【发布时间】:2019-11-30 21:44:37
【问题描述】:
我目前正在尝试仅执行从 Hive 到 ElasticSearch 的“SELECT * FROM table”。我正在使用 cloudera CDH 6.0.1。我已经将 elasticsearch-hadoop-hive-7.1.1 jar 添加到我的配置单元路径中。我有 ElasticSearch 7.1.1 Cloudera 堆栈和弹性运行在不同的服务器但在同一个网络中。
CREATE EXTERNAL TABLE ctrl_rater_resumen_lla_es
(
fecha_registro string,
direccion string,
linea_b_codigo_prestadora string,
linea_b_tipo_numero string,
es_roaming string,
call_duration string,
linea_b_routing_number string,
minutos string, fecha string
)
STORED BY 'org.elasticsearch.hadoop.hive.EsStorageHandler'
TBLPROPERTIES (
'es.resource' = 'ctrl_rater_resumen_lla/hb',
'es.node' = 'http://10.129.x.xxx',
'es.port' = '9200',
'es.index.auto.create' = 'true',
'es.index.read.missing.as.empty' = 'true',
'es.nodes.discovery'='true',
'es.net.ssl'='false'
'es.nodes.client.only'='false',
'es.nodes.wan.only' = 'true'
'es.net.http.auth.user'='xxxxx',
'es.net.http.auth.pass' = 'xxxxx'
);
创建成功
SELECT * FROM ctrl_rater_resumen_lla_es;
请求 TFetchResultsReq(fetchType=0, operationHandle=TOperationHandle(hasResultSet=True, modifiedRowCount=None, operationType=0, operationId=THandleIdentifier(secret='\xbaYG*\xd4wI\xc0\xb8\xf6\x94Q\ xa3\xa4IY', guid='\xff\xca\xdb\xb5\x040E\x0e\x8eE\xe4\xf7?t\x1b\x01')), 方向=4, maxRows=100): TFetchResultsResp(status=TStatus (errorCode=0, errorMessage="java.io.IOException: org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: 无法检测到 ES 版本 - 通常在无法访问网络/Elasticsearch 集群或针对没有适当的 WAN/Cloud 实例时发生这种情况设置 'es.nodes.wan.only'", sqlState=None, infoMessages=["*org.apache.hive.service.cli.HiveSQLException:java.io.IOException: org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: 无法检测到 ES版本 - 如果网络/Elasticsearch 集群不可访问,或者在没有正确设置 'es.nodes.wan.only':25 的情况下以 WAN/云实例为目标时,通常会发生这种情况:24", 'org.apache.hive.service.cli.operation.SQLOperation:getNextRowSet:SQLOperation.java:492', 'org.apache.hive.service.cli.operation.OperationManager:getOperationNextRowSet:OperationManager.java:297 ', 'org.apache.hive.service.cli.session.HiveSessionImpl:fetchResults:HiveSessionImpl.java:852', 'sun.reflect.GeneratedMethodAccessor24:invoke::-1', 'sun.reflect.DelegatingMethodAccessorImpl:invoke:DelegatingMethodAccessorImpl .java:43'、'java.lang.reflect.Method:invoke:Method.java:498'、'org.apache.hive.service.cli.session.HiveSessionProxy:invoke:HiveSessionProxy.java:78'、'org .apache.hive.service.cli.session.HiveSessionProxy:access$000:HiveSessionProxy.java:36', 'org.apache.hive.service.cli.session.HiveSessionProxy$1:run:HiveSessionProxy.java:63', 'java .security.AccessController:doPrivileged:AccessController.java:-2', 'javax.security.auth.Subject:doAs:Subject.java:422', 'org.apache.hadoop.security.UserGroupInformation:doAs:UserGroupInformation.java: 1726','org.apache.hive.service.cli.sessi on.HiveSessionProxy:invoke:HiveSessionProxy.java:59', 'com.sun.proxy.