0
我在外部服務器上運行pyspark時遇到問題。運行pyspark會導致多個錯誤，而我似乎無法確定如何解決它們。這裏的打印輸出：運行Pyspark的多個錯誤
[[email protected] ~]# pyspark
Python 3.6.0 |Anaconda 4.3.1 (64-bit)| (default, Dec 23 2016, 12:22:00)
[GCC 4.4.7 20120313 (Red Hat 4.4.7-1)] on linux
Type "help", "copyright", "credits" or "license" for more information.
Using Spark's default log4j profile: org/apache/spark/log4j-
defaults.properties
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use
setLogLevel(newLevel).
17/05/26 21:19:10 WARN NativeCodeLoader: Unable to load native-hadoop
library for your platform... using builtin-java classes where applicable
17/05/26 21:19:10 WARN SparkContext: Another SparkContext is being
constructed (or threw an exception in its constructor). This may indicate
an error, since only one SparkContext may be running in this JVM (see SPARK-
2243). The other SparkContext was created at:
org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
java.lang.reflect.Constructor.newInstance(Constructor.java:423)
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:247)
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
py4j.Gateway.invoke(Gateway.java:236)
py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)
py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)
py4j.GatewayConnection.run(GatewayConnection.java:214)
java.lang.Thread.run(Thread.java:748)
Traceback (most recent call last):File "/usr/local/spark/spark/python/pyspark/shell.py", line 43, in <module>
spark = SparkSession.builder\
File "/usr/local/spark/spark/python/pyspark/sql/session.py", line 169, in getOrCreate
sc = SparkContext.getOrCreate(sparkConf)
File "/usr/local/spark/spark/python/pyspark/context.py", line 310, in getOrCreate
SparkContext(conf=conf or SparkConf())
File "/usr/local/spark/spark/python/pyspark/context.py", line 118, in __init__
conf, jsc, profiler_cls)
File "/usr/local/spark/spark/python/pyspark/context.py", line 182, in _do_init
self._jsc = jsc or self._initialize_context(self._conf._jconf)
File "/usr/local/spark/spark/python/pyspark/context.py", line 249, in _initialize_context
return self._jvm.JavaSparkContext(jconf)
File "/usr/local/spark/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py", line 1401, in __call__
File "/usr/local/spark/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 None.org.apache.spark.api.java.JavaSparkContext.
: java.lang.ExceptionInInitializerError
at org.apache.spark.SparkContext.<init>(SparkContext.scala:397)
at org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:247)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:236)
at py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)
at py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.net.UnknownHostException: spark-master: spark-master: Temporary failure in name resolution
at java.net.InetAddress.getLocalHost(InetAddress.java:1505)
at org.apache.spark.util.Utils$.findLocalInetAddress(Utils.scala:870)
at org.apache.spark.util.Utils$.org$apache$spark$util$Utils$$localIpAddress$lzycompute(Utils.scala:863)
at org.apache.spark.util.Utils$.org$apache$spark$util$Utils$$localIpAddress(Utils.scala:863)
at org.apache.spark.util.Utils$$anonfun$localHostName$1.apply(Utils.scala:920)
at org.apache.spark.util.Utils$$anonfun$localHostName$1.apply(Utils.scala:920)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.util.Utils$.localHostName(Utils.scala:920)
at org.apache.spark.internal.config.package$.<init>(package.scala:189)
at org.apache.spark.internal.config.package$.<clinit>(package.scala)
... 13 more
Caused by: java.net.UnknownHostException: spark-master: Temporary failure in name resolution
at java.net.Inet6AddressImpl.lookupAllHostAddr(Native Method)
at java.net.InetAddress$2.lookupAllHostAddr(InetAddress.java:928)
at java.net.InetAddress.getAddressesFromNameService(InetAddress.java:1323)
at java.net.InetAddress.getLocalHost(InetAddress.java:1500)
... 22 more
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/spark/spark/python/pyspark/shell.py", line 47, in <module>
spark = SparkSession.builder.getOrCreate()
File "/usr/local/spark/spark/python/pyspark/sql/session.py", line 169, in getOrCreate
sc = SparkContext.getOrCreate(sparkConf)
File "/usr/local/spark/spark/python/pyspark/context.py", line 310, in getOrCreate
SparkContext(conf=conf or SparkConf())
File "/usr/local/spark/spark/python/pyspark/context.py", line 118, in __init__
conf, jsc, profiler_cls)
File "/usr/local/spark/spark/python/pyspark/context.py", line 182, in _do_init
self._jsc = jsc or self._initialize_context(self._conf._jconf)
File "/usr/local/spark/spark/python/pyspark/context.py", line 249, in _initialize_context
return self._jvm.JavaSparkContext(jconf)
File "/usr/local/spark/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py", line 1401, in __call__
File "/usr/local/spark/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py", line 319, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling None.org.apache.spark.api.java.JavaSparkContext.
: java.lang.NoClassDefFoundError: Could not initialize class org.apache.spark.internal.config.package$
at org.apache.spark.SparkContext.<init>(SparkContext.scala:397)
at org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:247)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:236)
at py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)
at py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
>>>
任何幫助將不勝感激！
編輯：在其他機器上，我試圖運行這個，我得到了一組類似的錯誤，但沒有UnknownHostException。
pyspark
Python 2.7.5 (default, Nov 20 2015, 02:00:19)
[GCC 4.8.5 20150623 (Red Hat 4.8.5-4)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
17/05/30 13:12:35 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
17/05/30 13:12:35 WARN SparkContext: Another SparkContext is being constructed (or threw an exception in its constructor). This may indicate an error, since only one SparkContext may be running in this JVM (see SPARK-2243). The other SparkContext was created at:
org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
java.lang.reflect.Constructor.newInstance(Constructor.java:423)
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:247)
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
py4j.Gateway.invoke(Gateway.java:236)
py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)
py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)
py4j.GatewayConnection.run(GatewayConnection.java:214)
java.lang.Thread.run(Thread.java:748)
Traceback (most recent call last):
File "/usr/local/spark/python/pyspark/shell.py", line 47, in <module>
spark = SparkSession.builder.getOrCreate()
File "/usr/local/spark/python/pyspark/sql/session.py", line 169, in getOrCreate
sc = SparkContext.getOrCreate(sparkConf)
File "/usr/local/spark/python/pyspark/context.py", line 310, in getOrCreate
SparkContext(conf=conf or SparkConf())
File "/usr/local/spark/python/pyspark/context.py", line 118, in __init__
conf, jsc, profiler_cls)
File "/usr/local/spark/python/pyspark/context.py", line 182, in _do_init
self._jsc = jsc or self._initialize_context(self._conf._jconf)
File "/usr/local/spark/python/pyspark/context.py", line 249, in _initialize_context
return self._jvm.JavaSparkContext(jconf)
File "/usr/local/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py", line 1401, in __call__
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 None.org.apache.spark.api.java.JavaSparkContext.
: java.lang.NoClassDefFoundError: Could not initialize class org.apache.spark.internal.config.package$
at org.apache.spark.SparkContext.<init>(SparkContext.scala:397)
at org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:247)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:236)
at py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)
at py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
>>>
'UnknownHostException：spark-master：spark-master' - 看起來像您配置的主url（在Spark配置中？）指向'spark-master'，它不會解析爲IP地址。 – zero323
@ zero323謝謝！但這似乎並不是全部問題。在其他機器上，我試圖運行它，我得到了一組類似的錯誤，但沒有UnknownHostException： –
更新：修復主機問題修復了大部分錯誤。常規火花外殼現在正在運行。 Pyspark仍然存在一些問題，將作爲單獨的問題發佈。 –