我正在尝试执行以下操作：
我尝试使用数据帧，但是在这种情况下，由于某些行的大小超过2GB，我最终遇到了OOM错误。
在作业运行期间，当我尝试将数据帧写为实木复合地板时，运行失败并出现以下错误：
/databricks/spark/python/pyspark/sql/readwriter.pyc in parquet(self, path, mode, partitionBy, compression)
837 self.partitionBy(partitionBy)
838 self._set_opts(compression=compression)
--> 839 self._jwrite.parquet(path)
840
841 @since(1.6)
/databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:
/databricks/spark/python/pyspark/sql/utils.pyc in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o589402.parquet.
: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:198)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:192)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:110)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:108)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:128)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:146)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:134)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$5.apply(SparkPlan.scala:187)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:183)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:134)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:114)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:114)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:710)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:710)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withCustomExecutionEnv$1.apply(SQLExecution.scala:111)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:240)
at org.apache.spark.sql.execution.SQLExecution$.withCustomExecutionEnv(SQLExecution.scala:97)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:170)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:710)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:306)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:292)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:235)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:600)
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:380)
at py4j.Gateway.invoke(Gateway.java:295)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:251)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 29 in stage 40.0 failed 4 times, most recent failure: Lost task 29.3 in stage 40.0 (TID 3394, 10.46.190.16, executor 26): ExecutorLostFailure (executor 26 exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 173204 ms
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:2355)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2343)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2342)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2342)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:1096)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:1096)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1096)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2574)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2522)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2510)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:893)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2243)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:167)
... 34 more
我试图找出可能导致此故障的原因？似乎是由于执行程序之一没有发出心跳响应，但令我感到惊讶的是，因为数据帧开始时并没有那么大。任何帮助将不胜感激。
如果我的数据框很小，那么将其写入s3便没有问题