API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Aug 18th, 2019
199
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 10.31 KB | None | 0 0
raw download clone embed print report
  1. ---------------------------------------------------------------------------
  2. Py4JJavaError Traceback (most recent call last)
  3. <command-4103967183024832> in <module>()
  4. ----> 1 df.write.format("delta").partitionBy("contigName", "bin").save("/mnt/data/home/jeremy/data/ukbb/delta/")
  5.  
  6. /databricks/spark/python/pyspark/sql/readwriter.py in save(self, path, format, mode, partitionBy, **options)
  7. 736 self._jwrite.save()
  8. 737 else:
  9. --> 738 self._jwrite.save(path)
  10. 739
  11. 740 @since(1.4)
  12.  
  13. /databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
  14. 1255 answer = self.gateway_client.send_command(command)
  15. 1256 return_value = get_return_value(
  16. -> 1257 answer, self.gateway_client, self.target_id, self.name)
  17. 1258
  18. 1259 for temp_arg in temp_args:
  19.  
  20. /databricks/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
  21. 61 def deco(*a, **kw):
  22. 62 try:
  23. ---> 63 return f(*a, **kw)
  24. 64 except py4j.protocol.Py4JJavaError as e:
  25. 65 s = e.java_exception.toString()
  26.  
  27. /databricks/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
  28. 326 raise Py4JJavaError(
  29. 327 "An error occurred while calling {0}{1}{2}.\n".
  30. --> 328 format(target_id, ".", name), value)
  31. 329 else:
  32. 330 raise Py4JError(
  33.  
  34. Py4JJavaError: An error occurred while calling o391.save.
  35. : org.apache.spark.SparkException: Job aborted.
  36. at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:198)
  37. at com.databricks.sql.transaction.tahoe.files.TransactionalWriteEdge$$anonfun$writeFiles$1$$anonfun$apply$1.apply(TransactionalWriteEdge.scala:147)
  38. at com.databricks.sql.transaction.tahoe.files.TransactionalWriteEdge$$anonfun$writeFiles$1$$anonfun$apply$1.apply(TransactionalWriteEdge.scala:130)
  39. at org.apache.spark.sql.execution.SQLExecution$$anonfun$withCustomExecutionEnv$1.apply(SQLExecution.scala:111)
  40. at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:240)
  41. at org.apache.spark.sql.execution.SQLExecution$.withCustomExecutionEnv(SQLExecution.scala:97)
  42. at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:170)
  43. at com.databricks.sql.transaction.tahoe.files.TransactionalWriteEdge$$anonfun$writeFiles$1.apply(TransactionalWriteEdge.scala:130)
  44. at com.databricks.sql.transaction.tahoe.files.TransactionalWriteEdge$$anonfun$writeFiles$1.apply(TransactionalWriteEdge.scala:87)
  45. at com.databricks.logging.UsageLogging$$anonfun$recordOperation$1.apply(UsageLogging.scala:369)
  46. at com.databricks.logging.UsageLogging$$anonfun$withAttributionContext$1.apply(UsageLogging.scala:238)
  47. at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
  48. at com.databricks.logging.UsageLogging$class.withAttributionContext(UsageLogging.scala:233)
  49. at com.databricks.spark.util.PublicDBLogging.withAttributionContext(DatabricksSparkUsageLogger.scala:18)
  50. at com.databricks.logging.UsageLogging$class.withAttributionTags(UsageLogging.scala:271)
  51. at com.databricks.spark.util.PublicDBLogging.withAttributionTags(DatabricksSparkUsageLogger.scala:18)
  52. at com.databricks.logging.UsageLogging$class.recordOperation(UsageLogging.scala:350)
  53. at com.databricks.spark.util.PublicDBLogging.recordOperation(DatabricksSparkUsageLogger.scala:18)
  54. at com.databricks.spark.util.PublicDBLogging.recordOperation0(DatabricksSparkUsageLogger.scala:55)
  55. at com.databricks.spark.util.DatabricksSparkUsageLogger.recordOperation(DatabricksSparkUsageLogger.scala:94)
  56. at com.databricks.spark.util.UsageLogger$class.recordOperation(UsageLogger.scala:66)
  57. at com.databricks.spark.util.DatabricksSparkUsageLogger.recordOperation(DatabricksSparkUsageLogger.scala:63)
  58. at com.databricks.spark.util.UsageLogging$class.recordOperation(UsageLogger.scala:297)
  59. at com.databricks.sql.transaction.tahoe.OptimisticTransaction.recordOperation(OptimisticTransaction.scala:79)
  60. at com.databricks.sql.transaction.tahoe.metering.DeltaLogging$class.recordDeltaOperation(DeltaLogging.scala:108)
  61. at com.databricks.sql.transaction.tahoe.OptimisticTransaction.recordDeltaOperation(OptimisticTransaction.scala:79)
  62. at com.databricks.sql.transaction.tahoe.files.TransactionalWriteEdge$class.writeFiles(TransactionalWriteEdge.scala:87)
  63. at com.databricks.sql.transaction.tahoe.OptimisticTransaction.writeFiles(OptimisticTransaction.scala:79)
  64. at com.databricks.sql.transaction.tahoe.files.TransactionalWrite$class.writeFiles(TransactionalWrite.scala:96)
  65. at com.databricks.sql.transaction.tahoe.OptimisticTransaction.writeFiles(OptimisticTransaction.scala:79)
