[
https://issues.apache.org/jira/browse/SPARK-10159?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Michael Armbrust resolved SPARK-10159.
--------------------------------------
Resolution: Fixed
Fix Version/s: 1.5.0
In Spark 1.5 there is a native implementation of this function.
https://github.com/apache/spark/blob/master/sql/core/src/main/scala/org/apache/spark/sql/functions.scala#L2103
> Hive 1.3.x GenericUDFDate NPE issue
> -----------------------------------
>
> Key: SPARK-10159
> URL: https://issues.apache.org/jira/browse/SPARK-10159
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.4.0
> Reporter: Alex Liu
> Fix For: 1.5.0
>
>
> When run sql query with HiveContext, Hive 1.3.x GenericUDFDate NPE issue.
> The following is the query and log
> {code}
> SELECT a.stationid AS stationid,
> a.month AS month,
> a.year AS year,
> AVG(a.mean) AS mean,
> MIN(a.min) AS min,
> MAX(a.max) AS max
> FROM
> (SELECT *,
> YEAR(date) AS year,
> MONTH(date) AS month,
> FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE(date), 'yyyy-MM-dd'), 'E') AS
> weekday
> FROM weathercql.daily) a
> WHERE ((a.weekday = 'Mon'))
> AND (a.metric = 'temperature')
> GROUP BY a.stationid, a.month, a.year
> ORDER BY stationid, year, month
> LIMIT 100
> {code}
> log {code}
> Filter
> ((HiveSimpleUdf#org.apache.hadoop.hive.ql.udf.UDFFromUnixTime(HiveGenericUdf#org.apache.hadoop.hive.ql.udf.generic.GenericUDFUnixTimeStamp(HiveGenericUdf#org.apache.hadoop.hive.ql.udf.generic.GenericUDFDate(date#81),yyyy-MM-dd),E)
> = Mon) && (metric#80 = temperature))
> ERROR 2015-08-20 15:39:06
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation: Error
> executing query:
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in
> stage 2.0 failed 4 times, most recent failure: Lost task 1.3 in stage 2.0
> (TID 208, 127.0.0.1): java.lang.NullPointerException
> at
> org.apache.hadoop.hive.ql.udf.generic.GenericUDFDate.evaluate(GenericUDFDate.java:119)
> at org.apache.spark.sql.hive.HiveGenericUdf.eval(hiveUdfs.scala:188)
> at
> org.apache.spark.sql.hive.HiveGenericUdf$$anonfun$eval$2.apply(hiveUdfs.scala:184)
> at
> org.apache.spark.sql.hive.DeferredObjectAdapter.get(hiveUdfs.scala:138)
> at
> org.apache.hadoop.hive.ql.udf.generic.GenericUDFToUnixTimeStamp.evaluate(GenericUDFToUnixTimeStamp.java:121)
> at
> org.apache.hadoop.hive.ql.udf.generic.GenericUDFUnixTimeStamp.evaluate(GenericUDFUnixTimeStamp.java:52)
> at org.apache.spark.sql.hive.HiveGenericUdf.eval(hiveUdfs.scala:188)
> at
> org.apache.spark.sql.hive.HiveSimpleUdf$$anonfun$eval$1.apply(hiveUdfs.scala:121)
> at
> org.apache.spark.sql.hive.HiveSimpleUdf$$anonfun$eval$1.apply(hiveUdfs.scala:121)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at org.apache.spark.sql.hive.HiveSimpleUdf.eval(hiveUdfs.scala:121)
> at
> org.apache.spark.sql.catalyst.expressions.EqualTo.eval(predicates.scala:191)
> at
> org.apache.spark.sql.catalyst.expressions.And.eval(predicates.scala:130)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedPredicate$$anonfun$create$1.apply(predicates.scala:30)
> at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at
> org.apache.spark.sql.execution.Aggregate$$anonfun$doExecute$1$$anonfun$7.apply(Aggregate.scala:154)
> at
> org.apache.spark.sql.execution.Aggregate$$anonfun$doExecute$1$$anonfun$7.apply(Aggregate.scala:149)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:70)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:70)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Driver stacktrace:
> at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1273)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1264)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1263)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> ~[scala-library-2.10.5.jar:na]
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> ~[scala-library-2.10.5.jar:na]
> at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1263)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at scala.Option.foreach(Option.scala:236) ~[scala-library-2.10.5.jar:na]
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1457)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1418)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> ~[spark-core_2.10-1.4.1.1.jar:1.4.1.1]
> {code}
> https://github.com/apache/hive/blob/branch-0.13/ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDFDate.java#L61
> needs to be transient.
> Should a custom Hive build for Spark? or open a ticket on OSS Hive on it?
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
