当前位置：首页 > news >正文

spark3.x 读取hudi报错

news 2025/8/4 7:58:26

报错信息如下：

Exception in thread "main" org.apache.hudi.exception.HoodieUpsertException: Failed to upsert for commit time 20231201203145254
   at org.apache.hudi.table.action.commit.BaseWriteHelper.write(BaseWriteHelper.java:64)
   at org.apache.hudi.table.action.commit.SparkInsertOverwriteCommitActionExecutor.execute(SparkInsertOverwriteCommitActionExecutor.java:63)
   at org.apache.hudi.table.HoodieSparkCopyOnWriteTable.insertOverwrite(HoodieSparkCopyOnWriteTable.java:159)
   at org.apache.hudi.table.HoodieSparkCopyOnWriteTable.insertOverwrite(HoodieSparkCopyOnWriteTable.java:97)
   at org.apache.hudi.client.SparkRDDWriteClient.insertOverwrite(SparkRDDWriteClient.java:207)
   at org.apache.hudi.DataSourceUtils.doWriteOperation(DataSourceUtils.java:208)
   at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:329)
   at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:183)
   at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:46)
   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
   at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:90)
   at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:180)
   at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:218)
   at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
   at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:215)
   at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:176)
   at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:132)
   at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:131)
   at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:989)
   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
   at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:989)
   at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:438)
   at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:415)
   at org.apache.spark.sql.DataFrameWrite