  66. at com.databricks.sql.transaction.tahoe.commands.WriteIntoDelta.write(WriteIntoDelta.scala:110)
  67. at com.databricks.sql.transaction.tahoe.commands.WriteIntoDelta$$anonfun$run$1$$anonfun$apply$1.apply(WriteIntoDelta.scala:71)
  68. at com.databricks.sql.transaction.tahoe.commands.WriteIntoDelta$$anonfun$run$1$$anonfun$apply$1.apply(WriteIntoDelta.scala:70)
  69. at com.databricks.sql.transaction.tahoe.DeltaLog.withNewTransaction(DeltaLog.scala:382)
  70. at com.databricks.sql.transaction.tahoe.commands.WriteIntoDelta$$anonfun$run$1.apply(WriteIntoDelta.scala:70)
  71. at com.databricks.sql.transaction.tahoe.commands.WriteIntoDelta$$anonfun$run$1.apply(WriteIntoDelta.scala:69)
  72. at com.databricks.sql.acl.CheckPermissions$.trusted(CheckPermissions.scala:781)
  73. at com.databricks.sql.transaction.tahoe.commands.WriteIntoDelta.run(WriteIntoDelta.scala:69)
  74. at com.databricks.sql.transaction.tahoe.sources.DeltaDataSource.createRelation(DeltaDataSource.scala:143)
  75. at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
  76. at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:72)
  77. at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:70)
  78. at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:88)
  79. at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:146)
  80. at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:134)
  81. at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$5.apply(SparkPlan.scala:187)
  82. at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
  83. at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:183)
  84. at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:134)
  85. at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:114)
  86. at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:114)
  87. at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:710)
  88. at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:710)
  89. at org.apache.spark.sql.execution.SQLExecution$$anonfun$withCustomExecutionEnv$1.apply(SQLExecution.scala:111)
  90. at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:240)
  91. at org.apache.spark.sql.execution.SQLExecution$.withCustomExecutionEnv(SQLExecution.scala:97)
  92. at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:170)
  93. at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:710)
  94. at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:306)
  95. at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:292)
  96. at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:235)
  97. at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
  98. at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
  99. at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
  100. at java.lang.reflect.Method.invoke(Method.java:498)
  101. at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
  102. at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:380)
  103. at py4j.Gateway.invoke(Gateway.java:295)
  104. at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
  105. at py4j.commands.CallCommand.execute(CallCommand.java:79)
  106. at py4j.GatewayConnection.run(GatewayConnection.java:251)
  107. at java.lang.Thread.run(Thread.java:748)
  108. Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 91 in stage 4.0 failed 4 times, most recent failure: Lost task 91.3 in stage 4.0 (TID 456, 10.26.238.110, executor 43): ExecutorLostFailure (executor 43 exited caused by one of the running tasks) Reason: Remote RPC client disassociated. Likely due to containers exceeding thresholds, or network issues. Check driver logs for WARN messages.
  109. Driver stacktrace:
  110. at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:2355)
  111. at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2343)
  112. at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2342)
  113. at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
  114. at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
  115. at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2342)
  116. at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:1096)
  117. at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:1096)
  118. at scala.Option.foreach(Option.scala:257)
  119. at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1096)
  120. at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2574)
  121. at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2522)
  122. at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2510)
  123. at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
  124. at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:893)
  125. at org.apache.spark.SparkContext.runJob(SparkContext.scala:2243)
  126. at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:167)
  127. ... 71 more
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!