При попытке записать фрейм данных в S3 я получаю сообщение об ошибке ниже с nullpointerexception. Иногда работа проходит нормально, а иногда и не удается.
Я использую EMR 5.20 и spark 2.4.0
Создание сеанса Spark
val spark = SparkSession.builder
.config("spark.sql.parquet.binaryAsString", "true")
.config("spark.sql.sources.partitionColumnTypeInference.enabled", "false")
.config("spark.sql.parquet.filterPushdown", "true")
.config("spark.sql.parquet.fs.optimized.committer.optimization-enabled","true")
.getOrCreate()
spark.sql("myQuery").write.partitionBy("partitionColumn").mode(SaveMode.Overwrite).option("inferSchema","false").parquet("s3a://...filePath")
Может кто-нибудь помочь решить эту проблемутайна. Заранее спасибо
java.lang.NullPointerException
at com.amazon.ws.emr.hadoop.fs.s3.lite.S3Errors.isHttp200WithErrorCode(S3Errors.java:57)
at com.amazon.ws.emr.hadoop.fs.s3.lite.executor.GlobalS3Executor.execute(GlobalS3Executor.java:100)
at com.amazon.ws.emr.hadoop.fs.s3.lite.AmazonS3LiteClient.invoke(AmazonS3LiteClient.java:184)
at com.amazon.ws.emr.hadoop.fs.s3.lite.AmazonS3LiteClient.deleteObjects(AmazonS3LiteClient.java:127)
at com.amazon.ws.emr.hadoop.fs.s3n.Jets3tNativeFileSystemStore.deleteAll(Jets3tNativeFileSystemStore.java:364)
at com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.doSingleThreadedBatchDelete(S3NativeFileSystem.java:1372)
at com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.delete(S3NativeFileSystem.java:663)
at com.amazon.ws.emr.hadoop.fs.EmrFileSystem.delete(EmrFileSystem.java:332)
at org.apache.spark.internal.io.FileCommitProtocol.deleteWithJob(FileCommitProtocol.scala:124)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.deleteMatchingPartitions(InsertIntoHadoopFsRelationCommand.scala:223)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:122)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:668)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:668)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:668)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:276)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:270)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:228)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:557)
... 55 elided