本文主要是介绍一次spark sql 优化的经历： SparkException: Job aborted / spark.yarn.executor.memoryOverhead，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
问题背景
某天 跑 sparkSQL 的时候，遇到报错：
org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter . w r i t e ( F i l e F o r m a t W r i t e r . s c a l a : 198 ) a t o r g . a p a c h e . s p a r k . s q l . h i v e . e x e c u t i o n . S a v e A s H i v e F i l e .write(FileFormatWriter.scala:198) at org.apache.spark.sql.hive.execution.SaveAsHiveFile .write(FileFormatWriter.scala:198)atorg.apache.spark.sql.hive.execution.SaveAsHiveFileclass.saveAsHiveFile(SaveAsHiveFile.scala:86)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.saveAsHiveFile(InsertIntoHiveTable.scala:66)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.processInsert(InsertIntoHiveTable.scala:195)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.run(InsertIntoHiveTable.scala:99)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult l z y c o m p u t e ( c o m m a n d s . s c a l a : 104 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . c o m m a n d . D a t a W r i t i n g C o m m a n d E x e c . s i d e E f f e c t R e s u l t ( c o m m a n d s . s c a l a : 102 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . c o m m a n d . D a t a W r i t i n g C o m m a n d E x e c . e x e c u t e C o l l e c t ( c o m m a n d s . s c a l a : 115 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t lzycompute(commands.scala:104) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102) at org.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:115) at org.apache.spark.sql.Dataset lzycompute(commands.scala:104)atorg.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)atorg.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:115)atorg.apache.spark.sql.Dataset$anonfun 6. a p p l y ( D a t a s e t . s c a l a : 194 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t 6.apply(Dataset.scala:194) at org.apache.spark.sql.Dataset 6.apply(Dataset.scala:194)atorg.apache.spark.sql.Dataset$anonfun 6. a p p l y ( D a t a s e t . s c a l a : 194 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t 6.apply(Dataset.scala:194) at org.apache.spark.sql.Dataset 6.apply(Dataset.scala:194)atorg.apache.spark.sql.Dataset$anonfun 52. a p p l y ( D a t a s e t . s c a l a : 3370 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . S Q L E x e c u t i o n 52.apply(Dataset.scala:3370) at org.apache.spark.sql.execution.SQLExecution 52.apply(Dataset.scala:3370)atorg.apache.spark.sql.execution.SQLExecution a n o n f u n anonfun anonfunwithNewExecutionId 1. a p p l y ( S Q L E x e c u t i o n . s c a l a : 80 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . S Q L E x e c u t i o n 1.apply(SQLExecution.scala:80) at org.apache.spark.sql.execution.SQLExecution 1.apply(SQLExecution.scala:80)atorg.apache.spark.sql.execution.SQLExecution.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution . w i t h N e w E x e c u t i o n I d ( S Q L E x e c u t i o n . s c a l a : 75 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t . o r g .withNewExecutionId(SQLExecution.scala:75) at org.apache.spark.sql.Dataset.org .withNewExecutionId(SQLExecution.scala:75)atorg.apache.spark.sql.Dataset.orgapache s p a r k spark sparksql D a t a s e t Dataset Dataset w i t h A c t i o n ( D a t a s e t . s c a l a : 3369 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t . < i n i t > ( D a t a s e t . s c a l a : 194 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t withAction(Dataset.scala:3369) at org.apache.spark.sql.Dataset.<init>(Dataset.scala:194) at org.apache.spark.sql.Dataset withAction(Dataset.scala:3369)atorg.apache.spark.sql.Dataset.<init>(Dataset.scala:194)atorg.apache.spark.sql.Dataset.ofRows(Dataset.scala:79)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:643)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:694)
