[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16788811#comment-16788811
]
Takeshi Yamamuro commented on SPARK-25863:
--
Thanks alot!
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Assignee: Takeshi Yamamuro
>Priority: Major
> Labels: cache, catalyst, code-generation
> Fix For: 2.3.4, 2.4.2, 3.0.0
>
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> 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.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:109)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
> at
> java.util.concurrent.ThreadPo
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16787989#comment-16787989
]
Val Feldsher commented on SPARK-25863:
--
[~maropu] yes it works now, I still see the warning but it doesn't crash.
Thanks!
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Assignee: Takeshi Yamamuro
>Priority: Major
> Labels: cache, catalyst, code-generation
> Fix For: 2.3.4, 2.4.2, 3.0.0
>
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:109)
> at org.apache.spark.executor.Executor$TaskRunner
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16786512#comment-16786512
]
Takeshi Yamamuro commented on SPARK-25863:
--
[~vfeldsher] Can you check if your query works well in the current master?
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Assignee: Takeshi Yamamuro
>Priority: Major
> Labels: cache, catalyst, code-generation
> Fix For: 3.0.0
>
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> 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.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:109)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16786202#comment-16786202
]
Val Feldsher commented on SPARK-25863:
--
I recently experienced similar issue while upgrading from spark 2.1.0 to 2.3.2,
and it appears that this happens whenever I use spark.driver.userClassPathFirst
or spark.executor.userClassPathFirst. Similar to
[SPARK-20241|https://issues.apache.org/jira/browse/SPARK-20241] , I see 2
different class loaders when I set this property to true:
org.apache.spark.util.ChildFirstURLClassLoader and
sun.misc.Launcher$AppClassLoader. This is accompanied by warning:
Error calculating stats of compiled class.
java.lang.IllegalArgumentException: Can not set final [B field
org.codehaus.janino.util.ClassFile$CodeAttribute.code to
org.codehaus.janino.util.ClassFile$CodeAttribute
Followed by the empty.max error.
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Priority: Major
> Labels: cache, catalyst, code-generation
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadC
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16782903#comment-16782903
]
Takeshi Yamamuro commented on SPARK-25863:
--
Yea, returning 0 sounds reasonable to me, too.
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Priority: Major
> Labels: cache, catalyst, code-generation
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> 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.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:109)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16782810#comment-16782810
]
Sean Owen commented on SPARK-25863:
---
Returning 0 seems like the correct thing to do, locally. [~maropu] does that
sound right? this particular line was added in
https://github.com/apache/spark/commit/4a779bdac3e75c17b7d36c5a009ba6c948fa9fb6
It seems like it could happen if you had errors computing stats. Do you see
warnings like "Error calculating stats of compiled class"?
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Priority: Major
> Labels: cache, catalyst, code-generation
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.sp
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16668438#comment-16668438
]
Marco Gaido commented on SPARK-25863:
-
[~Tagar] thanks.
??not sure yet as it might depend on data I guess too.??
No for sure, code generation doesn't depend on the data, it depends on the
query and the schema.
??Is there is some debugging we can enable that would be helpful to get to root
cause\???
May you post the logs? I expect some warnings or similar to happen before the
exception that might help understanding more.
??Would it make sense just to add an `if` codeSizes is empty, return zero.??
I can't say which is the right fix if I don't know the root cause.
Thanks.
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Priority: Major
> Labels: cache, catalyst, code-generation
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apach
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16667721#comment-16667721
]
Ruslan Dautkhanov commented on SPARK-25863:
---
[~mgaido], I will try to get a reproducer, but it might be a tough task, not
sure yet as it might depend on data I guess too.
If this helps, I can tell that this Spark job was operating on a very wide
table (thousands of columns),
and the SQL itself was generated and have a long SELECT clause with a lot of
CASE statements...
so I can imaging Spark's Code Generation had a hard time to crank through this.
Is there is some debugging we can enable that would be helpful to get to root
cause?
Thank you.
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Priority: Major
> Labels: cache, catalyst, code-generation
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.compute
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=1876#comment-1876
]
Marco Gaido commented on SPARK-25863:
-
[~Tagar] thanks for reporting this. May you please provide a reproducer? If you
can post a simplified version of your code generating the issue, it would be
helpful, otherwise it is hard to investigate the issue. Thanks.
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Priority: Major
> Labels: cache, catalyst, code-generation
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> 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.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:10
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=1736#comment-1736
]
Ruslan Dautkhanov commented on SPARK-25863:
---
It seems error happens here
[https://github.com/apache/spark/blob/branch-2.3/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala#L1475]
but this is as far as I can go... any ideas why this happens? thanks!
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.1, 2.3.2
>Reporter: Ruslan Dautkhanov
>Priority: Major
> Labels: cache, catalyst, code-generation
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org
[jira] [Commented] (SPARK-25863) java.lang.UnsupportedOperationException: empty.max at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala
[
https://issues.apache.org/jira/browse/SPARK-25863?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=1726#comment-1726
]
Ruslan Dautkhanov commented on SPARK-25863:
---
This happens only on one of our heaviest Spark jobs..
> java.lang.UnsupportedOperationException: empty.max at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> -
>
> Key: SPARK-25863
> URL: https://issues.apache.org/jira/browse/SPARK-25863
> Project: Spark
> Issue Type: Bug
> Components: Optimizer, Spark Core
>Affects Versions: 2.3.2
>Reporter: Ruslan Dautkhanov
>Priority: Major
> Labels: cache, catalyst, code-generation
>
> Failing task :
> {noformat}
> An error occurred while calling o2875.collectToPython.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 58
> in stage 21413.0 failed 4 times, most recent failure: Lost task 58.3 in stage
> 21413.0 (TID 4057314, pc1udatahad117, executor 431):
> java.lang.UnsupportedOperationException: empty.max
> at scala.collection.TraversableOnce$class.max(TraversableOnce.scala:229)
> at scala.collection.AbstractTraversable.max(Traversable.scala:104)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.updateAndGetCompilationStats(CodeGenerator.scala:1475)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.org$apache$spark$sql$catalyst$expressions$codegen$CodeGenerator$$doCompile(CodeGenerator.scala:1418)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1493)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:1490)
> at
> org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at
> org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at
> org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004)
> at
> org.spark_project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1365)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$.create(GeneratePredicate.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1321)
> at
> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1318)
> at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:401)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:263)
> at
> org.apache.spark.sql.execution.columnar.InMemoryTableScanExec$$anonfun$filteredCachedBatches$1.apply(InMemoryTableScanExec.scala:262)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndexInternal$1$$anonfun$apply$24.apply(RDD.scala:818)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:109)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:114
