[ 
https://issues.apache.org/jira/browse/DRILL-5670?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16154349#comment-16154349
 ] 

Robert Hou commented on DRILL-5670:
-----------------------------------

Here is the plan.  There is a StreamAgg.  Can that affect things?

{noformat}
| 00-00    Screen
00-01      Project(EXPR$0=[$0])
00-02        StreamAgg(group=[{}], EXPR$0=[$SUM0($0)])
00-03          UnionExchange
01-01            StreamAgg(group=[{}], EXPR$0=[COUNT()])
01-02              Project($f0=[0])
01-03                SelectionVectorRemover
01-04                  Filter(condition=[=(ITEM($0, 'col433'), 'sjka skjf')])
01-05                    Project(T1¦¦*=[$0])
01-06                      SingleMergeExchange(sort0=[1 ASC], sort1=[2 ASC], 
sort2=[3 ASC], sort3=[4 ASC], sort4=[5 ASC], sort5=[6 ASC], sort6=[7 ASC], 
sort7=[8 ASC], sort8=[9 ASC], sort9=[10 ASC], sort10=[11 ASC], sort11=[12 ASC], 
sort12=[9 ASC], sort13=[13 ASC], sort14=[14 ASC], sort15=[15 ASC], sort16=[16 
ASC], sort17=[17 ASC], sort18=[18 ASC], sort19=[19 ASC], sort20=[20 ASC], 
sort21=[21 ASC], sort22=[12 ASC], sort23=[22 ASC], sort24=[23 ASC], sort25=[24 
ASC], sort26=[25 ASC], sort27=[26 ASC], sort28=[27 ASC], sort29=[28 ASC], 
sort30=[29 ASC], sort31=[30 ASC], sort32=[31 ASC], sort33=[32 ASC], sort34=[33 
ASC], sort35=[34 ASC], sort36=[35 ASC], sort37=[36 ASC], sort38=[37 ASC], 
sort39=[38 ASC], sort40=[39 ASC], sort41=[40 ASC], sort42=[41 ASC], sort43=[42 
ASC], sort44=[43 ASC], sort45=[44 ASC], sort46=[45 ASC], sort47=[46 ASC])
02-01                        SelectionVectorRemover
02-02                          Sort(sort0=[$1], sort1=[$2], sort2=[$3], 
sort3=[$4], sort4=[$5], sort5=[$6], sort6=[$7], sort7=[$8], sort8=[$9], 
sort9=[$10], sort10=[$11], sort11=[$12], sort12=[$9], sort13=[$13], 
sort14=[$14], sort15=[$15], sort16=[$16], sort17=[$17], sort18=[$18], 
sort19=[$19], sort20=[$20], sort21=[$21], sort22=[$12], sort23=[$22], 
sort24=[$23], sort25=[$24], sort26=[$25], sort27=[$26], sort28=[$27], 
sort29=[$28], sort30=[$29], sort31=[$30], sort32=[$31], sort33=[$32], 
sort34=[$33], sort35=[$34], sort36=[$35], sort37=[$36], sort38=[$37], 
sort39=[$38], sort40=[$39], sort41=[$40], sort42=[$41], sort43=[$42], 
sort44=[$43], sort45=[$44], sort46=[$45], sort47=[$46], dir0=[ASC], dir1=[ASC], 
dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], 
dir8=[ASC], dir9=[ASC], dir10=[ASC], dir11=[ASC], dir12=[ASC], dir13=[ASC], 
dir14=[ASC], dir15=[ASC], dir16=[ASC], dir17=[ASC], dir18=[ASC], dir19=[ASC], 
dir20=[ASC], dir21=[ASC], dir22=[ASC], dir23=[ASC], dir24=[ASC], dir25=[ASC], 
dir26=[ASC], dir27=[ASC], dir28=[ASC], dir29=[ASC], dir30=[ASC], dir31=[ASC], 
dir32=[ASC], dir33=[ASC], dir34=[ASC], dir35=[ASC], dir36=[ASC], dir37=[ASC], 
dir38=[ASC], dir39=[ASC], dir40=[ASC], dir41=[ASC], dir42=[ASC], dir43=[ASC], 
dir44=[ASC], dir45=[ASC], dir46=[ASC], dir47=[ASC])
02-03                            Project(T1¦¦*=[$0], EXPR$1=[$1], EXPR$2=[$2], 
EXPR$3=[$3], EXPR$4=[$4], EXPR$5=[$5], EXPR$6=[$6], EXPR$7=[$7], EXPR$8=[$8], 
EXPR$9=[$9], EXPR$10=[$10], EXPR$11=[$11], EXPR$12=[$12], EXPR$13=[$13], 
