Rahul Challapalli created DRILL-5522:
----------------------------------------
Summary: OOM during the merge and spill process of the managed
external sort
Key: DRILL-5522
URL: https://issues.apache.org/jira/browse/DRILL-5522
Project: Apache Drill
Issue Type: Bug
Components: Execution - Relational Operators
Affects Versions: 1.10.0
Reporter: Rahul Challapalli
Assignee: Paul Rogers
git.commit.id.abbrev=1e0a14c
The below query fails with an OOM
{code}
ALTER SESSION SET `exec.sort.disable_managed` = false;
alter session set `planner.memory.max_query_memory_per_node` = 1552428800;
create table dfs.drillTestDir.xsort_ctas3_multiple partition by (type, aCol) as
select type, rptds, rms, s3.rms.a aCol, uid from (
select * from (
select s1.type type, flatten(s1.rms.rptd) rptds, s1.rms, s1.uid
from (
select d.type type, d.uid uid, flatten(d.map.rm) rms from
dfs.`/drill/testdata/resource-manager/nested-large.json` d order by d.uid
) s1
) s2
order by s2.rms.mapid, s2.rptds.a
) s3;
{code}
Stack trace
{code}
2017-05-17 15:15:35,027 [26e334aa-1afa-753f-3afe-862f76b80c18:frag:4:2] INFO
o.a.d.e.w.fragment.FragmentExecutor - User Error Occurred: One or more nodes
ran out of memory while executing the query. (Unable to allocate buffer of size
2097152 due to memory limit. Current allocation: 29229064)
org.apache.drill.common.exceptions.UserException: RESOURCE ERROR: One or more
nodes ran out of memory while executing the query.
Unable to allocate buffer of size 2097152 due to memory limit. Current
allocation: 29229064
[Error Id: 619e2e34-704c-4964-a354-1348fb33ce8a ]
at
org.apache.drill.common.exceptions.UserException$Builder.build(UserException.java:544)
~[drill-common-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.work.fragment.FragmentExecutor.run(FragmentExecutor.java:244)
[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.common.SelfCleaningRunnable.run(SelfCleaningRunnable.java:38)
[drill-common-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
[na:1.7.0_111]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
[na:1.7.0_111]
at java.lang.Thread.run(Thread.java:745) [na:1.7.0_111]
Caused by: org.apache.drill.exec.exception.OutOfMemoryException: Unable to
allocate buffer of size 2097152 due to memory limit. Current allocation:
29229064
at
org.apache.drill.exec.memory.BaseAllocator.buffer(BaseAllocator.java:220)
~[drill-memory-base-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.memory.BaseAllocator.buffer(BaseAllocator.java:195)
~[drill-memory-base-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.vector.BigIntVector.reAlloc(BigIntVector.java:212)
~[vector-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.vector.BigIntVector.copyFromSafe(BigIntVector.java:324)
~[vector-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.vector.NullableBigIntVector.copyFromSafe(NullableBigIntVector.java:367)
~[vector-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.vector.NullableBigIntVector$TransferImpl.copyValueSafe(NullableBigIntVector.java:328)
~[vector-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.RepeatedMapVector$RepeatedMapTransferPair.copyValueSafe(RepeatedMapVector.java:360)
~[vector-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.MapVector$MapTransferPair.copyValueSafe(MapVector.java:220)
~[vector-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.MapVector.copyFromSafe(MapVector.java:82)
~[vector-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.test.generated.PriorityQueueCopierGen49.doCopy(PriorityQueueCopierTemplate.java:34)
~[na:na]
at
org.apache.drill.exec.test.generated.PriorityQueueCopierGen49.next(PriorityQueueCopierTemplate.java:76)
~[na:na]
at
org.apache.drill.exec.physical.impl.xsort.managed.CopierHolder$BatchMerger.next(CopierHolder.java:234)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.xsort.managed.ExternalSortBatch.mergeSpilledRuns(ExternalSortBatch.java:1214)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.xsort.managed.ExternalSortBatch.load(ExternalSortBatch.java:689)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.xsort.managed.ExternalSortBatch.innerNext(ExternalSortBatch.java:559)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:162)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:215)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:119)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:109)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.svremover.RemovingRecordBatch.innerNext(RemovingRecordBatch.java:93)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:162)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:215)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:104)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.SingleSenderCreator$SingleSenderRootExec.innerNext(SingleSenderCreator.java:92)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:94)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:234)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:227)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at java.security.AccessController.doPrivileged(Native Method)
~[na:1.7.0_111]
at javax.security.auth.Subject.doAs(Subject.java:415) ~[na:1.7.0_111]
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1595)
~[hadoop-common-2.7.0-mapr-1607.jar:na]
at
org.apache.drill.exec.work.fragment.FragmentExecutor.run(FragmentExecutor.java:227)
[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
... 4 common frames omitted
{code}
I attached the logs and the profile files. The data set is too large to attach
here
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