at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:371)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver . m a i n ( S p a r k S Q L C L I D r i v e r . s c a l a : 274 ) a t o r g . a p a c h e . s p a r k . s q l . h i v e . t h r i f t s e r v e r . S p a r k S Q L C L I D r i v e r . m a i n ( S p a r k S Q L C L I D r i v e r . s c a l a ) a t s u n . r e f l e c t . N a t i v e M e t h o d A c c e s s o r I m p l . i n v o k e 0 ( N a t i v e M e t h o d ) a t s u n . r e f l e c t . N a t i v e M e t h o d A c c e s s o r I m p l . i n v o k e ( N a t i v e M e t h o d A c c e s s o r I m p l . j a v a : 62 ) a t s u n . r e f l e c t . D e l e g a t i n g M e t h o d A c c e s s o r I m p l . i n v o k e ( D e l e g a t i n g M e t h o d A c c e s s o r I m p l . j a v a : 43 ) a t j a v a . l a n g . r e f l e c t . M e t h o d . i n v o k e ( M e t h o d . j a v a : 498 ) a t o r g . a p a c h e . s p a r k . d e p l o y . J a v a M a i n A p p l i c a t i o n . s t a r t ( S p a r k A p p l i c a t i o n . s c a l a : 52 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t . o r g .main(SparkSQLCLIDriver.scala:274) at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala) 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 org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52) at org.apache.spark.deploy.SparkSubmit.org .main(SparkSQLCLIDriver.scala:274)atorg.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)atsun.reflect.NativeMethodAccessorImpl.invoke0(NativeMethod)atsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)atsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)atjava.lang.reflect.Method.invoke(Method.java:498)atorg.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)atorg.apache.spark.deploy.SparkSubmit.orgapache s p a r k spark sparkdeploy S p a r k S u b m i t SparkSubmit SparkSubmit$runMain(SparkSubmit.scala:845)
at org.apache.spark.deploy.SparkSubmit.doRunMain 1 ( S p a r k S u b m i t . s c a l a : 161 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t . s u b m i t ( S p a r k S u b m i t . s c a l a : 184 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t . d o S u b m i t ( S p a r k S u b m i t . s c a l a : 86 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t 1(SparkSubmit.scala:161) at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184) at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86) at org.apache.spark.deploy.SparkSubmit 1(SparkSubmit.scala:161)atorg.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184)atorg.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)atorg.apache.spark.deploy.SparkSubmit$anon 2. d o S u b m i t ( S p a r k S u b m i t . s c a l a : 920 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t 2.doSubmit(SparkSubmit.scala:920) at org.apache.spark.deploy.SparkSubmit 2.doSubmit(SparkSubmit.scala:920)atorg.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala:929)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 6 in stage 16.0 failed 4 times, most recent failure: Lost task 6.3 in stage 16.0 (TID 478, idc-sql-dms-13, executor 40): ExecutorLostFailure (executor 40 exited caused by one of the running tasks) Reason: Container killed by YARN for exceeding memory limits. 11.8 GB of 11 GB physical memory used. Consider boosting spark.yarn.executor.memoryOverhead or disabling yarn.nodemanager.vmem-check-enabled because of YARN-4714.
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org a p a c h e apache apachespark s c h e d u l e r scheduler schedulerDAGScheduler f a i l J o b A n d I n d e p e n d e n t S t a g e s ( D A G S c h e d u l e r . s c a l a : 1925 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r failJobAndIndependentStages(DAGScheduler.scala:1925) at org.apache.spark.scheduler.DAGScheduler failJobAndIndependentStages(DAGScheduler.scala:1925)atorg.apache.spark.scheduler.DAGScheduleranonfun$abortStage 1. a p p l y ( D A G S c h e d u l e r . s c a l a : 1913 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r 1.apply(DAGScheduler.scala:1913) at org.apache.spark.scheduler.DAGScheduler 1.apply(DAGScheduler.scala:1913)atorg.apache.spark.scheduler.DAGScheduler a n o n f u n anonfun anonfunabortStage 1. a p p l y ( D A G S c h e d u l e r . s c a l a : 1912 ) a t s c a l a . c o l l e c t i o n . m u t a b l e . R e s i z a b l e A r r a y 1.apply(DAGScheduler.scala:1912) at scala.collection.mutable.ResizableArray 1.apply(DAGScheduler.scala:1912)atscala.collection.mutable.ResizableArrayclass.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1912)
