[
https://issues.apache.org/jira/browse/SPARK-9831?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Michael Armbrust updated SPARK-9831:
------------------------------------
Description:
{code}
select
c_last_name,
c_first_name,
c_salutation,
c_preferred_cust_flag,
ss_ticket_number,
cnt
from
(select
ss_ticket_number,
ss_customer_sk,
count(*) cnt
from
store_sales
join household_demographics on (store_sales.ss_hdemo_sk =
household_demographics.hd_demo_sk)
join store on (store_sales.ss_store_sk = store.s_store_sk)
-- join date_dim on (store_sales.ss_sold_date_sk = date_dim.d_date_sk)
where
store.s_county in ('Saginaw County', 'Sumner County', 'Appanoose County',
'Daviess County')
-- and date_dim.d_dom between 1 and 2
-- and date_dim.d_year in(1998, 1998 + 1, 1998 + 2)
-- and ss_date between '1999-01-01' and '2001-12-02'
-- and dayofmonth(ss_date) in (1,2)
-- partition key filter
-- and ss_sold_date_sk in (2450816, 2450846, 2450847, 2450874, 2450875,
2450905, 2450906, 2450935, 2450936, 2450966, 2450967,
-- 2450996, 2450997, 2451027, 2451028, 2451058,
2451059, 2451088, 2451089, 2451119, 2451120, 2451149,
-- 2451150, 2451180, 2451181, 2451211, 2451212,
2451239, 2451240, 2451270, 2451271, 2451300, 2451301,
-- 2451331, 2451332, 2451361, 2451362, 2451392,
2451393, 2451423, 2451424, 2451453, 2451454, 2451484,
-- 2451485, 2451514, 2451515, 2451545, 2451546,
2451576, 2451577, 2451605, 2451606, 2451636, 2451637,
-- 2451666, 2451667, 2451697, 2451698, 2451727,
2451728, 2451758, 2451759, 2451789, 2451790, 2451819,
-- 2451820, 2451850, 2451851, 2451880, 2451881)
and (household_demographics.hd_buy_potential = '>10000'
or household_demographics.hd_buy_potential = 'unknown')
and household_demographics.hd_vehicle_count > 0
and case when household_demographics.hd_vehicle_count > 0 then
household_demographics.hd_dep_count / household_demographics.hd_vehicle_count
else null end > 1
and ss_sold_date_sk between 2451180 and 2451269 -- partition key filter (3
months)
group by
ss_ticket_number,
ss_customer_sk
) dj
join customer on (dj.ss_customer_sk = customer.c_customer_sk)
where
cnt between 1 and 5
order by
cnt desc
limit 1000
{code}
{code}
Job aborted due to stage failure: Task 63 in stage 57.0 failed 4 times, most
recent failure: Lost task 63.3 in stage 57.0 (TID 5103, 10.0.197.102):
java.io.IOException: java.lang.IllegalArgumentException: Initial capacity must
be greater than 0
at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1264)
at
org.apache.spark.sql.execution.joins.UnsafeHashedRelation.readExternal(HashedRelation.scala:280)
at
java.io.ObjectInputStream.readExternalData(ObjectInputStream.java:1837)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
at
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:72)
at
org.apache.spark.broadcast.TorrentBroadcast$.unBlockifyObject(TorrentBroadcast.scala:217)
at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:178)
at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1276)
at
org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:165)
at
org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:64)
at
org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:64)
at
org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:88)
at org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoin$$anonfun$2.apply(BroadcastHashJoin.scala:91)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoin$$anonfun$2.apply(BroadcastHashJoin.scala:90)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.IllegalArgumentException: Initial capacity must be greater
than 0
at
org.apache.spark.unsafe.map.BytesToBytesMap.<init>(BytesToBytesMap.java:185)
at
org.apache.spark.unsafe.map.BytesToBytesMap.<init>(BytesToBytesMap.java:203)
at
org.apache.spark.sql.execution.joins.UnsafeHashedRelation$$anonfun$readExternal$1.apply$mcV$sp(HashedRelation.scala:295)
at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1261)
... 40 more
{code}
was:
{code}
select c_last_name
,c_first_name
,c_salutation
,c_preferred_cust_flag
,ss_ticket_number
,cnt from
(select ss_ticket_number
,ss_customer_sk
,count(*) cnt
from store_sales
JOIN date_dim ON store_sales.ss_sold_date_sk = date_dim.d_date_sk
JOIN store ON store_sales.ss_store_sk = store.s_store_sk
JOIN household_demographics ON store_sales.ss_hdemo_sk =
household_demographics.hd_demo_sk
where
date_dim.d_dom between 1 and 2
and (household_demographics.hd_buy_potential = '>10000' or
household_demographics.hd_buy_potential = 'unknown')
and household_demographics.hd_vehicle_count > 0
and case when household_demographics.hd_vehicle_count > 0 then
household_demographics.hd_dep_count/
household_demographics.hd_vehicle_count else null end > 1
and date_dim.d_year in (1998,1998+1,1998+2)
and store.s_county in ('Williamson County','Williamson County','Williamson
County','Williamson County')
group by ss_ticket_number,ss_customer_sk) dj
JOIN customer ON dj.ss_customer_sk = customer.c_customer_sk
where
cnt between 5 and 10
order by cnt desc
{code}
{code}
Job aborted due to stage failure: Task 63 in stage 57.0 failed 4 times, most
recent failure: Lost task 63.3 in stage 57.0 (TID 5103, 10.0.197.102):
java.io.IOException: java.lang.IllegalArgumentException: Initial capacity must
be greater than 0
at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1264)
at
org.apache.spark.sql.execution.joins.UnsafeHashedRelation.readExternal(HashedRelation.scala:280)
at
java.io.ObjectInputStream.readExternalData(ObjectInputStream.java:1837)
at
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
at
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:72)
at