EXPR$14=[$14], EXPR$15=[$15], EXPR$16=[$16], EXPR$17=[$17], EXPR$18=[$18], 
EXPR$19=[$19], EXPR$20=[$20], EXPR$21=[$21], EXPR$22=[$22], EXPR$23=[$23], 
EXPR$24=[$24], EXPR$25=[$25], EXPR$26=[$26], EXPR$27=[$27], EXPR$28=[$28], 
EXPR$29=[$29], EXPR$30=[$30], EXPR$31=[$31], EXPR$32=[$32], EXPR$33=[$33], 
EXPR$34=[$34], EXPR$35=[$35], EXPR$36=[$36], EXPR$37=[$37], EXPR$38=[$38], 
EXPR$39=[$39], EXPR$40=[$40], EXPR$41=[$41], EXPR$42=[$42], EXPR$43=[$43], 
EXPR$44=[$44], EXPR$45=[$45], EXPR$46=[$46])
02-04                              HashToRandomExchange(dist0=[[$1]], 
dist1=[[$2]], dist2=[[$3]], dist3=[[$4]], dist4=[[$5]], dist5=[[$6]], 
dist6=[[$7]], dist7=[[$8]], dist8=[[$9]], dist9=[[$10]], dist10=[[$11]], 
dist11=[[$12]], dist12=[[$9]], dist13=[[$13]], dist14=[[$14]], dist15=[[$15]], 
dist16=[[$16]], dist17=[[$17]], dist18=[[$18]], dist19=[[$19]], dist20=[[$20]], 
dist21=[[$21]], dist22=[[$12]], dist23=[[$22]], dist24=[[$23]], dist25=[[$24]], 
dist26=[[$25]], dist27=[[$26]], dist28=[[$27]], dist29=[[$28]], dist30=[[$29]], 
dist31=[[$30]], dist32=[[$31]], dist33=[[$32]], dist34=[[$33]], dist35=[[$34]], 
dist36=[[$35]], dist37=[[$36]], dist38=[[$37]], dist39=[[$38]], dist40=[[$39]], 
dist41=[[$40]], dist42=[[$41]], dist43=[[$42]], dist44=[[$43]], dist45=[[$44]], 
dist46=[[$45]], dist47=[[$46]])
03-01                                UnorderedMuxExchange
04-01                                  Project(T1¦¦*=[$0], EXPR$1=[$1], 
EXPR$2=[$2], EXPR$3=[$3], EXPR$4=[$4], EXPR$5=[$5], EXPR$6=[$6], EXPR$7=[$7], 
EXPR$8=[$8], EXPR$9=[$9], EXPR$10=[$10], EXPR$11=[$11], EXPR$12=[$12], 
EXPR$13=[$13], EXPR$14=[$14], EXPR$15=[$15], EXPR$16=[$16], EXPR$17=[$17], 
EXPR$18=[$18], EXPR$19=[$19], EXPR$20=[$20], EXPR$21=[$21], EXPR$22=[$22], 
EXPR$23=[$23], EXPR$24=[$24], EXPR$25=[$25], EXPR$26=[$26], EXPR$27=[$27], 
EXPR$28=[$28], EXPR$29=[$29], EXPR$30=[$30], EXPR$31=[$31], EXPR$32=[$32], 
EXPR$33=[$33], EXPR$34=[$34], EXPR$35=[$35], EXPR$36=[$36], EXPR$37=[$37], 
EXPR$38=[$38], EXPR$39=[$39], EXPR$40=[$40], EXPR$41=[$41], EXPR$42=[$42], 
EXPR$43=[$43], EXPR$44=[$44], EXPR$45=[$45], EXPR$46=[$46], 
E_X_P_R_H_A_S_H_F_I_E_L_D=[hash32AsDouble($46, hash32AsDouble($45, 
hash32AsDouble($44, hash32AsDouble($43, hash32AsDouble($42, hash32AsDouble($41, 
hash32AsDouble($40, hash32AsDouble($39, hash32AsDouble($38, hash32AsDouble($37, 
hash32AsDouble($36, hash32AsDouble($35, hash32AsDouble($34, hash32AsDouble($33, 
hash32AsDouble($32, hash32AsDouble($31, hash32AsDouble($30, hash32AsDouble($29, 
hash32AsDouble($28, hash32AsDouble($27, hash32AsDouble($26, hash32AsDouble($25, 
hash32AsDouble($24, hash32AsDouble($23, hash32AsDouble($22, hash32AsDouble($12, 
hash32AsDouble($21, hash32AsDouble($20, hash32AsDouble($19, hash32AsDouble($18, 
hash32AsDouble($17, hash32AsDouble($16, hash32AsDouble($15, hash32AsDouble($14, 
hash32AsDouble($13, hash32AsDouble($9, hash32AsDouble($12, hash32AsDouble($11, 
hash32AsDouble($10, hash32AsDouble($9, hash32AsDouble($8, hash32AsDouble($7, 
hash32AsDouble($6, hash32AsDouble($5, hash32AsDouble($4, hash32AsDouble($3, 
hash32AsDouble($2, hash32AsDouble($1, 
1301011))))))))))))))))))))))))))))))))))))))))))))))))])
