Yes, it's always appears on a part of the whole tasks in a stage(i.e. 100/100 (65 failed)), and sometimes cause the stage to fail.
And there is another error that I'm not sure if there is a correlation. java.lang.NoClassDefFoundError: Could not initialize class org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$ at org.apache.spark.sql.execution.SparkPlan.newPredicate(SparkPlan.scala:114) at org.apache.spark.sql.execution.Filter.conditionEvaluator$lzycompute(basicOperators.scala:55) at org.apache.spark.sql.execution.Filter.conditionEvaluator(basicOperators.scala:55) at org.apache.spark.sql.execution.Filter$$anonfun$2.apply(basicOperators.scala:58) at org.apache.spark.sql.execution.Filter$$anonfun$2.apply(basicOperators.scala:57) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) at org.apache.spark.rdd.RDD.iterator(RDD.scala:229) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) at org.apache.spark.rdd.RDD.iterator(RDD.scala:229) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) at org.apache.spark.rdd.RDD.iterator(RDD.scala:229) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:54) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:178) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:744) On Tue, Nov 18, 2014 at 11:41 AM, Michael Armbrust <mich...@databricks.com> wrote: > Interesting, I believe we have run that query with version 1.1.0 with > codegen turned on and not much has changed there. Is the error > deterministic? > > On Mon, Nov 17, 2014 at 7:04 PM, Eric Zhen <zhpeng...@gmail.com> wrote: > >> Hi Michael, >> >> We use Spark v1.1.1-rc1 with jdk 1.7.0_51 and scala 2.10.4. >> >> On Tue, Nov 18, 2014 at 7:09 AM, Michael Armbrust <mich...@databricks.com >> > wrote: >> >>> What version of Spark SQL? >>> >>> On Sat, Nov 15, 2014 at 10:25 PM, Eric Zhen <zhpeng...@gmail.com> wrote: >>> >>>> Hi all, >>>> >>>> We run SparkSQL on TPCDS benchmark Q19 with spark.sql.codegen=true, we >>>> got exceptions as below, has anyone else saw these before? >>>> >>>> java.lang.ExceptionInInitializerError >>>> at >>>> org.apache.spark.sql.execution.SparkPlan.newProjection(SparkPlan.scala:92) >>>> at >>>> org.apache.spark.sql.execution.Exchange$$anonfun$execute$1$$anonfun$1.apply(Exchange.scala:51) >>>> at >>>> org.apache.spark.sql.execution.Exchange$$anonfun$execute$1$$anonfun$1.apply(Exchange.scala:48) >>>> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) >>>> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) >>>> at >>>> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) >>>> at >>>> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) >>>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:229) >>>> at >>>> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68) >>>> at >>>> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) >>>> at org.apache.spark.scheduler.Task.run(Task.scala:54) >>>> at >>>> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:178) >>>> at >>>> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) >>>> at >>>> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) >>>> at java.lang.Thread.run(Thread.java:744) >>>> Caused by: java.lang.NullPointerException >>>> at >>>> scala.reflect.internal.Types$TypeRef.computeHashCode(Types.scala:2358) >>>> at >>>> scala.reflect.internal.Types$UniqueType.<init>(Types.scala:1304) >>>> at scala.reflect.internal.Types$TypeRef.<init>(Types.scala:2341) >>>> at >>>> scala.reflect.internal.Types$NoArgsTypeRef.<init>(Types.scala:2137) >>>> at >>>> scala.reflect.internal.Types$TypeRef$$anon$6.<init>(Types.scala:2544) >>>> at scala.reflect.internal.Types$TypeRef$.apply(Types.scala:2544) >>>> at scala.reflect.internal.Types$class.typeRef(Types.scala:3615) >>>> at >>>> scala.reflect.internal.SymbolTable.typeRef(SymbolTable.scala:13) >>>> at >>>> scala.reflect.internal.Symbols$TypeSymbol.newTypeRef(Symbols.scala:2752) >>>> at >>>> scala.reflect.internal.Symbols$TypeSymbol.typeConstructor(Symbols.scala:2806) >>>> at >>>> scala.reflect.internal.Symbols$SymbolContextApiImpl.toTypeConstructor(Symbols.scala:103) >>>> at >>>> scala.reflect.internal.Symbols$TypeSymbol.toTypeConstructor(Symbols.scala:2698) >>>> at >>>> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$typecreator1$1.apply(CodeGenerator.scala:46) >>>> at >>>> scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe$lzycompute(TypeTags.scala:231) >>>> at >>>> scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe(TypeTags.scala:231) >>>> at scala.reflect.api.TypeTags$class.typeOf(TypeTags.scala:335) >>>> at scala.reflect.api.Universe.typeOf(Universe.scala:59) >>>> at >>>> org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.<init>(CodeGenerator.scala:46) >>>> at >>>> org.apache.spark.sql.catalyst.expressions.codegen.GenerateProjection$.<init>(GenerateProjection.scala:29) >>>> at >>>> org.apache.spark.sql.catalyst.expressions.codegen.GenerateProjection$.<clinit>(GenerateProjection.scala) >>>> ... 15 more >>>> -- >>>> Best Regards >>>> >>> >>> >> >> >> -- >> Best Regards >> > > -- Best Regards