[ https://issues.apache.org/jira/browse/SPARK-9832?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Apache Spark reassigned SPARK-9832: ----------------------------------- Assignee: Davies Liu (was: Apache Spark) > TPCDS Q98 Fails > --------------- > > Key: SPARK-9832 > URL: https://issues.apache.org/jira/browse/SPARK-9832 > Project: Spark > Issue Type: Sub-task > Components: SQL > Reporter: Michael Armbrust > Assignee: Davies Liu > Priority: Blocker > > {code} > select > i_item_desc, > i_category, > i_class, > i_current_price, > sum(ss_ext_sales_price) as itemrevenue > -- sum(ss_ext_sales_price) * 100 / sum(sum(ss_ext_sales_price)) over > (partition by i_class) as revenueratio > from > store_sales > join item on (store_sales.ss_item_sk = item.i_item_sk) > join date_dim on (store_sales.ss_sold_date_sk = date_dim.d_date_sk) > where > i_category in('Jewelry', 'Sports', 'Books') > -- and d_date between cast('2001-01-12' as date) and (cast('2001-01-12' as > date) + 30) > -- and d_date between '2001-01-12' and '2001-02-11' > -- and ss_date between '2001-01-12' and '2001-02-11' > -- and ss_sold_date_sk between 2451922 and 2451952 -- partition key filter > and ss_sold_date_sk between 2451911 and 2451941 -- partition key filter (1 > calendar month) > and d_date between '2001-01-01' and '2001-01-31' > group by > i_item_id, > i_item_desc, > i_category, > i_class, > i_current_price > order by > i_category, > i_class, > i_item_id, > i_item_desc > -- revenueratio > limit 1000 > {code} > {code} > Job aborted due to stage failure: Task 11 in stage 62.0 failed 4 times, most > recent failure: Lost task 11.3 in stage 62.0 (TID 5289, 10.0.227.73): > java.lang.IllegalArgumentException: Unscaled value too large for precision > at org.apache.spark.sql.types.Decimal.set(Decimal.scala:76) > at org.apache.spark.sql.types.Decimal$.apply(Decimal.scala:338) > at org.apache.spark.sql.types.Decimal.apply(Decimal.scala) > at > org.apache.spark.sql.catalyst.expressions.UnsafeRow.getDecimal(UnsafeRow.java:386) > at > org.apache.spark.sql.catalyst.expressions.JoinedRow.getDecimal(JoinedRow.scala:97) > at > org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown > Source) > at > org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown > Source) > at > org.apache.spark.sql.execution.joins.HashJoin$$anon$1.next(HashJoin.scala:101) > at > org.apache.spark.sql.execution.joins.HashJoin$$anon$1.next(HashJoin.scala:74) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > at > org.apache.spark.sql.execution.joins.HashJoin$$anon$1.fetchNext(HashJoin.scala:115) > at > org.apache.spark.sql.execution.joins.HashJoin$$anon$1.hasNext(HashJoin.scala:93) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) > at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) > at > org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:353) > at > org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:587) > at > org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$1.apply(TungstenAggregate.scala:72) > at > org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$1.apply(TungstenAggregate.scala:64) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) > at > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) > at > org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) > at org.apache.spark.scheduler.Task.run(Task.scala:88) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) > 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) > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org