04-02                                    Project(T1¦¦*=[$0], EXPR$1=[ITEM($1, 
450)], EXPR$2=[ITEM($1, 330)], EXPR$3=[ITEM($1, 230)], EXPR$4=[ITEM($1, 220)], 
EXPR$5=[ITEM($1, 110)], EXPR$6=[ITEM($1, 90)], EXPR$7=[ITEM($1, 80)], 
EXPR$8=[ITEM($1, 70)], EXPR$9=[ITEM($1, 40)], EXPR$10=[ITEM($1, 10)], 
EXPR$11=[ITEM($1, 20)], EXPR$12=[ITEM($1, 30)], EXPR$13=[ITEM($1, 50)], 
EXPR$14=[ITEM($1, 454)], EXPR$15=[ITEM($1, 413)], EXPR$16=[ITEM($1, 940)], 
EXPR$17=[ITEM($1, 834)], EXPR$18=[ITEM($1, 73)], EXPR$19=[ITEM($1, 140)], 
EXPR$20=[ITEM($1, 104)], EXPR$21=[ITEM($1, 2222)], EXPR$22=[ITEM($1, 2420)], 
EXPR$23=[ITEM($1, 1520)], EXPR$24=[ITEM($1, 1410)], EXPR$25=[ITEM($1, 1110)], 
EXPR$26=[ITEM($1, 1290)], EXPR$27=[ITEM($1, 2380)], EXPR$28=[ITEM($1, 705)], 
EXPR$29=[ITEM($1, 45)], EXPR$30=[ITEM($1, 1054)], EXPR$31=[ITEM($1, 2430)], 
EXPR$32=[ITEM($1, 420)], EXPR$33=[ITEM($1, 404)], EXPR$34=[ITEM($1, 3350)], 
EXPR$35=[ITEM($1, 3333)], EXPR$36=[ITEM($1, 153)], EXPR$37=[ITEM($1, 356)], 
EXPR$38=[ITEM($1, 84)], EXPR$39=[ITEM($1, 745)], EXPR$40=[ITEM($1, 1450)], 
EXPR$41=[ITEM($1, 103)], EXPR$42=[ITEM($1, 2065)], EXPR$43=[ITEM($1, 343)], 
EXPR$44=[ITEM($1, 3420)], EXPR$45=[ITEM($1, 530)], EXPR$46=[ITEM($1, 3210)])
04-03                                      Project(T1¦¦*=[$0], columns=[$1])
04-04                                        Scan(groupscan=[EasyGroupScan 
[selectionRoot=maprfs:/drill/testdata/resource-manager/3500cols.tbl, 
numFiles=1, columns=[`*`], 
files=[maprfs:///drill/testdata/resource-manager/3500cols.tbl]]])
{noformat}

> Varchar vector throws an assertion error when allocating a new vector
> ---------------------------------------------------------------------
>
>                 Key: DRILL-5670
>                 URL: https://issues.apache.org/jira/browse/DRILL-5670
>             Project: Apache Drill
>          Issue Type: Bug
>          Components: Execution - Relational Operators
>    Affects Versions: 1.11.0
>            Reporter: Rahul Challapalli
>            Assignee: Paul Rogers
>             Fix For: 1.12.0
>
>         Attachments: 26555749-4d36-10d2-6faf-e403db40c370.sys.drill, 
> 266290f3-5fdc-5873-7372-e9ee053bf867.sys.drill, 
> 269969ca-8d4d-073a-d916-9031e3d3fbf0.sys.drill, drillbit.log, drillbit.log, 
> drillbit.log, drillbit.out, drill-override.conf
>
>
> I am running this test on a private branch of [paul's 
> repository|https://github.com/paul-rogers/drill]. Below is the commit info
> {code}
> git.commit.id.abbrev=d86e16c
> [email protected]
> git.commit.message.full=DRILL-5601\: Rollup of external sort fixes an 
> improvements\n\n- DRILL-5513\: Managed External Sort \: OOM error during the 
> merge phase\n- DRILL-5519\: Sort fails to spill and results in an OOM\n- 
> DRILL-5522\: OOM during the merge and spill process of the managed external 
> sort\n- DRILL-5594\: Excessive buffer reallocations during merge phase of 
> external sort\n- DRILL-5597\: Incorrect "bits" vector allocation in nullable 
> vectors allocateNew()\n- DRILL-5602\: Repeated List Vector fails to 
> initialize the offset vector\n\nAll of the bugs have to do with handling 
> low-memory conditions, and with\ncorrectly estimating the sizes of vectors, 
