我遇到了一个不寻常的情况，即在spark-submit中运行这段代码失败，但在运行pyspark shell时会按预期工作（'pyspark'）
这是代码段：
from pyspark import SparkContext
from pyspark.sql import SQLContext
from pyspark.sql.types import *
sc = SparkContext('yarn-client', 'pyspark')
sqlContext = SQLContext(sc)
sqlContext.registerFunction("stringLengthString", lambda x: len(x), IntegerType())
sqlContext.sql("SELECT stringLengthString('test')").collect()
我得到的错误是：
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 418, in loads
return pickle.loads(obj, encoding=encoding)
AttributeError: Can't get attribute '_create_row_inbound_converter' on <module 'pyspark.sql.types' from '/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/sql/types.py'>
有关如何解决失败的任何建议？
完整追踪：
16/01/14 19:59:31 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0, 10.0.0.9): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 139, in load_stream
yield self._read_with_length(stream)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 164, in _read_with_length
return self.loads(obj)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 418, in loads
return pickle.loads(obj, encoding=encoding)
AttributeError: Can't get attribute '_create_row_inbound_converter' on <module 'pyspark.sql.types' from '/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/sql/types.py'>
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.sql.execution.BatchPythonEvaluation$$anonfun$doExecute$1.apply(python.scala:398)
at org.apache.spark.sql.execution.BatchPythonEvaluation$$anonfun$doExecute$1.apply(python.scala:363)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
16/01/14 19:59:36 ERROR TaskSetManager: Task 0 in stage 0.0 failed 4 times; aborting job
Traceback (most recent call last):
File "/home/azureuser/test.py", line 9, in <module>
sqlContext.sql("SELECT stringLengthString('test')").collect()
File "/usr/hdp/current/spark/python/lib/pyspark.zip/pyspark/sql/dataframe.py", line 280, in collect
File "/usr/hdp/current/spark/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py", line 813, in __call__
File "/usr/hdp/current/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 45, in deco
File "/usr/hdp/current/spark/python/lib/py4j-0.9-src.zip/py4j/protocol.py", line 308, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o31.collectToPython.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3, 10.0.0.9): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 139, in load_stream
yield self._read_with_length(stream)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 164, in _read_with_length
return self.loads(obj)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 418, in loads
return pickle.loads(obj, encoding=encoding)
AttributeError: Can't get attribute '_create_row_inbound_converter' on <module 'pyspark.sql.types' from '/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/sql/types.py'>
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.sql.execution.BatchPythonEvaluation$$anonfun$doExecute$1.apply(python.scala:398)
at org.apache.spark.sql.execution.BatchPythonEvaluation$$anonfun$doExecute$1.apply(python.scala:363)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$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.SparkContext.runJob(SparkContext.scala:1929)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:927)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.collect(RDD.scala:926)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405)
at org.apache.spark.sql.DataFrame$$anonfun$collectToPython$1.apply$mcI$sp(DataFrame.scala:1778)
at org.apache.spark.sql.DataFrame$$anonfun$collectToPython$1.apply(DataFrame.scala:1778)
at org.apache.spark.sql.DataFrame$$anonfun$collectToPython$1.apply(DataFrame.scala:1778)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2125)
at org.apache.spark.sql.DataFrame.collectToPython(DataFrame.scala:1777)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
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.api.python.PythonException: Traceback (most recent call last):
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 139, in load_stream
yield self._read_with_length(stream)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 164, in _read_with_length
return self.loads(obj)
File "/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/serializers.py", line 418, in loads
return pickle.loads(obj, encoding=encoding)
AttributeError: Can't get attribute '_create_row_inbound_converter' on <module 'pyspark.sql.types' from '/usr/hdp/current/spark-client/python/lib/pyspark.zip/pyspark/sql/types.py'>
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.sql.execution.BatchPythonEvaluation$$anonfun$doExecute$1.apply(python.scala:398)
at org.apache.spark.sql.execution.BatchPythonEvaluation$$anonfun$doExecute$1.apply(python.scala:363)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
... 1 more