大家好，我在 kerberos 环境中运行 Spark(2.4.4)，我编写了一段代码来通过 Spark 查询 Hive 表。我也在spark-submit命令中执行kinit，但我仍然面临
java.io.IOException:
org.apache.hadoop.security.AccessControlException: Client cannot authenticate via:[TOKEN, KERBEROS];
这是我的代码:-
@transient lazy val spark: SparkSession = getSparkSession()
def getSparkSession(): SparkSession = {
log.info("Creating spark session")
var sparkBuilder: SparkSession.Builder = SparkSession.builder().
master("local[*]").
appName("Query Hive Via Spark").
config("hive.exec.scratchdir", "/tmp/hive").enableHiveSupport().
config("hive.exec.dynamic.partition", "true").
config("hive.exec.dynamic.partition.mode", "nonstrict").
config("hive.exec.max.dynamic.partitions", "1000")
@transient lazy val spark: SparkSession = sparkBuilder.getOrCreate()
registerUdfs(spark)
spark.sparkContext.setLogLevel(logLevel)
spark
}
通过 Spark Sql 访问 Hive 表的代码。
val resultDF= spark.sql(s"SELECT count(*) AS cnt FROM brl_in_cash.cash_in_incoming_data WHERE insert_date='20200821'")
resultDF.printSchema()
resultDF.show(false)
我正在执行 Spark-submit 的 shell 脚本，其中我正在执行 kinit 并传递 --principal $KERBEROS_PRINCIPAL --keytab $KERBEROS_KEYTAB 。
Spark-提交命令:-
spark-submit --master yarn --deploy-mode cluster \
--verbose \
--name ${appName} \
--principal $KERBEROS_PRINCIPAL \
--keytab $KERBEROS_KEYTAB \
--driver-memory 4g \
--executor-memory 4g \
--executor-cores 2 \
--files ${hiveSite.xml} \
--conf spark.hadoop.yarn.timeline-service.enabled=false \
--conf spark.hadoop.yarn.client.failover-proxy-provider=org.apache.hadoop.yarn.client.ConfiguredRMFailoverProxyProvider \
--conf spark.security.credentials.EsServiceCredentialProvider.enabled=false \
--class com.dpk.hive.HiveViaSpark "${jarPath}"
错误日志:-
20/08/26 13:34:17 INFO TezClient: Failed to retrieve AM Status via proxy
com.google.protobuf.ServiceException: java.io.IOException: Failed on local exception: java.io.IOException: org.apache.hadoop.security.AccessControlException: Client cannot authenticate via:[TOKEN, KERBEROS]; Host Details : local host is: "dfghcv012.global.xyz.com/10.7.1.52"; destination host is: "dfghcv013.global.xyz.com":43890;
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:243)
at com.sun.proxy.$Proxy36.getAMStatus(Unknown Source)
at org.apache.tez.client.TezClient.getAppMasterStatus(TezClient.java:618)
at org.apache.tez.client.TezClient.waitTillReady(TezClient.java:697)
at org.apache.hadoop.hive.ql.exec.tez.TezSessionState.open(TezSessionState.java:205)
at org.apache.hadoop.hive.ql.exec.tez.TezSessionState.open(TezSessionState.java:116)
at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:532)
at org.apache.spark.sql.hive.client.HiveClientImpl.newState(HiveClientImpl.scala:183)
at org.apache.spark.sql.hive.client.HiveClientImpl.<init>(HiveClientImpl.scala:117)
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:422)
at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:271)
at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:384)
at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:286)
at org.apache.spark.sql.hive.HiveExternalCatalog.client$lzycompute(HiveExternalCatalog.scala:66)
at org.apache.spark.sql.hive.HiveExternalCatalog.client(HiveExternalCatalog.scala:65)
at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply$mcZ$sp(HiveExternalCatalog.scala:215)
at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:215)
at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:215)
at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
at org.apache.spark.sql.hive.HiveExternalCatalog.databaseExists(HiveExternalCatalog.scala:214)
at org.apache.spark.sql.internal.SharedState.externalCatalog$lzycompute(SharedState.scala:114)
at org.apache.spark.sql.internal.SharedState.externalCatalog(SharedState.scala:102)
at org.apache.spark.sql.internal.SharedState.globalTempViewManager$lzycompute(SharedState.scala:141)
at org.apache.spark.sql.internal.SharedState.globalTempViewManager(SharedState.scala:136)
at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anonfun$2.apply(HiveSessionStateBuilder.scala:55)
at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anonfun$2.apply(HiveSessionStateBuilder.scala:55)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.globalTempViewManager$lzycompute(SessionCatalog.scala:91)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.globalTempViewManager(SessionCatalog.scala:91)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.isTemporaryTable(SessionCatalog.scala:736)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.isRunningDirectlyOnFiles(Analyzer.scala:747)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.resolveRelation(Analyzer.scala:681)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:713)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:706)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:89)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:706)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:652)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
at com.sc.sdm.rt.oa.recon.TestConnection$.main(TestConnection.scala:34)
at com.sc.sdm.rt.oa.recon.TestConnection.main(TestConnection.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 org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:684)
Caused by: java.io.IOException: Failed on local exception: java.io.IOException: org.apache.hadoop.security.AccessControlException: Client cannot authenticate via:[TOKEN, KERBEROS]; Host Details : local host is: "dfghcv012.global.xyz.com/10.7.1.52"; destination host is: "dfghcv013.global.xyz.com":43890;
at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:776)
at org.apache.hadoop.ipc.Client.call(Client.java:1479)
at org.apache.hadoop.ipc.Client.call(Client.java:1412)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
... 91 more
感谢任何帮助!!
最佳答案
我能够解决这个问题。
我删除了
--files hive-site.xml
添加了 Spark 配置
--conf spark.security.credentials.hadoopfs.enabled=true
上述更改对我有用。
关于apache-spark - 在 Kerberos 环境中无法通过 Spark 访问 Hive : Client cannot authenticate via:[TOKEN, KERBEROS]，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/63596797/