spark-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Lau, Kawing (GE Global Research)" <kawing....@ge.com>
Subject Error running rdd.first on hadoop
Date Thu, 12 Mar 2015 23:45:41 GMT
Hi 

I was running with spark-1.3.0-snapshot
rdd = sc.textFile("hdfs://X.X.X.X/data")
rdd.first() 


Then I got this error:
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/pyspark/rdd.py", line 1243, in first
    rs = self.take(1)
  File "/pyspark/rdd.py", line 1195, in take
    totalParts = self._jrdd.partitions().size()
  File "/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py", line
538, in __call__
  File "/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py", line
300, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling
o28.partitions.
: java.net.ConnectException: Call From etl1.gphd.local/X.X.X.X to
etl1.gphd.local:8020 failed on connection exception:
java.net.ConnectException: Connection refused; For more details see:
http://wiki.apache.org/hadoop/ConnectionRefused
	at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
	at 
sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAcce
ssorImpl.java:57)
	at 
sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstru
ctorAccessorImpl.java:45)
	at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
	at org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:783)
	at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:730)
	at org.apache.hadoop.ipc.Client.call(Client.java:1351)
	at org.apache.hadoop.ipc.Client.call(Client.java:1300)
	at 
org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.ja
va:206)
	at com.sun.proxy.$Proxy13.getDelegationToken(Unknown Source)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at 
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:5
7)
	at 
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImp
l.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at 
org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocat
ionHandler.java:186)
	at 
org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHan
dler.java:102)
	at com.sun.proxy.$Proxy13.getDelegationToken(Unknown Source)
	at 
org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getDel
egationToken(ClientNamenodeProtocolTranslatorPB.java:805)
	at org.apache.hadoop.hdfs.DFSClient.getDelegationToken(DFSClient.java:847)
	at 
org.apache.hadoop.hdfs.DistributedFileSystem.getDelegationToken(Distributed
FileSystem.java:1318)
	at 
org.apache.hadoop.fs.FileSystem.collectDelegationTokens(FileSystem.java:526
)
	at 
org.apache.hadoop.fs.FileSystem.addDelegationTokens(FileSystem.java:504)
	at 
org.apache.hadoop.mapreduce.security.TokenCache.obtainTokensForNamenodesInt
ernal(TokenCache.java:121)
	at 
org.apache.hadoop.mapreduce.security.TokenCache.obtainTokensForNamenodesInt
ernal(TokenCache.java:100)
	at 
org.apache.hadoop.mapreduce.security.TokenCache.obtainTokensForNamenodes(To
kenCache.java:80)
	at 
org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:20
2)
	at 
org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:270
)
	at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:203)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
	at 
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:
32)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
	at 
org.apache.spark.api.java.JavaRDDLike$class.partitions(JavaRDDLike.scala:56
)
	at org.apache.spark.api.java.JavaRDD.partitions(JavaRDD.scala:32)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at 
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:5
7)
	at 
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImp
l.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:379)
	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:207)
	at java.lang.Thread.run(Thread.java:744)
Caused by: java.net.ConnectException: Connection refused
	at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
	at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:735)
	at 
org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:
206)
	at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:529)
	at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:493)
	at 
org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:547)
	at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:642)
	at org.apache.hadoop.ipc.Client$Connection.access$2600(Client.java:314)
	at org.apache.hadoop.ipc.Client.getConnection(Client.java:1399)
	at org.apache.hadoop.ipc.Client.call(Client.java:1318)
	... 43 more

Anyone has an idea how to solve this?

Sherry


---------------------------------------------------------------------
To unsubscribe, e-mail: user-unsubscribe@spark.apache.org
For additional commands, e-mail: user-help@spark.apache.org


Mime
View raw message