at org.apache.spark.scheduler.DAGSchedulerKaTeX parse error: Can't use function '$' in math mode at position 8: anonfun$̲handleTaskSetFa…anonfun$handleTaskSetFailed 1. a p p l y ( D A G S c h e d u l e r . s c a l a : 948 ) a t s c a l a . O p t i o n . f o r e a c h ( O p t i o n . s c a l a : 257 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r . h a n d l e T a s k S e t F a i l e d ( D A G S c h e d u l e r . s c a l a : 948 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r E v e n t P r o c e s s L o o p . d o O n R e c e i v e ( D A G S c h e d u l e r . s c a l a : 2146 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r E v e n t P r o c e s s L o o p . o n R e c e i v e ( D A G S c h e d u l e r . s c a l a : 2095 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r E v e n t P r o c e s s L o o p . o n R e c e i v e ( D A G S c h e d u l e r . s c a l a : 2084 ) a t o r g . a p a c h e . s p a r k . u t i l . E v e n t L o o p 1.apply(DAGScheduler.scala:948) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:948) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2146) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2095) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2084) at org.apache.spark.util.EventLoop 1.apply(DAGScheduler.scala:948)atscala.Option.foreach(Option.scala:257)atorg.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:948)atorg.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2146)atorg.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2095)atorg.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2084)atorg.apache.spark.util.EventLoop$anon 1. r u n ( E v e n t L o o p . s c a l a : 49 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r . r u n J o b ( D A G S c h e d u l e r . s c a l a : 759 ) a t o r g . a p a c h e . s p a r k . S p a r k C o n t e x t . r u n J o b ( S p a r k C o n t e x t . s c a l a : 2061 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . d a t a s o u r c e s . F i l e F o r m a t W r i t e r 1.run(EventLoop.scala:49) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:759) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061) at org.apache.spark.sql.execution.datasources.FileFormatWriter 1.run(EventLoop.scala:49)atorg.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:759)atorg.apache.spark.SparkContext.runJob(SparkContext.scala:2061)atorg.apache.spark.sql.execution.datasources.FileFormatWriter.write(FileFormatWriter.scala:167)
… 35 more
org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter . w r i t e ( F i l e F o r m a t W r i t e r . s c a l a : 198 ) a t o r g . a p a c h e . s p a r k . s q l . h i v e . e x e c u t i o n . S a v e A s H i v e F i l e .write(FileFormatWriter.scala:198) at org.apache.spark.sql.hive.execution.SaveAsHiveFile .write(FileFormatWriter.scala:198)atorg.apache.spark.sql.hive.execution.SaveAsHiveFileclass.saveAsHiveFile(SaveAsHiveFile.scala:86)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.saveAsHiveFile(InsertIntoHiveTable.scala:66)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.processInsert(InsertIntoHiveTable.scala:195)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.run(InsertIntoHiveTable.scala:99)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult l z y c o m p u t e ( c o m m a n d s . s c a l a : 104 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . c o m m a n d . D a t a W r i t i n g C o m m a n d E x e c . s i d e E f f e c t R e s u l t ( c o m m a n d s . s c a l a : 102 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . c o m m a n d . D a t a W r i t i n g C o m m a n d E x e c . e x e c u t e C o l l e c t ( c o m m a n d s . s c a l a : 115 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t lzycompute(commands.scala:104) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102) at org.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:115) at org.apache.spark.sql.Dataset lzycompute(commands.scala:104)atorg.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)atorg.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:115)atorg.apache.spark.sql.Dataset$anonfun 6. a p p l y ( D a t a s e t . s c a l a : 194 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t 6.apply(Dataset.scala:194) at org.apache.spark.sql.Dataset 6.apply(Dataset.scala:194)atorg.apache.spark.sql.Dataset$anonfun 6. a p p l y ( D a t a s e t . s c a l a : 194 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t 6.apply(Dataset.scala:194) at org.apache.spark.sql.Dataset 6.apply(Dataset.scala:194)atorg.apache.spark.sql.Dataset$anonfun 52. a p p l y ( D a t a s e t . s c a l a : 3370 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . S Q L E x e c u t i o n 52.apply(Dataset.scala:3370) at org.apache.spark.sql.execution.SQLExecution 52.apply(Dataset.scala:3370)atorg.apache.spark.sql.execution.SQLExecution a n o n f u n anonfun anonfunwithNewExecutionId 1. a p p l y ( S Q L E x e c u t i o n . s c a l a : 80 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . S Q L E x e c u t i o n 1.apply(SQLExecution.scala:80) at org.apache.spark.sql.execution.SQLExecution 1.apply(SQLExecution.scala:80)atorg.apache.spark.sql.execution.SQLExecution.