Я пытаюсь загрузить фрейм данных в тераданные, используя драйвер JDB C, но получаю ошибку ниже.
jdb c версия: - 16.10.00.07 версия cloudera: - 5.15
вызывая искровую оболочку используя команду ниже. spark2-shell --jars terajdbc4.jar, tdgssconfig.jar, teradata-connector-1.4.4.jar
мы можем получить схему таблицы, но не можем выбрать или вставить операцию для всех столбцов таблицы.
также код, который я использую, можно найти ниже.
val insertdf = spark.sql(query)
val prop = new java.util.Properties
prop.setProperty("driver", "com.teradata.jdbc.TeraDriver")
prop.setProperty("user", "xxxxxx")
prop.setProperty("password", "*******")
val url = "jdbc:teradata://10.xxx.130.69/database=stg_database, TMODE=TERA"
val table = "test_table"
insertdf.write.mode("append").jdbc(url, table, prop)
ERROR:-
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1499)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1487)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1486)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1486)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1714)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1669)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1658)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2024)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2045)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2064)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:336)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2853)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153)
at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2837)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2836)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2153)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2366)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:245)
at org.apache.spark.sql.Dataset.show(Dataset.scala:644)
at org.apache.spark.sql.Dataset.show(Dataset.scala:603)
at org.apache.spark.sql.Dataset.show(Dataset.scala:612)
... 48 elided
Caused by: java.sql.SQLException: [Teradata JDBC Driver] [TeraJDBC 16.10.00.07] [Error 1277] [SQLState 08S01] Login timeout for Connection to 10.130.130.69 Tue Feb 04 02:05:21 EST 2020 socket orig=10.130.130.69 cid=44c91563 sess=0 java.net.SocketTimeoutException: connect timed out 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 com.teradata.jdbc.jdbc_4.io.TDNetworkIOIF$ConnectThread.run(TDNetworkIOIF.java:1242)
at com.teradata.jdbc.jdbc_4.util.ErrorFactory.makeDriverJDBCException(ErrorFactory.java:95)
at com.teradata.jdbc.jdbc_4.util.ErrorFactory.makeDriverJDBCException(ErrorFactory.java:70)
at com.teradata.jdbc.jdbc_4.util.ErrorFactory.makeIoJDBCException(ErrorFactory.java:208)
at com.teradata.jdbc.jdbc_4.util.ErrorAnalyzer.analyzeIoError(ErrorAnalyzer.java:59)
at com.teradata.jdbc.jdbc_4.io.TDNetworkIOIF.createSocketConnection(TDNetworkIOIF.java:163)
at com.teradata.jdbc.jdbc_4.io.TDNetworkIOIF.<init>(TDNetworkIOIF.java:142)
at com.teradata.jdbc.jdbc.GenericTeradataConnection.getIO(GenericTeradataConnection.java:142)
at com.teradata.jdbc.jdbc.GenericLogonController.run(GenericLogonController.java:100)
at com.teradata.jdbc.jdbc_4.TDSession.<init>(TDSession.java:211)
at com.teradata.jdbc.jdk6.JDK6_SQL_Connection.<init>(JDK6_SQL_Connection.java:36)
at com.teradata.jdbc.jdk6.JDK6ConnectionFactory.constructSQLConnection(JDK6ConnectionFactory.java:25)
at com.teradata.jdbc.jdbc.ConnectionFactory.createConnection(ConnectionFactory.java:178)
at com.teradata.jdbc.jdbc.ConnectionFactory.createConnection(ConnectionFactory.java:168)
at com.teradata.jdbc.TeraDriver.doConnect(TeraDriver.java:236)
at com.teradata.jdbc.TeraDriver.connect(TeraDriver.java:162)
at org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect(DriverWrapper.scala:45)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:61)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:52)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(JDBCRDD.scala:286)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.net.SocketTimeoutException: connect timed out
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)