531498233339_0285/__spark_conf__.zip
18/07/14 15:48:51 WARN NativeAzureFileSystem: Attempt to delete non-existent file user/a7adu31/.sparkStaging/application_1531498233339_0285/mssql-jdbc-6.4.0.jre8.jar
18/07/14 15:48:51 WARN NativeAzureFileSystem: Attempt to delete non-existent file user/a7adu31/.sparkStaging/application_1531498233339_0285/py4j-0.10.4-src.zip
18/07/14 15:48:52 WARN NativeAzureFileSystem: Attempt to delete non-existent file user/a7adu31/.sparkStaging/application_1531498233339_0285/pyspark.zip
18/07/14 15:48:52 WARN NativeAzureFileSystem: Attempt to delete non-existent file user/a7adu31/.sparkStaging/application_1531498233339_0285/spark-avro_2.11-3.2.0.jar
18/07/14 15:48:52 ERROR YarnClientSchedulerBackend: Yarn application has already exited with state FINISHED!
18/07/14 15:48:54 WARN BlockManagerMasterEndpoint: No more replicas available for rdd_7_2 !
18/07/14 15:48:54 WARN BlockManagerMasterEndpoint: No more replicas available for rdd_7_109 !
...更多...
18/07/14 15:48:55 WARN BlockManagerMasterEndpoint: No more replicas available for rdd_7_64 !
18/07/14 15:49:00 ERROR FileFormatWriter: Aborting job null.
org.apache.spark.SparkException: Job 4 cancelled because SparkContext was shut down
at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:820)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:818)
at scala.collection.mutable.HashSet.foreach(HashSet.scala:78)
at org.apache.spark.scheduler.DAGScheduler.cleanUpAfterSchedulerStop(DAGScheduler.scala:818)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onStop(DAGScheduler.scala:1750)
at org.apache.spark.util.EventLoop.stop(EventLoop.scala:83)
at org.apache.spark.scheduler.DAGScheduler.stop(DAGScheduler.scala:1669)
at org.apache.spark.SparkContext$$anonfun$stop$8.apply$mcV$sp(SparkContext.scala:1928)
at org.apache.spark.util.Utils$.tryLogNonFatalError(Utils.scala:1317)
at org.apache.spark.SparkContext.stop(SparkContext.scala:1927)
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend$MonitorThread.run(YarnClientSchedulerBackend.scala:108)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2029)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:186)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:166)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:166)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:166)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:145)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.execution.datasources.DataSource.writeInFileFormat(DataSource.scala:437)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:473)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:50)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:609)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:217)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:508)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
18/07/14 15:49:00 WARN AzureFileSystemThreadPoolExecutor: Disabling threads for Delete operation as thread count 0 is <= 1
Traceback (most recent call last):
File "reload_smart_meter_validated_base_linear.py", line 3, in <module>
smart_meters.data_processing.full_reload()
File "/datadisk/home/a7adu31/src/de-etl-smart-meters/de_etl/smart_meters/data_processing.py", line 91, in full_reload
stage2_tmp_path="smart_meters_full_reload/stage2")
File "/datadisk/home/a7adu31/src/de-etl-smart-meters/de_etl/smart_meters/data_processing.py", line 121, in reload
output_path=stage1_tmp_path)
File "/datadisk/home/a7adu31/src/de-etl-smart-meters/de_etl/smart_meters/data_processing.py", line 174, in reload_stage1
sm_mandates_incl.write.parquet(output_path, mode='overwrite')
File "/usr/hdp/current/spark2-client/python/pyspark/sql/readwriter.py", line 691, in parquet
self._jwrite.parquet(path)
File "/usr/hdp/current/spark2-client/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py", line 1133, in __call__
File "/usr/hdp/current/spark2-client/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/usr/hdp/current/spark2-client/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py", line 319, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o564.parquet.
: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:213)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:166)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:166)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:166)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:145)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.execution.datasources.DataSource.writeInFileFormat(DataSource.scala:437)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:473)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:50)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:609)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:217)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:508)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job 4 cancelled because SparkContext was shut down
at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:820)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:818)
at scala.collection.mutable.HashSet.foreach(HashSet.scala:78)
at org.apache.spark.scheduler.DAGScheduler.cleanUpAfterSchedulerStop(DAGScheduler.scala:818)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onStop(DAGScheduler.scala:1750)
at org.apache.spark.util.EventLoop.stop(EventLoop.scala:83)
at org.apache.spark.scheduler.DAGScheduler.stop(DAGScheduler.scala:1669)
at org.apache.spark.SparkContext$$anonfun$stop$8.apply$mcV$sp(SparkContext.scala:1928)
at org.apache.spark.util.Utils$.tryLogNonFatalError(Utils.scala:1317)
at org.apache.spark.SparkContext.stop(SparkContext.scala:1927)
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend$MonitorThread.run(YarnClientSchedulerBackend.scala:108)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2029)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:186)
... 45 more