Ливий выпуск на EMR-Hudi с S3
Я пытаюсь отправить сценарий hudi на EMR, который отлично работает при прямом запуске на EMR. В моем сценарии Hudi Spark я использую S3 в качестве целевой файловой системы. Каким-то образом при отправке через Livy.. Я получаю ошибку, например, не могу писать в s3a//dummy-bucket и т. Д., Что кажется проблемой записи s3. Я попытался передать параметр proxyUser для livy, чтобы выдать себя за пользователя hadoop. Но ничего не работает!! такая же ошибка появляется...
in <module>
save(basePath)
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/readwriter.py", line 738, in save
File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o127.save.
: org.apache.hudi.exception.HoodieIOException: Could not load Hoodie properties from s3a://demo_bucket/warehouse/emp-table-cow/.hoodie/hoodie.properties
at org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:97)
at org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:128)
at org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:113)
at org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:99)
at org.apache.hudi.HoodieSparkSqlWriter$.$anonfun$getHoodieTableConfig$1(HoodieSparkSqlWriter.scala:459)
at scala.Option.getOrElse(Option.scala:189)
at org.apache.hudi.HoodieSparkSqlWriter$.getHoodieTableConfig(HoodieSparkSqlWriter.scala:459)
at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:100)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:125)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:46)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$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:86)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:156)
at org.apache.spark.rdd.RDDOperationScope$.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$lzycompute(QueryExecution.scala:83)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:83)
at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:676)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:84)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:165)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:74)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:290)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229)
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:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.FileNotFoundException: No such file or directory: s3a://demo_bucket/warehouse/emp-table-cow/.hoodie/hoodie.properties
at org.apache.hadoop.fs.s3a.S3AFileSystem.s3GetFileStatus(S3AFileSystem.java:2310)
at org.apache.hadoop.fs.s3a.S3AFileSystem.innerGetFileStatus(S3AFileSystem.java:2204)
at org.apache.hadoop.fs.s3a.S3AFileSystem.getFileStatus(S3AFileSystem.java:2143)
at org.apache.hadoop.fs.s3a.S3AFileSystem.open(S3AFileSystem.java:716)
at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:902)
at org.apache.hudi.common.fs.HoodieWrapperFileSystem.open(HoodieWrapperFileSystem.java:369)
at org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:86)
... 38 more```