azure-cosmosdb-spark
azure-cosmosdb-spark copied to clipboard
Published
20 hours ago •
Azure
Azure
updateEnable failure
sample code
json_insert = '{ "id" : "1", "title" : "Rambo", "releaseDate" : "1975-12-14", "ticketPrice" : "10.345"}'
df_insert = cls.spark.read.json(sc.parallelize([json_insert]))
df_insert.write.format("cosmos.oltp") \
.option("spark.synapse.linkedService", "CosmosDBLinkedService") \
.option("spark.cosmos.container", "batchTestContainer") \
.option("spark.cosmos.write.upsertEnabled", "true") \
.mode('append') \
.save()
time.sleep(10)
json_update = '{ "id" : "1", "title" : "Rambo", "releaseDate" : "1999-12-14", "ticketPrice" : "19.345"}'
sc = self.spark.sparkContext
df_update = self.spark.read.json(sc.parallelize([json_update]))
df_update.write.format("cosmos.oltp")\
.option("spark.synapse.linkedService", "CosmosDBLinkedService")\
.option("spark.cosmos.container", "batchTestContainer")\
.option("spark.cosmos.write.bulk.updateEnabled", "true")\
.mode('append')\
.save()
error
test_update_oltp (__main__.CosmosDBTests) ... ERROR
======================================================================
ERROR: test_update_oltp (__main__.CosmosDBTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File "cosmosdb_runner.py", line 164, in test_update_oltp
.mode('append')\
File "/opt/spark/python/lib/pyspark.zip/pyspark/sql/readwriter.py", line 736, in save
self._jwrite.save()
File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
answer, self.gateway_client, self.target_id, self.name)
File "/opt/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o424.save.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 298.0 failed 4 times, most recent failure: Lost task 1.3 in stage 298.0 (TID 6727, c398e1d976bd46ba9b742838dcc95a6c00140834399, executor 1): com.microsoft.azure.documentdb.DocumentClientException: java.util.NoSuchElementException
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.toDocumentClientException(DocumentBulkExecutor.java:1570)
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.executeBulkUpdateWithPatchInternal(DocumentBulkExecutor.java:765)
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.mergeAll(DocumentBulkExecutor.java:535)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$.bulkUpdate(CosmosDBSpark.scala:216)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$.com$microsoft$azure$cosmosdb$spark$CosmosDBSpark$$savePartition(CosmosDBSpark.scala:427)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$$anonfun$1.apply(CosmosDBSpark.scala:152)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$$anonfun$1.apply(CosmosDBSpark.scala:152)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:801)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:801)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:122)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.util.NoSuchElementException
at java.util.ArrayList$Itr.next(ArrayList.java:862)
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.executeBulkUpdateWithPatchAsyncImpl(DocumentBulkExecutor.java:1107)
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.executeBulkUpdateWithPatchInternal(DocumentBulkExecutor.java:712)
... 18 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1889)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1877)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1876)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1876)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2110)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2059)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2048)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2065)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2086)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2105)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2130)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:945)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.collect(RDD.scala:944)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$.save(CosmosDBSpark.scala:153)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$.save(CosmosDBSpark.scala:465)
at com.microsoft.azure.cosmosdb.spark.DefaultSource.createRelation(DefaultSource.scala:69)
at com.microsoft.azure.cosmos.oltp.spark.CosmosOLTPSource.createRelation(CosmosOLTPSource.scala:39)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.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$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: com.microsoft.azure.documentdb.DocumentClientException: java.util.NoSuchElementException
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.toDocumentClientException(DocumentBulkExecutor.java:1570)
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.executeBulkUpdateWithPatchInternal(DocumentBulkExecutor.java:765)
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.mergeAll(DocumentBulkExecutor.java:535)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$.bulkUpdate(CosmosDBSpark.scala:216)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$.com$microsoft$azure$cosmosdb$spark$CosmosDBSpark$$savePartition(CosmosDBSpark.scala:427)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$$anonfun$1.apply(CosmosDBSpark.scala:152)
at com.microsoft.azure.cosmosdb.spark.CosmosDBSpark$$anonfun$1.apply(CosmosDBSpark.scala:152)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:801)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:801)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:122)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Caused by: java.util.NoSuchElementException
at java.util.ArrayList$Itr.next(ArrayList.java:862)
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.executeBulkUpdateWithPatchAsyncImpl(DocumentBulkExecutor.java:1107)
at com.microsoft.azure.documentdb.bulkexecutor.DocumentBulkExecutor.executeBulkUpdateWithPatchInternal(DocumentBulkExecutor.java:712)
... 18 more