$Proxy38:fetchResults::-1', 'org.apache.hive.service.cli.CLIService:fetchResults:CLIService.java:505 ', 'org.apache.hive.service.cli.thrift.ThriftCLIService:FetchResults:ThriftCLIService.java:702', 'org.apache.hive.service.rpc.thrift.TCLIService$Processor$FetchResults:getResult:TCLIService.java :1717', 'org.apache.hive.service.rpc.thrift.TCLIService$Processor$FetchResults:getResult:TCLIService.java:1702', 'org.apache.thrift.ProcessFunction:process:ProcessFunction.java:39', 'org.apache.thrift.TBaseProcessor:process:TBaseProcessor.java:39', 'org.apache.hive.service.auth.TSetIpAddressProcessor:process:TSetIpAddressProcessor.java:56', 'org.apache.thrift.server.TThreadPoolServer $WorkerProcess:run:TThreadPoolServer.java:286', 'java.util.concurrent.ThreadPoolExecutor:runWorker:ThreadPoolExecutor.java:1149', 'java.util.concurrent.ThreadPoolExecutor$Worker:run:ThreadPoolExecutor.java:624', 'java.lang.Thread:run:Thread.java:748', "*java.io.IOException:org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: 无法检测到 ES 版本 - 通常如果网络/Elasticsearch 集群不可访问或在没有正确设置 'es.nodes. wan.only':29:4", 'org.apache.hadoop.hive.ql.exec.FetchOperator:getNextRow:FetchOperator.java:521', 'org.apache.hadoop.hive.ql.exec.FetchOperator:pushRow :FetchOperator.java:428', 'org.apache.hadoop.hive.ql.exec.FetchTask:fetch:FetchTask.java:146', 'org.apache.hadoop.hive.ql.Driver:getResults:Driver.java :2196', 'org.apache.hive.service.cli.operation.SQLOperation:getNextRowSet:SQLOperation.java:487', "*org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: 无法检测 ES 版本 - 通常如果网络/无法访问 Elasticsearch 集群或在没有正确设置 'es.nodes.wan.only':35:6", 'org.elasticsearch.hadoop.rest.InitializationUtils:discoverClusterInfo:Initial 的情况下定位 WAN/Cloud 实例izationUtils.java:340'、'org.elasticsearch.hadoop.hive.HiveUtils:init:HiveUtils.java:197'、'org.elasticsearch.hadoop.hive.EsHiveInputFormat:getSplits:EsHiveInputFormat.java:112'、'org. elasticsearch.hadoop.hive.EsHiveInputFormat:getSplits:EsHiveInputFormat.java:51', 'org.apache.hadoop.hive.ql.exec.FetchOperator:getNextSplits:FetchOperator.java:372', 'org.apache.hadoop.hive. ql.exec.FetchOperator:getRecordReader:FetchOperator.java:304', 'org.apache.hadoop.hive.ql.exec.FetchOperator:getNextRow:FetchOperator.java:459', '*org.elasticsearch.hadoop.rest.EsHadoopNoNodesLeftException :连接错误(检查网络和/或代理设置)- 所有节点都失败;试过 [[localhost:9200]] :41:6', 'org.elasticsearch.hadoop.rest.NetworkClient:execute:NetworkClient.java:152', 'org.elasticsearch.hadoop.rest.RestClient:execute:RestClient.java :424', 'org.elasticsearch.hadoop.rest.RestClient:execute:RestClient.java:388', 'org.elasticsearch.hadoop.rest.RestClient:execute:RestClient.java:392', 'org.elasticsearch.hadoop .rest.RestClient:get:RestClient.java:168', 'org.elasticsearch.hadoop.rest.RestClient:mainInfo:RestClient.java:735', 'org.elasticsearch.hadoop.rest.InitializationUtils:discoverClusterInfo:InitializationUtils.java :330'], statusCode=3), results=None, hasMoreRows=None)
【问题讨论】:
标签: apache-spark hadoop elasticsearch hive cloudera