> even when those vectors come\nfrom the spill file or from an exchange. Hence, 
> the changes for all of\nthe above issues are interrelated.\n
> git.commit.id=d86e16c551e7d3553f2cde748a739b1c5a7a7659
> git.commit.message.short=DRILL-5601\: Rollup of external sort fixes an 
> improvements
> git.commit.user.name=Paul Rogers
> git.build.user.name=Rahul Challapalli
> git.commit.id.describe=0.9.0-1078-gd86e16c
> [email protected]
> git.branch=d86e16c551e7d3553f2cde748a739b1c5a7a7659
> git.commit.time=05.07.2017 @ 20\:34\:39 PDT
> git.build.time=12.07.2017 @ 14\:27\:03 PDT
> [email protected]\:paul-rogers/drill.git
> {code}
> Below query fails with an Assertion Error
> {code}
> 0: jdbc:drill:zk=10.10.100.190:5181> ALTER SESSION SET 
> `exec.sort.disable_managed` = false;
> +-------+-------------------------------------+
> |  ok   |               summary               |
> +-------+-------------------------------------+
> | true  | exec.sort.disable_managed updated.  |
> +-------+-------------------------------------+
> 1 row selected (1.044 seconds)
> 0: jdbc:drill:zk=10.10.100.190:5181> alter session set 
> `planner.memory.max_query_memory_per_node` = 482344960;
> +-------+----------------------------------------------------+
> |  ok   |                      summary                       |
> +-------+----------------------------------------------------+
> | true  | planner.memory.max_query_memory_per_node updated.  |
> +-------+----------------------------------------------------+
> 1 row selected (0.372 seconds)
> 0: jdbc:drill:zk=10.10.100.190:5181> alter session set 
> `planner.width.max_per_node` = 1;
> +-------+--------------------------------------+
> |  ok   |               summary                |
> +-------+--------------------------------------+
> | true  | planner.width.max_per_node updated.  |
> +-------+--------------------------------------+
> 1 row selected (0.292 seconds)
> 0: jdbc:drill:zk=10.10.100.190:5181> alter session set 
> `planner.width.max_per_query` = 1;
> +-------+---------------------------------------+
> |  ok   |                summary                |
> +-------+---------------------------------------+
> | true  | planner.width.max_per_query updated.  |
> +-------+---------------------------------------+
> 1 row selected (0.25 seconds)
> 0: jdbc:drill:zk=10.10.100.190:5181> select count(*) from (select * from 
> dfs.`/drill/testdata/resource-manager/3500cols.tbl` order by 
> columns[450],columns[330],columns[230],columns[220],columns[110],columns[90],columns[80],columns[70],columns[40],columns[10],columns[20],columns[30],columns[40],columns[50],
>  
> columns[454],columns[413],columns[940],columns[834],columns[73],columns[140],columns[104],columns[2222],columns[30],columns[2420],columns[1520],
>  columns[1410], 
> columns[1110],columns[1290],columns[2380],columns[705],columns[45],columns[1054],columns[2430],columns[420],columns[404],columns[3350],
>  
> columns[3333],columns[153],columns[356],columns[84],columns[745],columns[1450],columns[103],columns[2065],columns[343],columns[3420],columns[530],
>  columns[3210] ) d where d.col433 = 'sjka skjf';
