Created 01-19-2016 07:53 AM
when i use spark-submit to run some code, the spark does not work, the error follows:
Traceback (most recent call last): File "/home/lizhen/test.py", line 27, in <module> abc = raw_data.count() File "/usr/hdp/2.3.4.0-3485/spark/python/lib/pyspark.zip/pyspark/rdd.py", line 1006, in count File "/usr/hdp/2.3.4.0-3485/spark/python/lib/pyspark.zip/pyspark/rdd.py", line 997, in sum File "/usr/hdp/2.3.4.0-3485/spark/python/lib/pyspark.zip/pyspark/rdd.py", line 871, in fold File "/usr/hdp/2.3.4.0-3485/spark/python/lib/pyspark.zip/pyspark/rdd.py", line 773, in collect File "/usr/hdp/2.3.4.0-3485/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py", line 538, in __call__ File "/usr/hdp/2.3.4.0-3485/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 z:org.apache.spark.api.python.PythonRDD.collectAndServe. : java.io.IOException: java.net.ConnectException: Connection refused at org.apache.hadoop.crypto.key.kms.KMSClientProvider.addDelegationTokens(KMSClientProvider.java:888) at org.apache.hadoop.crypto.key.KeyProviderDelegationTokenExtension.addDelegationTokens(KeyProviderDelegationTokenExtension.java:86) at org.apache.hadoop.hdfs.DistributedFileSystem.addDelegationTokens(DistributedFileSystem.java:2243) at org.apache.hadoop.mapreduce.security.TokenCache.obtainTokensForNamenodesInternal(TokenCache.java:121) at org.apache.hadoop.mapreduce.security.TokenCache.obtainTokensForNamenodesInternal(TokenCache.java:100) at org.apache.hadoop.mapreduce.security.TokenCache.obtainTokensForNamenodes(TokenCache.java:80) at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:206) at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315) at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:207) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) at org.apache.spark.api.python.PythonRDD.getPartitions(PythonRDD.scala:58) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1921) at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:909) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108) at org.apache.spark.rdd.RDD.withScope(RDD.scala:310) at org.apache.spark.rdd.RDD.collect(RDD.scala:908) at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405) at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) 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: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:745) Caused by: java.net.ConnectException: Connection refused at java.net.PlainSocketImpl.socketConnect(Native Method) at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:350) at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:206) at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:188) at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392) at java.net.Socket.connect(Socket.java:589) at sun.net.NetworkClient.doConnect(NetworkClient.java:175) at sun.net.www.http.HttpClient.openServer(HttpClient.java:432) at sun.net.www.http.HttpClient.openServer(HttpClient.java:527) at sun.net.www.http.HttpClient.<init>(HttpClient.java:211) at sun.net.www.http.HttpClient.New(HttpClient.java:308) at sun.net.www.http.HttpClient.New(HttpClient.java:326) at sun.net.www.protocol.http.HttpURLConnection.getNewHttpClient(HttpURLConnection.java:1169) at sun.net.www.protocol.http.HttpURLConnection.plainConnect0(HttpURLConnection.java:1105) at sun.net.www.protocol.http.HttpURLConnection.plainConnect(HttpURLConnection.java:999) at sun.net.www.protocol.http.HttpURLConnection.connect(HttpURLConnection.java:933) at org.apache.hadoop.security.authentication.client.KerberosAuthenticator.authenticate(KerberosAuthenticator.java:190) at org.apache.hadoop.security.token.delegation.web.DelegationTokenAuthenticator.authenticate(DelegationTokenAuthenticator.java:128) at org.apache.hadoop.security.authentication.client.AuthenticatedURL.openConnection(AuthenticatedURL.java:215) at org.apache.hadoop.security.token.delegation.web.DelegationTokenAuthenticator.doDelegationTokenOperation(DelegationTokenAuthenticator.java:285) at org.apache.hadoop.security.token.delegation.web.DelegationTokenAuthenticator.getDelegationToken(DelegationTokenAuthenticator.java:166) at org.apache.hadoop.security.token.delegation.web.DelegationTokenAuthenticatedURL.getDelegationToken(DelegationTokenAuthenticatedURL.java:371) at org.apache.hadoop.crypto.key.kms.KMSClientProvider$2.run(KMSClientProvider.java:875) at org.apache.hadoop.crypto.key.kms.KMSClientProvider$2.run(KMSClientProvider.java:870) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:422) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657) at org.apache.hadoop.crypto.key.kms.KMSClientProvider.addDelegationTokens(KMSClientProvider.java:870) ... 41 more
Created 01-19-2016 09:46 PM
Connection refused invariably means "there's no service at the destination". Here I'd assume that either the configuration of the KMS is wrong (it's URL), or its not currently running.
Created 01-19-2016 08:22 AM
when i test use the mapreduce example, the error also appear
Created 01-19-2016 09:12 AM
Do your service checks (Spark, HDFS, Yarn, Mapred etc) work? If they do, have you acquired a ticket, what does "klist" say? If klist lists nothing you have to acquire a ticket using kinit, either as an end-user, or as spark or hdfs service user. Try first to list hdfs: "hdfs dfs -ls /", does it work?
Created 01-19-2016 09:46 PM
Connection refused invariably means "there's no service at the destination". Here I'd assume that either the configuration of the KMS is wrong (it's URL), or its not currently running.
Created 01-20-2016 06:46 AM
yes,you are right. after i install the kms service ,it works!