Major Description
For certain multi-insert queries, Hive on Spark throws a deserialization error.
create table status_updates(userid int,status string,ds string); create table profiles(userid int,school string,gender int); drop table school_summary; create table school_summary(school string,cnt int) partitioned by (ds string); drop table gender_summary; create table gender_summary(gender int,cnt int) partitioned by (ds string); insert into status_updates values (1, "status_1", "2016-03-16"); insert into profiles values (1, "school_1", 0); set hive.auto.convert.join=false; set hive.execution.engine=spark; FROM (SELECT a.status, b.school, b.gender FROM status_updates a JOIN profiles b ON (a.userid = b.userid and a.ds='2009-03-20' ) ) subq1 INSERT OVERWRITE TABLE gender_summary PARTITION(ds='2009-03-20') SELECT subq1.gender, COUNT(1) GROUP BY subq1.gender INSERT OVERWRITE TABLE school_summary PARTITION(ds='2009-03-20') SELECT subq1.school, COUNT(1) GROUP BY subq1.school
Error:
16/03/17 13:29:00 [task-result-getter-3]: WARN scheduler.TaskSetManager: Lost task 0.0 in stage 2.0 (TID 3, localhost): java.lang.RuntimeException: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error: Unable to deserialize reduce input key from x1x128x0x0 with properties {serialization.sort.order.null=a, columns=reducesinkkey0, serialization.lib=org.apache.hadoop.hive.serde2.binarysortable.BinarySortableSerDe, serialization.sort.order=+, columns.types=int}
at org.apache.hadoop.hive.ql.exec.spark.SparkReduceRecordHandler.processRow(SparkReduceRecordHandler.java:279)
at org.apache.hadoop.hive.ql.exec.spark.HiveReduceFunctionResultList.processNextRecord(HiveReduceFunctionResultList.java:49)
at org.apache.hadoop.hive.ql.exec.spark.HiveReduceFunctionResultList.processNextRecord(HiveReduceFunctionResultList.java:28)
at org.apache.hadoop.hive.ql.exec.spark.HiveBaseFunctionResultList$ResultIterator.hasNext(HiveBaseFunctionResultList.java:95)
at scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:41)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
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:89)
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:724)
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error: Unable to deserialize reduce input key from x1x128x0x0 with properties {serialization.sort.order.null=a, columns=reducesinkkey0, serialization.lib=org.apache.hadoop.hive.serde2.binarysortable.BinarySortableSerDe, serialization.sort.order=+, columns.types=int}
at org.apache.hadoop.hive.ql.exec.spark.SparkReduceRecordHandler.processRow(SparkReduceRecordHandler.java:251)
... 12 more
Caused by: org.apache.hadoop.hive.serde2.SerDeException: java.io.EOFException
at org.apache.hadoop.hive.serde2.binarysortable.BinarySortableSerDe.deserialize(BinarySortableSerDe.java:241)
at org.apache.hadoop.hive.ql.exec.spark.SparkReduceRecordHandler.processRow(SparkReduceRecordHandler.java:249)
... 12 more
Caused by: java.io.EOFException
at org.apache.hadoop.hive.serde2.binarysortable.InputByteBuffer.read(InputByteBuffer.java:54)
at org.apache.hadoop.hive.serde2.binarysortable.BinarySortableSerDe.deserializeInt(BinarySortableSerDe.java:597)
at org.apache.hadoop.hive.serde2.binarysortable.BinarySortableSerDe.deserialize(BinarySortableSerDe.java:288)
at org.apache.hadoop.hive.serde2.binarysortable.BinarySortableSerDe.deserialize(BinarySortableSerDe.java:237)
... 13 more