各位好
我的spark是2.1.0，用的hive-jdbc 2.1.0，现在写入impala的时候报以下错：
java.sql.SQLException: Method not supported
at org.apache.hive.jdbc.HivePreparedStatement.addBatch(HivePreparedStatement.java:75)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.savePartition(JdbcUtils.scala:589)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$saveTable$1.apply(JdbcUtils.scala:670)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$saveTable$1.apply(JdbcUtils.scala:670)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$29.apply(RDD.scala:925)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$29.apply(RDD.scala:925)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1944)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1944)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1931)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1944)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1958)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:925)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1.apply(RDD.scala:923)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.foreachPartition(RDD.scala:923)
at org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply$mcV$sp(Dataset.scala:2305)
at org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply(Dataset.scala:2305)
at org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply(Dataset.scala:2305)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2765)
at org.apache.spark.sql.Dataset.foreachPartition(Dataset.scala:2304)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.saveTable(JdbcUtils.scala:670)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:77)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:518)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:215)
at org.apache.spark.sql.DataFrameWriter.jdbc(DataFrameWriter.scala:446)
at com.aoyou.data.CustomerVisitProduct$.saveToHive(CustomerVisitProduct.scala:281)
at com.aoyou.data.CustomerVisitProduct$.main(CustomerVisitProduct.scala:221)
at com.aoyou.data.CustomerVisitProduct.main(CustomerVisitProduct.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:738)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:187)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:212)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:126)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.sql.SQLException: Method not supported
at org.apache.hive.jdbc.HivePreparedStatement.addBatch(HivePreparedStatement.java:75)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.savePartition(JdbcUtils.scala:589)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$saveTable$1.apply(JdbcUtils.scala:670)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$saveTable$1.apply(JdbcUtils.scala:670)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$29.apply(RDD.scala:925)
at org.apache.spark.rdd.RDD$$anonfun$foreachPartition$1$$anonfun$apply$29.apply(RDD.scala:925)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1944)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1944)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
以下是代码实现
val sparkConf = new SparkConf().setAppName("save").set("spark.sql.crossJoin.enabled", "true");
val sparkSession = SparkSession
.builder()
.enableHiveSupport()
.getOrCreate();
val dataframe = sparkSession.createDataFrame(rddSchema, new Row().getClass())
val property = new Properties();
property.put("user", "xxxxx")
property.put("password", "xxxxx")
dataframe.write.mode(SaveMode.Append).option("driver", "org.apache.hive.jdbc.HiveDriver").jdbc("jdbc:hive2://xxxx:21050/rawdata;auth=noSasl", "tablename", property)
请问这是怎么回事啊？感觉是驱动版本问题
