I have set up a spark cluster and all the nodes have access to network shared storage where they can access a file to read. I am running this in a python jupyter notebook. It was working a few days ago, and now it stopped working but I'm not sure why, or what I have changed.
I have tried restarting the nodes and master.
I have also tried copying the csv file to a new directory and pointing the spark.read there, but it still gives the same error.
When I delete the csv file, it gives a much shorter error saying 'File not found'
Any help would be greatly appreciated.
This is my code:
from pyspark.sql import SparkSession
from pyspark.conf import SparkConf
spark = SparkSession.builder \
.master("spark://IP:PORT") \
.appName("app_1") \
.config(conf=SparkConf()) \
.getOrCreate()
df = spark.read.csv("/nas/file123.csv")
string1 = df.rdd.map(lambda x: x.column1).collect()
However, I get this error:
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-2-12bd938122cd> in <module>()
29
30
---> 31 string1 = df.rdd.map(lambda x: x.column1).collect()
32
33
/home/hjk/Downloads/spark-2.1.0-bin-hadoop2.7/python/pyspark/rdd.pyc in collect(self)
807 """
808 with SCCallSiteSync(self.context) as css:
--> 809 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
810 return list(_load_from_socket(port, self._jrdd_deserializer))
811
/usr/local/lib/python2.7/dist-packages/py4j/java_gateway.pyc in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/home/hjk/Downloads/spark-2.1.0-bin-hadoop2.7/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()
/usr/local/lib/python2.7/dist-packages/py4j/protocol.pyc in get_return_value(answer, gateway_client, target_id, name)
317 raise Py4JJavaError(
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
321 raise Py4JError(
Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 4 in stage 3.0 failed 4 times, most recent failure: Lost task 4.3 in stage 3.0 (TID 37, executor 2): java.io.FileNotFoundException: File file:/nas/file123.csv does not exist
It is possible the underlying files have been updated. You can explicitly invalidate the cache in Spark by running 'REFRESH TABLE tableName' command in SQL or by recreating the Dataset/DataFrame involved.
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:157)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:102)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.hasNext(SerDeUtil.scala:117)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.foreach(SerDeUtil.scala:112)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:504)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:328)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1951)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:269)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1931)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1944)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1958)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:935)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.collect(RDD.scala:934)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:453)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.FileNotFoundException: File file:/nas/file123.csv does not exist
It is possible the underlying files have been updated. You can explicitly invalidate the cache in Spark by running 'REFRESH TABLE tableName' command in SQL or by recreating the Dataset/DataFrame involved.
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:157)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:102)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.hasNext(SerDeUtil.scala:117)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.foreach(SerDeUtil.scala:112)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:504)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:328)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1951)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:269)
