I'm processing large spark dataframe in databricks and when I'm trying to write the final dataframe into csv format it gives me the following error: org.apache.spark.SparkException: Job aborted.
#Creating a data frame with entire date seuence for each user
df=pd.DataFrame({'transaction_date':dt_range2,'msno':msno1})
from pyspark.sql.types import *
mySchema1 = StructType([StructField("transaction_date", DateType(), True),
StructField("msno", StringType(), True)
])
#user wise date sequence conversion to pyspark data frame
df = spark.createDataFrame(df,schema=mySchema1)
#writing to a csv
df.write.csv("dbfs:/mnt/entracermount1/kkbox/Data_test.csv")
#full traceback
Py4JJavaError Traceback (most recent call last)
<command-3754966373119602> in <module>
----> 1 df.write.csv("dbfs:/mnt/entracermount1/kkbox/Data_test.csv")
/databricks/spark/python/pyspark/sql/readwriter.py in csv(self, path, mode, compression, sep, quote, escape, header, nullValue, escapeQuotes, quoteAll, dateFormat, timestampFormat, ignoreLeadingWhiteSpace, ignoreTrailingWhiteSpace, charToEscapeQuoteEscaping, encoding, emptyValue)
930 charToEscapeQuoteEscaping=charToEscapeQuoteEscaping,
931 encoding=encoding, emptyValue=emptyValue)
--> 932 self._jwrite.csv(path)
933
934 @since(1.5)
/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.py 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 o1459.csv.
: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:201)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:192)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:108)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:106)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:126)
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$$anonfun$executeQuery$5.apply(SparkPlan.scala:187)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:183)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:134)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:113)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:113)
at org.apache.spark.sql.DataFrameWriter$$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.csv(DataFrameWriter.scala:698)
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: Serialized task 64:0 was 614833921 bytes, which exceeds max allowed: spark.rpc.message.maxSize (268435456 bytes). Consider increasing spark.rpc.message.maxSize or using broadcast variables for large values.
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:2360)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2348)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2347)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2347)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:1101)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:1101)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1101)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2579)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2527)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2515)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:896)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2280)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:170)
... 34 more
Even I have tried to save as parquet file and it is giving the same error. If you could suggest any solution for this it will be great. Thanks.
Serialized task 64:0 was 614833921 bytes, which exceeds max allowed: spark.rpc.message.maxSize (268435456 bytes). Consider increasing spark.rpc.message.maxSize or using broadcast variables for large values- OneCricketeer