我正在使用一个系统，该系统使用一个默认hadoop namenode在yarn上运行spark作业。最近，我在我的系统中添加了另一个hadoop namenodes。我现在希望spark作业从默认namenode读取输入数据，并将输出写入第二个namenode。如何在spark作业中配置或指定路径？我尝试将hdfs路径放到代码中，例如：

val spark = SparkSession.builder().appName("Example").getOrCreate();
 val input = spark.read.parquet("hdfs://defaultnamenode:9000/sample.parquet")
 input.write.parquet("hdfs://secondnamenode:9000/sample")

但它抛出了一个例外：

17/12/18 10:49:42 ERROR yarn.ApplicationMaster: User class threw exception: org.apache.spark.sql.AnalysisException: path hdfs://secondnamenode:9000/sample already exists.;
org.apache.spark.sql.AnalysisException: path hdfs://secondnamenode:9000/sample already exists.;
        at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:106)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
        at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
        at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
        at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
        at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
        at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
        at org.apache.spark.sql.execution.datasources.DataSource.writeInFileFormat(DataSource.scala:438)
        at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:474)
        at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:48)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
        at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
        at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
        at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
        at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
        at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
        at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:610)
        at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
        at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:217)
        at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:509)

根本没有结果：(