Container mit einem Exit-Code ungleich Null 143 ausgestiegen. Durch externes Signal getötet ⇐ Python

[Guest]

Ich speichere die Ausgabe eines Modells als Tabelle in Google Big Query aus dem DataProc -Cluster mit dem folgenden Code: < /p>
Rules.write \
.format("bigquery") \
.option("table","{}.{}".format(bq_dataset, bq_table)) \
.option("temporaryGcsBucket", gcs_bucket) \
.mode('append') \
.save()
< /code>
dem folgenden Fehler beim Ausführen des obigen Codes: < /p>
Py4JJavaError Traceback (most recent call last)
in
33 .option("table","{}.{}".format(bq_dataset, bq_table)) \
34 .option("temporaryGcsBucket", gcs_bucket) \
---> 35 .mode('append') \
36 .save()
37 #change overwrite to append

/usr/lib/spark/python/pyspark/sql/readwriter.py in save(self, path, format, mode, partitionBy, **options)
735 self.format(format)
736 if path is None:
--> 737 self._jwrite.save()
738 else:
739 self._jwrite.save(path)

/opt/conda/anaconda/lib/python3.6/site-packages/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:

/usr/lib/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()

/opt/conda/anaconda/lib/python3.6/site-packages/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 o122.save.
: java.lang.RuntimeException: Failed to write to BigQuery
at com.google.cloud.spark.bigquery.BigQueryWriteHelper.writeDataFrameToBigQuery(BigQueryWriteHelper.scala:70)
at com.google.cloud.spark.bigquery.BigQueryInsertableRelation.insert(BigQueryInsertableRelation.scala:42)
at com.google.cloud.spark.bigquery.BigQueryRelationProvider.createRelation(BigQueryRelationProvider.scala:85)
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$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81)
at org.apache.spark.sql.DataFrameWriter$$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$1.apply(SQLExecution.scala:80)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:198)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:159)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122)
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$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81)
at org.apache.spark.sql.DataFrameWriter$$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$1.apply(SQLExecution.scala:80)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
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 org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229)
at com.google.cloud.spark.bigquery.BigQueryWriteHelper.writeDataFrameToBigQuery(BigQueryWriteHelper.scala:75)
... 33 more
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 4.0 failed 4 times, most recent failure: Lost task 1.3 in stage 4.0 (TID 14, cluster-first-w-2.c.main, executor 3): ExecutorLostFailure (executor 3 exited caused by one of the running tasks) Reason: Container from a bad node: container_1593684541132_0002_01_000005 on host: cluster-Py4JJavaError Traceback (most recent call last)
in
33 .option("table","{}.{}".format(bq_dataset, bq_table)) \
34 .option("temporaryGcsBucket", gcs_bucket) \
---> 35 .mode('append') \
36 .save()
37 #change overwrite to append

/usr/lib/spark/python/pyspark/sql/readwriter.py in save(self, path, format, mode, partitionBy, **options)
735 self.format(format)
736 if path is None:
--> 737 self._jwrite.save()
738 else:
739 self._jwrite.save(path)

/opt/conda/anaconda/lib/python3.6/site-packages/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:

/usr/lib/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()

/opt/conda/anaconda/lib/python3.6/site-packages/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 o122.save.
: java.lang.RuntimeException: Failed to write to BigQuery
at com.google.cloud.spark.bigquery.BigQueryWriteHelper.writeDataFrameToBigQuery(BigQueryWriteHelper.scala:70)
at com.google.cloud.spark.bigquery.BigQueryInsertableRelation.insert(BigQueryInsertableRelation.scala:42)
at com.google.cloud.spark.bigquery.BigQueryRelationProvider.createRelation(BigQueryRelationProvider.scala:85)
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$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81)
at org.apache.spark.sql.DataFrameWriter$$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$1.apply(SQLExecution.scala:80)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:198)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:159)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122)
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$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81)
at org.apache.spark.sql.DataFrameWriter$$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$1.apply(SQLExecution.scala:80)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229)
at com.google.cloud.spark.bigquery.BigQueryWriteHelper.writeDataFrameToBigQuery(BigQueryWriteHelper.scala:75)
... 33 more
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 4.0 failed 4 times, most recent failure: Lost task 1.3 in stage 4.0 (TID 14, cluster-first-w-2.c.main.internal, executor 3): ExecutorLostFailure (executor 3 exited caused by one of the running tasks) Reason: Container from a bad node: container_1593684541132_0002_01_000005 on host: cluster-first-w-2.c.main.internal. Exit status: 143. Diagnostics: [2020-07-02 12:16:23.881]Container killed on request. Exit code is 143
[2020-07-02 12:16:23.881]Container exited with a non-zero exit code 143.
[2020-07-02 12:16:23.882]Killed by external signal
.
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1892)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1880)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1879)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1879)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2113)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2062)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2051)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:738)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:167)
... 55 more. Exit status: 143. Diagnostics: [2020-07-02 12:16:23.881]Container killed on request. Exit code is 143
[2020-07-02 12:16:23.881]Container exited with a non-zero exit code 143.
[2020-07-02 12:16:23.882]Killed by external signal
.
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1892)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1880)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1879)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1879)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2113)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2062)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2051)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:738)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:167)
... 55 more
< /code>
Unten finden Sie das Protokolldetail: < /p>
{
insertId: "ukfr1kykqi44b6z0n"
jsonPayload: {
application: "application_1593765937787_0003"
class: "org.apache.spark.deploy.yarn.YarnAllocator"
container: "container_1593765937787_0003_01_000001"
container_logname: "stderr"
filename: "application_1593765937787_0003.container_1593765937787_0003_01_000001.stderr"
message: "Container from a bad node: container_1593765937787_0003_01_000008 on host: cluster-first-w-2.c.main.internal. Exit status: 143. Diagnostics: [2020-07-03 10:47:32.493]Container killed on request. Exit code is 143"
}
labels: {
compute.googleapis.com/resource_id: "4317452345300701444"
compute.googleapis.com/resource_name: "cluster-first-w-1"
compute.googleapis.com/zone: "us"
}
logName: "projects/main/logs/yarn-userlogs"
receiveTimestamp: "2020-07-03T10:47:37.775061029Z"
resource: {
labels: {
cluster_name: "cluster-first"
cluster_uuid: "59505b2f-9814-4dbc-add1-9b93dabc7144"
project_id: "main"
region: "global"
}
type: "cloud_dataproc_cluster"
}
severity: "WARNING"
timestamp: "2020-07-03T10:47:32Z"
}
< /code>
Nach meiner Online -Forschung ergibt sich der oben genannte Fehler aufgrund des Speicherproblems. Ich habe versucht, die Erinnerung an meinen Cluster zu erhöhen und auch versucht zu haben, den Speicheraufwand zu erhöhen, kann dieses Problem jedoch nicht beheben. Was kann noch getan werden?