我不知道问题出在哪里以及如何修复它.Spark版本是2.1.0,python版本是3.4.6。
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/__ / .__/\_,_/_/ /_/\_\ version 2.1.0
/_/
Using Python version 3.4.6 (default, Mar 9 2017 19:57:54)
SparkSession available as 'spark'.
##这是我编码为官方文档的命令
>>> input_data = sc.textFile('my python')
>>> input_data.count()
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/spark/python/pyspark/rdd.py", line 1041, in count
return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
File "/usr/local/spark/python/pyspark/rdd.py", line 1032, in sum
return self.mapPartitions(lambda x: [sum(x)]).fold(0, operator.add)
File "/usr/local/spark/python/pyspark/rdd.py", line 906, in fold
vals = self.mapPartitions(func).collect()
File "/usr/local/spark/python/pyspark/rdd.py", line 809, in collect
port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
File "/usr/local/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py", line 1133, in __call__
File "/usr/local/spark/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/usr/local/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py", line 319, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: java.net.ConnectException: Call From hadoop/192.168.81.129 to localhost:9000 failed on connection exception: java.net.ConnectException: 拒绝连接; For more details see: http://wiki.apache.org/hadoop/ConnectionRefused
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
at org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:792)
at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:732)
at org.apache.hadoop.ipc.Client.call(Client.java:1479)
at org.apache.hadoop.ipc.Client.call(Client.java:1412)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
at com.sun.proxy.$Proxy19.getFileInfo(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getFileInfo(ClientNamenodeProtocolTranslatorPB.java:771)
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 org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:191)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
at com.sun.proxy.$Proxy20.getFileInfo(Unknown Source)
at org.apache.hadoop.hdfs.DFSClient.getFileInfo(DFSClient.java:2108)
at org.apache.hadoop.hdfs.DistributedFileSystem$22.doCall(DistributedFileSystem.java:1305)
at org.apache.hadoop.hdfs.DistributedFileSystem$22.doCall(DistributedFileSystem.java:1301)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1301)
at org.apache.hadoop.fs.Globber.getFileStatus(Globber.java:57)
at org.apache.hadoop.fs.Globber.glob(Globber.java:252)
at org.apache.hadoop.fs.FileSystem.globStatus(FileSystem.java:1674)
at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:259)
at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:202)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
at org.apache.spark.api.python.PythonRDD.getPartitions(PythonRDD.scala:53)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
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: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: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:745)
Caused by: java.net.ConnectException: 拒绝连接
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:744)
at org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:206)
at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:531)
at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:495)
at org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:614)
at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:712)
at org.apache.hadoop.ipc.Client$Connection.access$2900(Client.java:375)
at org.apache.hadoop.ipc.Client.getConnection(Client.java:1528)
at org.apache.hadoop.ipc.Client.call(Client.java:1451)
... 56 more
>>>