----> 1 df.write.parquet("lakefs://smb/main/datasets/03_test/")
/databricks/spark/python/pyspark/sql/readwriter.py in parquet(self, path, mode, partitionBy, compression)
934 self.partitionBy(partitionBy)
935 self._set_opts(compression=compression)
--> 936 self._jwrite.parquet(path)
937
938 @since(1.6)
/databricks/spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py in __call__(self, *args)
1303 answer = self.gateway_client.send_command(command)
1304 return_value = get_return_value(
-> 1305 answer, self.gateway_client, self.target_id, self.name)
1306
1307 for temp_arg in temp_args:
/databricks/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
125 def deco(*a, **kw):
126 try:
--> 127 return f(*a, **kw)
128 except py4j.protocol.Py4JJavaError as e:
129 converted = convert_exception(e.java_exception)
/databricks/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o330.parquet.
: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:230)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:192)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:116)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:114)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:139)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:200)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$3(SparkPlan.scala:252)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:165)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:248)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:192)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:158)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:157)
at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:999)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withCustomExecutionEnv$5(SQLExecution.scala:116)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:249)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withCustomExecutionEnv$1(SQLExecution.scala:101)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:845)
at org.apache.spark.sql.execution.SQLExecution$.withCustomExecutionEnv(SQLExecution.scala:77)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:199)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:999)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:437)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:421)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:294)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:884)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:380)
at py4j.Gateway.invoke(Gateway.java:295)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:251)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 2.0 failed 4 times, most recent failure: Lost task 0.3 in stage 2.0 (TID 13, 10.15.212.215, executor 0): java.io.IOException: get object metadata using underlying wrapped s3 client
at io.lakefs.MetadataClient.getObjectMetadata(MetadataClient.java:82)
at io.lakefs.LakeFSFileSystem.linkPhysicalAddress(LakeFSFileSystem.java:659)
at io.lakefs.LinkOnCloseOutputStream.close(LinkOnCloseOutputStream.java:66)
at org.apache.hadoop.fs.FSDataOutputStream$PositionCache.close(FSDataOutputStream.java:72)
at org.apache.hadoop.fs.FSDataOutputStream.close(FSDataOutputStream.java:106)
at com.databricks.sql.transaction.directory.DirectoryAtomicCommitProtocol.newTaskTempFileAbsPath(DirectoryAtomicCommitProtocol.scala:123)
at com.databricks.sql.transaction.directory.DirectoryAtomicCommitProtocol.newTaskTempFile(DirectoryAtomicCommitProtocol.scala:104)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.newOutputWriter(FileFormatDataWriter.scala:121)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.<init>(FileFormatDataWriter.scala:111)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:268)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$write$15(FileFormatWriter.scala:209)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.doRunTask(Task.scala:144)
at org.apache.spark.scheduler.Task.run(Task.scala:117)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$9(Executor.scala:655)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1581)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:658)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.NoSuchMethodException: com.databricks.s3a.S3AFileSystem.getWrappedFs()
at java.lang.Class.getDeclaredMethod(Class.java:2130)
at io.lakefs.MetadataClient.getObjectMetadata(MetadataClient.java:72)
... 19 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2519)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2466)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2460)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2460)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1152)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1152)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1152)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2721)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2668)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2656)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:938)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2339)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:199)
... 34 more
Caused by: java.io.IOException: get object metadata using underlying wrapped s3 client
at io.lakefs.MetadataClient.getObjectMetadata(MetadataClient.java:82)
at io.lakefs.LakeFSFileSystem.linkPhysicalAddress(LakeFSFileSystem.java:659)
at io.lakefs.LinkOnCloseOutputStream.close(LinkOnCloseOutputStream.java:66)
at org.apache.hadoop.fs.FSDataOutputStream$PositionCache.close(FSDataOutputStream.java:72)
at org.apache.hadoop.fs.FSDataOutputStream.close(FSDataOutputStream.java:106)
at com.databricks.sql.transaction.directory.DirectoryAtomicCommitProtocol.newTaskTempFileAbsPath(DirectoryAtomicCommitProtocol.scala:123)
at com.databricks.sql.transaction.directory.DirectoryAtomicCommitProtocol.newTaskTempFile(DirectoryAtomicCommitProtocol.scala:104)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.newOutputWriter(FileFormatDataWriter.scala:121)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.<init>(FileFormatDataWriter.scala:111)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:268)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$write$15(FileFormatWriter.scala:209)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.doRunTask(Task.scala:144)
at org.apache.spark.scheduler.Task.run(Task.scala:117)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$9(Executor.scala:655)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1581)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:658)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Caused by: java.lang.NoSuchMethodException: com.databricks.s3a.S3AFileSystem.getWrappedFs()
at java.lang.Class.getDeclaredMethod(Class.java:2130)
at io.lakefs.MetadataClient.getObjectMetadata(MetadataClient.java:72)
... 19 more