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution . w i t h N e w E x e c u t i o n I d ( S Q L E x e c u t i o n . s c a l a : 75 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t . o r g .withNewExecutionId(SQLExecution.scala:75) at org.apache.spark.sql.Dataset.org .withNewExecutionId(SQLExecution.scala:75)atorg.apache.spark.sql.Dataset.orgapache s p a r k spark sparksql D a t a s e t Dataset Dataset w i t h A c t i o n ( D a t a s e t . s c a l a : 3369 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t . < i n i t > ( D a t a s e t . s c a l a : 194 ) a t o r g . a p a c h e . s p a r k . s q l . D a t a s e t withAction(Dataset.scala:3369) at org.apache.spark.sql.Dataset.<init>(Dataset.scala:194) at org.apache.spark.sql.Dataset withAction(Dataset.scala:3369)atorg.apache.spark.sql.Dataset.<init>(Dataset.scala:194)atorg.apache.spark.sql.Dataset.ofRows(Dataset.scala:79)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:643)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:694)
at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:371)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver . m a i n ( S p a r k S Q L C L I D r i v e r . s c a l a : 274 ) a t o r g . a p a c h e . s p a r k . s q l . h i v e . t h r i f t s e r v e r . S p a r k S Q L C L I D r i v e r . m a i n ( S p a r k S Q L C L I D r i v e r . s c a l a ) a t s u n . r e f l e c t . N a t i v e M e t h o d A c c e s s o r I m p l . i n v o k e 0 ( N a t i v e M e t h o d ) a t s u n . r e f l e c t . N a t i v e M e t h o d A c c e s s o r I m p l . i n v o k e ( N a t i v e M e t h o d A c c e s s o r I m p l . j a v a : 62 ) a t s u n . r e f l e c t . D e l e g a t i n g M e t h o d A c c e s s o r I m p l . i n v o k e ( D e l e g a t i n g M e t h o d A c c e s s o r I m p l . j a v a : 43 ) a t j a v a . l a n g . r e f l e c t . M e t h o d . i n v o k e ( M e t h o d . j a v a : 498 ) a t o r g . a p a c h e . s p a r k . d e p l o y . J a v a M a i n A p p l i c a t i o n . s t a r t ( S p a r k A p p l i c a t i o n . s c a l a : 52 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t . o r g .main(SparkSQLCLIDriver.scala:274) at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala) 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 org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52) at org.apache.spark.deploy.SparkSubmit.org .main(SparkSQLCLIDriver.scala:274)atorg.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)atsun.reflect.NativeMethodAccessorImpl.invoke0(NativeMethod)atsun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)atsun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)atjava.lang.reflect.Method.invoke(Method.java:498)atorg.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)atorg.apache.spark.deploy.SparkSubmit.orgapache s p a r k spark sparkdeploy S p a r k S u b m i t SparkSubmit SparkSubmit$runMain(SparkSubmit.scala:845)
at org.apache.spark.deploy.SparkSubmit.doRunMain 1 ( S p a r k S u b m i t . s c a l a : 161 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t . s u b m i t ( S p a r k S u b m i t . s c a l a : 184 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t . d o S u b m i t ( S p a r k S u b m i t . s c a l a : 86 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t 1(SparkSubmit.scala:161) at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184) at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86) at org.apache.spark.deploy.SparkSubmit 1(SparkSubmit.scala:161)atorg.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184)atorg.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)atorg.apache.spark.deploy.SparkSubmit$anon 2. d o S u b m i t ( S p a r k S u b m i t . s c a l a : 920 ) a t o r g . a p a c h e . s p a r k . d e p l o y . S p a r k S u b m i t 2.doSubmit(SparkSubmit.scala:920) at org.apache.spark.deploy.SparkSubmit 2.doSubmit(SparkSubmit.scala:920)atorg.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala:929)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 6 in stage 16.0 failed 4 times, most recent failure: Lost task 6.3 in stage 16.0 (TID 478, idc-sql-dms-13, executor 40): ExecutorLostFailure (executor 40 exited caused by one of the running tasks) Reason: Container killed by YARN for exceeding memory limits. 11.8 GB of 11 GB physical memory used. Consider boosting spark.yarn.executor.memoryOverhead or disabling yarn.nodemanager.vmem-check-enabled because of YARN-4714.