> Error: RESOURCE ERROR: External Sort encountered an error while spilling to 
> disk
> Fragment 2:0
> [Error Id: 26b55576-1a5c-4756-96d6-fbec25eecf03 on qa-node190.qa.lab:31010]
>   (java.lang.AssertionError) null
>     org.apache.drill.exec.vector.VarCharVector.allocateNew():400
>     org.apache.drill.exec.vector.RepeatedVarCharVector.allocateNew():272
>     
> org.apache.drill.exec.vector.AllocationHelper.allocatePrecomputedChildCount():37
>     org.apache.drill.exec.vector.AllocationHelper.allocate():44
>     org.apache.drill.exec.record.SmartAllocationHelper.allocateVector():117
>     org.apache.drill.exec.record.SmartAllocationHelper.allocateVector():97
>     org.apache.drill.exec.record.SmartAllocationHelper.allocateBatch():87
>     
> org.apache.drill.exec.physical.impl.xsort.managed.PriorityQueueCopierWrapper$BatchMerger.next():262
>     
> org.apache.drill.exec.physical.impl.xsort.managed.SpilledRuns.doMergeAndSpill():171
>     
> org.apache.drill.exec.physical.impl.xsort.managed.SpilledRuns.safeMergeAndSpill():138
>     
> org.apache.drill.exec.physical.impl.xsort.managed.SpilledRuns.mergeAndSpill():91
>     
> org.apache.drill.exec.physical.impl.xsort.managed.SortImpl.spillFromMemory():298
>     org.apache.drill.exec.physical.impl.xsort.managed.SortImpl.addBatch():191
>     
> org.apache.drill.exec.physical.impl.xsort.managed.ExternalSortBatch.loadBatch():402
>     
> org.apache.drill.exec.physical.impl.xsort.managed.ExternalSortBatch.load():338
>     
> org.apache.drill.exec.physical.impl.xsort.managed.ExternalSortBatch.innerNext():290
>     org.apache.drill.exec.record.AbstractRecordBatch.next():162
>     
> org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next():225
>     org.apache.drill.exec.record.AbstractRecordBatch.next():119
>     org.apache.drill.exec.record.AbstractRecordBatch.next():109
>     org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext():51
>     
> org.apache.drill.exec.physical.impl.svremover.RemovingRecordBatch.innerNext():93
>     org.apache.drill.exec.record.AbstractRecordBatch.next():162
>     
> org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next():225
>     org.apache.drill.exec.physical.impl.BaseRootExec.next():105
>     
> org.apache.drill.exec.physical.impl.SingleSenderCreator$SingleSenderRootExec.innerNext():92
>     org.apache.drill.exec.physical.impl.BaseRootExec.next():95
>     org.apache.drill.exec.work.fragment.FragmentExecutor$1.run():234
>     org.apache.drill.exec.work.fragment.FragmentExecutor$1.run():227
>     java.security.AccessController.doPrivileged():-2
>     javax.security.auth.Subject.doAs():415
>     org.apache.hadoop.security.UserGroupInformation.doAs():1595
>     org.apache.drill.exec.work.fragment.FragmentExecutor.run():227
>     org.apache.drill.common.SelfCleaningRunnable.run():38
>     java.util.concurrent.ThreadPoolExecutor.runWorker():1145
>     java.util.concurrent.ThreadPoolExecutor$Worker.run():615
>     java.lang.Thread.run():745 (state=,code=0)
> {code}
> The data set is too large to attach here. Logs and profiles are attached



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

Reply via email to