org.apache.spark.broadcast.TorrentBroadcast$.unBlockifyObject(TorrentBroadcast.scala:217)
at
org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:178)
at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1276)
at
org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:165)
at
org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:64)
at
org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:64)
at
org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:88)
at org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoin$$anonfun$2.apply(BroadcastHashJoin.scala:91)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoin$$anonfun$2.apply(BroadcastHashJoin.scala:90)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.IllegalArgumentException: Initial capacity must be greater
than 0
at
org.apache.spark.unsafe.map.BytesToBytesMap.<init>(BytesToBytesMap.java:185)
at
org.apache.spark.unsafe.map.BytesToBytesMap.<init>(BytesToBytesMap.java:203)
at
org.apache.spark.sql.execution.joins.UnsafeHashedRelation$$anonfun$readExternal$1.apply$mcV$sp(HashedRelation.scala:295)
at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1261)
... 40 more
{code}
> TPCDS Q73 Fails
> ---------------
>
> Key: SPARK-9831
> URL: https://issues.apache.org/jira/browse/SPARK-9831
> Project: Spark
> Issue Type: Sub-task
> Components: SQL
> Reporter: Michael Armbrust
> Assignee: Davies Liu
> Priority: Blocker
>
> {code}
> select
> c_last_name,
> c_first_name,
> c_salutation,
> c_preferred_cust_flag,
> ss_ticket_number,
> cnt
> from
> (select
> ss_ticket_number,
> ss_customer_sk,
> count(*) cnt
> from
> store_sales
> join household_demographics on (store_sales.ss_hdemo_sk =
> household_demographics.hd_demo_sk)
> join store on (store_sales.ss_store_sk = store.s_store_sk)
> -- join date_dim on (store_sales.ss_sold_date_sk = date_dim.d_date_sk)
> where
> store.s_county in ('Saginaw County', 'Sumner County', 'Appanoose County',
> 'Daviess County')
> -- and date_dim.d_dom between 1 and 2
> -- and date_dim.d_year in(1998, 1998 + 1, 1998 + 2)
> -- and ss_date between '1999-01-01' and '2001-12-02'
> -- and dayofmonth(ss_date) in (1,2)
> -- partition key filter
> -- and ss_sold_date_sk in (2450816, 2450846, 2450847, 2450874, 2450875,
> 2450905, 2450906, 2450935, 2450936, 2450966, 2450967,
> -- 2450996, 2450997, 2451027, 2451028, 2451058,
> 2451059, 2451088, 2451089, 2451119, 2451120, 2451149,
> -- 2451150, 2451180, 2451181, 2451211, 2451212,
> 2451239, 2451240, 2451270, 2451271, 2451300, 2451301,
> -- 2451331, 2451332, 2451361, 2451362, 2451392,
> 2451393, 2451423, 2451424, 2451453, 2451454, 2451484,
> -- 2451485, 2451514, 2451515, 2451545, 2451546,
> 2451576, 2451577, 2451605, 2451606, 2451636, 2451637,
> -- 2451666, 2451667, 2451697, 2451698, 2451727,
> 2451728, 2451758, 2451759, 2451789, 2451790, 2451819,
> -- 2451820, 2451850, 2451851, 2451880, 2451881)
> and (household_demographics.hd_buy_potential = '>10000'
> or household_demographics.hd_buy_potential = 'unknown')
> and household_demographics.hd_vehicle_count > 0
> and case when household_demographics.hd_vehicle_count > 0 then
> household_demographics.hd_dep_count / household_demographics.hd_vehicle_count
> else null end > 1
> and ss_sold_date_sk between 2451180 and 2451269 -- partition key filter
> (3 months)
> group by
> ss_ticket_number,
> ss_customer_sk
> ) dj
> join customer on (dj.ss_customer_sk = customer.c_customer_sk)
> where
> cnt between 1 and 5
> order by
> cnt desc
> limit 1000
> {code}
> {code}
> Job aborted due to stage failure: Task 63 in stage 57.0 failed 4 times, most
> recent failure: Lost task 63.3 in stage 57.0 (TID 5103, 10.0.197.102):
> java.io.IOException: java.lang.IllegalArgumentException: Initial capacity
> must be greater than 0
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1264)
> at
> org.apache.spark.sql.execution.joins.UnsafeHashedRelation.readExternal(HashedRelation.scala:280)
> at
> java.io.ObjectInputStream.readExternalData(ObjectInputStream.java:1837)
> at
> java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
> at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350)
> at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
> at
> org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:72)
> at
> org.apache.spark.broadcast.TorrentBroadcast$.unBlockifyObject(TorrentBroadcast.scala:217)
> at
> org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:178)
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1276)
> at
> org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:165)
> at
> org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:64)
> at
> org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:64)
> at
> org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:88)
> at org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70)
> at
> org.apache.spark.sql.execution.joins.BroadcastHashJoin$$anonfun$2.apply(BroadcastHashJoin.scala:91)
> at
> org.apache.spark.sql.execution.joins.BroadcastHashJoin$$anonfun$2.apply(BroadcastHashJoin.scala:90)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
> at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.IllegalArgumentException: Initial capacity must be
> greater than 0
> at
> org.apache.spark.unsafe.map.BytesToBytesMap.<init>(BytesToBytesMap.java:185)
> at
> org.apache.spark.unsafe.map.BytesToBytesMap.<init>(BytesToBytesMap.java:203)
> at
> org.apache.spark.sql.execution.joins.UnsafeHashedRelation$$anonfun$readExternal$1.apply$mcV$sp(HashedRelation.scala:295)
> at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1261)
> ... 40 more
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