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org a p a c h e apache apachespark s c h e d u l e r scheduler schedulerDAGScheduler f a i l J o b A n d I n d e p e n d e n t S t a g e s ( D A G S c h e d u l e r . s c a l a : 1925 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r failJobAndIndependentStages(DAGScheduler.scala:1925) at org.apache.spark.scheduler.DAGScheduler failJobAndIndependentStages(DAGScheduler.scala:1925)atorg.apache.spark.scheduler.DAGScheduleranonfun$abortStage 1. a p p l y ( D A G S c h e d u l e r . s c a l a : 1913 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r 1.apply(DAGScheduler.scala:1913) at org.apache.spark.scheduler.DAGScheduler 1.apply(DAGScheduler.scala:1913)atorg.apache.spark.scheduler.DAGScheduler a n o n f u n anonfun anonfunabortStage 1. a p p l y ( D A G S c h e d u l e r . s c a l a : 1912 ) a t s c a l a . c o l l e c t i o n . m u t a b l e . R e s i z a b l e A r r a y 1.apply(DAGScheduler.scala:1912) at scala.collection.mutable.ResizableArray 1.apply(DAGScheduler.scala:1912)atscala.collection.mutable.ResizableArrayclass.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1912)
at org.apache.spark.scheduler.DAGSchedulerKaTeX parse error: Can't use function '$' in math mode at position 8: anonfun$̲handleTaskSetFa…anonfun$handleTaskSetFailed 1. a p p l y ( D A G S c h e d u l e r . s c a l a : 948 ) a t s c a l a . O p t i o n . f o r e a c h ( O p t i o n . s c a l a : 257 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r . h a n d l e T a s k S e t F a i l e d ( D A G S c h e d u l e r . s c a l a : 948 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r E v e n t P r o c e s s L o o p . d o O n R e c e i v e ( D A G S c h e d u l e r . s c a l a : 2146 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r E v e n t P r o c e s s L o o p . o n R e c e i v e ( D A G S c h e d u l e r . s c a l a : 2095 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r E v e n t P r o c e s s L o o p . o n R e c e i v e ( D A G S c h e d u l e r . s c a l a : 2084 ) a t o r g . a p a c h e . s p a r k . u t i l . E v e n t L o o p 1.apply(DAGScheduler.scala:948) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:948) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2146) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2095) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2084) at org.apache.spark.util.EventLoop 1.apply(DAGScheduler.scala:948)atscala.Option.foreach(Option.scala:257)atorg.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:948)atorg.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2146)atorg.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2095)atorg.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2084)atorg.apache.spark.util.EventLoop$anon 1. r u n ( E v e n t L o o p . s c a l a : 49 ) a t o r g . a p a c h e . s p a r k . s c h e d u l e r . D A G S c h e d u l e r . r u n J o b ( D A G S c h e d u l e r . s c a l a : 759 ) a t o r g . a p a c h e . s p a r k . S p a r k C o n t e x t . r u n J o b ( S p a r k C o n t e x t . s c a l a : 2061 ) a t o r g . a p a c h e . s p a r k . s q l . e x e c u t i o n . d a t a s o u r c e s . F i l e F o r m a t W r i t e r 1.run(EventLoop.scala:49) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:759) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061) at org.apache.spark.sql.execution.datasources.FileFormatWriter 1.run(EventLoop.scala:49)atorg.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:759)atorg.apache.spark.SparkContext.runJob(SparkContext.scala:2061)atorg.apache.spark.sql.execution.datasources.FileFormatWriter.write(FileFormatWriter.scala:167)
… 35 more
通过上面的日志，大概了解到任务失败的原因应该是内存超过限定。 “Container killed by YARN for exceeding memory limits. ”，解决问题的第一思路是 sql 能不能优化下，加内存属于下下策。
解决办法
先讲一下原来的 sql 思路：
SELECT a.name, a.age, b.alias
from a
left join (SELECT id, concat_ws(',', COLLECT_LIST(alias)) aliasfrom bbgroup by id
) b
这是一个很简单的逻辑，猜测问题应该出现在 collect_ws() 函数， 当 b 表根据 id 聚合的时候，如果大量的数据 加载到 list （COLLECT_LIST）里面，将导致内存耗尽。
解决思路 应该是先把重复数据去掉，再调用 concat_ws(’,’ , COLLECT_LIST(alias))，优化后的sql 如下：
SELECT a.name, a.age, b.alias
from a
left join (SELECT id, collect_ws(',', COLLECT_LIST(alias)) aliasfrom (SELECT id, aliasfrom bb group by id, alias)group by id
) b
还有更简单的一种写法，就是使用 COLLECT_SET 代替 COLLECT_LIST：
SELECT a.name, a.age, b.alias
from a
left join (SELECT id, collect_ws(',', COLLECT_SET(alias)) aliasfrom bbgroup by id
) b
哈哈，问题解决！
这篇关于一次spark sql 优化的经历： SparkException: Job aborted / spark.yarn.executor.memoryOverhead的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
