Hi!
I get SocketTimeoutException when execute piece of code first time. When I re-run it - it works fine. The code just reads csv file and transforms it to dataframe. Any ideas abot the reason? import pyspark_csv as pycsv plaintext_rdd = sc.textFile(r'file:///c:\data\sample.csv') dataframe = pycsv.csvToDataFrame(sql, plaintext_rdd) csv file size is 50MB. I use Spark 1.6.1 on Windows locally. Regards, Sergey. Py4JJavaError Traceback (most recent call last)<ipython-input-72-d4227bb48a6a> in <module>() 2 plaintext_rdd = sc.textFile(r'file:///c:\data\sample.csv') 3 #plaintext_rdd.count()----> 4 dataframe = pycsv.csvToDataFrame(sql, plaintext_rdd) C:\Users\sergun\AppData\Local\Temp\spark-f4884acc-f8fd-416b-836b-2adebfd8e027\userFiles-02d6b0ee-569a-41ee-bd80-ccff2e09725e\pyspark_csv.py in csvToDataFrame(sqlCtx, rdd, columns, sep, parseDate) c:\spark\python\pyspark\rdd.py in first(self) 1313 ValueError: RDD is empty 1314 """-> 1315 rs = self.take(1) 1316 if rs: 1317 return rs[0] c:\spark\python\pyspark\rdd.py in take(self, num) 1295 1296 p = range(partsScanned, min(partsScanned + numPartsToTry, totalParts))-> 1297 res = self.context.runJob(self, takeUpToNumLeft, p) 1298 1299 items += res c:\spark\python\pyspark\context.py in runJob(self, rdd, partitionFunc, partitions, allowLocal) 937 # SparkContext#runJob. 938 mappedRDD = rdd.mapPartitions(partitionFunc)--> 939 port = self._jvm.PythonRDD.runJob(self._jsc.sc(), mappedRDD._jrdd, partitions) 940 return list(_load_from_socket(port, mappedRDD._jrdd_deserializer)) 941 c:\spark\python\lib\py4j-0.9-src.zip\py4j\java_gateway.py in __call__(self, *args) 811 answer = self.gateway_client.send_command(command) 812 return_value = get_return_value(--> 813 answer, self.gateway_client, self.target_id, self.name) 814 815 for temp_arg in temp_args: c:\spark\python\pyspark\sql\utils.py in deco(*a, **kw) 43 def deco(*a, **kw): 44 try:---> 45 return f(*a, **kw) 46 except py4j.protocol.Py4JJavaError as e: 47 s = e.java_exception.toString() c:\spark\python\lib\py4j-0.9-src.zip\py4j\protocol.py in get_return_value(answer, gateway_client, target_id, name) 306 raise Py4JJavaError( 307 "An error occurred while calling {0}{1}{2}.\n".--> 308 format(target_id, ".", name), value) 309 else: 310 raise Py4JError( Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.runJob. : 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): org.apache.spark.SparkException: Python worker did not connect back in time at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:136) at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:65) at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:134) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:101) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Caused by: java.net. : Accept timed out at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method) at java.net.DualStackPlainSocketImpl.socketAccept(DualStackPlainSocketImpl.java:135) at java.net.AbstractPlainSocketImpl.accept(AbstractPlainSocketImpl.java:409) at java.net.PlainSocketImpl.accept(PlainSocketImpl.java:199) at java.net.ServerSocket.implAccept(ServerSocket.java:545) at java.net.ServerSocket.accept(ServerSocket.java:513) at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:131) ... 12 more Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858) at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:393) at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala) at sun.reflect.GeneratedMethodAccessor51.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:497) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381) at py4j.Gateway.invoke(Gateway.java:259) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:209) at java.lang.Thread.run(Thread.java:745) Caused by: org.apache.spark.SparkException: Python worker did not connect back in time at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:136) at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:65) at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:134) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:101) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) ... 1 more Caused by: java.net.SocketTimeoutException: Accept timed out at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method) at java.net.DualStackPlainSocketImpl.socketAccept(DualStackPlainSocketImpl.java:135) at java.net.AbstractPlainSocketImpl.accept(AbstractPlainSocketImpl.java:409) at java.net.PlainSocketImpl.accept(PlainSocketImpl.java:199) at java.net.ServerSocket.implAccept(ServerSocket.java:545) at java.net.ServerSocket.accept(ServerSocket.java:513) at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:131) ... 12 more