Stamatis Zampetakis created HIVE-25611:
------------------------------------------
Summary: OOM when running MERGE query on wide transactional table
with many buckets
Key: HIVE-25611
URL: https://issues.apache.org/jira/browse/HIVE-25611
Project: Hive
Issue Type: Bug
Components: Query Processor
Reporter: Stamatis Zampetakis
Assignee: Stamatis Zampetakis
Attachments: merge_query_plan.txt, merge_wide_acid_bucketed_table.q,
wide_table_100_char_cols.csv
Running a {{MERGE}} statement over a wide transactional/ACID table with many
buckets leads to {{OutOfMemoryError}} during the execution of the query.
A step-by-step reproducer is attached to the case (
[^merge_wide_acid_bucketed_table.q] [^wide_table_100_char_cols.csv] ) but the
main idea is outlined below.
{code:sql}
CREATE TABLE wide_table_txt (
w_id_col int,
w_char_col0 char(20),
...
w_char_col99 char(20)) STORED AS ORC TBLPROPERTIES ('transactional'='true')
-- Load data into the table in a way that it gets bucketed
CREATE TABLE simple_table_txt (id int, name char(20)) STORED AS TEXTFILE;
-- Load data into simple_table_txt overlapping with the data in wide_table_txt
MERGE INTO wide_table_orc target USING simple_table_txt source ON
(target.w_id_col = source.id)
WHEN MATCHED THEN UPDATE SET w_char_col0 = source.name
WHEN NOT MATCHED THEN INSERT (w_id_col, w_char_col1) VALUES (source.id, 'Actual
value does not matter');
{code}
A sample stacktrace showing the memory pressure is given below:
{noformat}
java.lang.OutOfMemoryError: GC overhead limit exceeded
at
org.apache.orc.OrcProto$RowIndexEntry$Builder.create(OrcProto.java:8962)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.OrcProto$RowIndexEntry$Builder.access$12100(OrcProto.java:8931)
~[orc-core-1.6.9.jar:1.6.9]
at org.apache.orc.OrcProto$RowIndexEntry.newBuilder(OrcProto.java:8915)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriterBase.<init>(TreeWriterBase.java:98)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.StringBaseTreeWriter.<init>(StringBaseTreeWriter.java:66)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.CharTreeWriter.<init>(CharTreeWriter.java:40)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.createSubtree(TreeWriter.java:163)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.create(TreeWriter.java:133)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.StructTreeWriter.<init>(StructTreeWriter.java:41)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.createSubtree(TreeWriter.java:181)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.create(TreeWriter.java:133)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.StructTreeWriter.<init>(StructTreeWriter.java:41)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.createSubtree(TreeWriter.java:181)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.create(TreeWriter.java:133)
~[orc-core-1.6.9.jar:1.6.9]
at org.apache.orc.impl.WriterImpl.<init>(WriterImpl.java:216)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.hadoop.hive.ql.io.orc.WriterImpl.<init>(WriterImpl.java:95)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcFile.createWriter(OrcFile.java:396)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcRecordUpdater.initWriter(OrcRecordUpdater.java:615)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcRecordUpdater.addSimpleEvent(OrcRecordUpdater.java:442)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcRecordUpdater.addSplitUpdateEvent(OrcRecordUpdater.java:495)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcRecordUpdater.update(OrcRecordUpdater.java:519)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.FileSinkOperator.process(FileSinkOperator.java:1200)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.vector.VectorFileSinkOperator.process(VectorFileSinkOperator.java:111)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.Operator.vectorForward(Operator.java:919)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:158)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.processVectorGroup(ReduceRecordSource.java:497)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.pushRecordVector(ReduceRecordSource.java:399)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.pushRecord(ReduceRecordSource.java:256)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordProcessor.run(ReduceRecordProcessor.java:291)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:311)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.TezProcessor.run(TezProcessor.java:277)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.run(LogicalIOProcessorRuntimeTask.java:381)
~[tez-runtime-internals-0.10.1.jar:0.10.1]
2021-10-12T10:31:57,723 INFO [TezTR-775147_1_3_4_0_0] task.TezTaskRunner2:
Received notification of a failure which will cause the task to die
java.lang.OutOfMemoryError: GC overhead limit exceeded
at
org.apache.orc.OrcProto$RowIndexEntry$Builder.create(OrcProto.java:8962)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.OrcProto$RowIndexEntry$Builder.access$12100(OrcProto.java:8931)
~[orc-core-1.6.9.jar:1.6.9]
at org.apache.orc.OrcProto$RowIndexEntry.newBuilder(OrcProto.java:8915)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriterBase.<init>(TreeWriterBase.java:98)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.StringBaseTreeWriter.<init>(StringBaseTreeWriter.java:66)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.CharTreeWriter.<init>(CharTreeWriter.java:40)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.createSubtree(TreeWriter.java:163)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.create(TreeWriter.java:133)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.StructTreeWriter.<init>(StructTreeWriter.java:41)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.createSubtree(TreeWriter.java:181)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.create(TreeWriter.java:133)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.StructTreeWriter.<init>(StructTreeWriter.java:41)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.createSubtree(TreeWriter.java:181)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.orc.impl.writer.TreeWriter$Factory.create(TreeWriter.java:133)
~[orc-core-1.6.9.jar:1.6.9]
at org.apache.orc.impl.WriterImpl.<init>(WriterImpl.java:216)
~[orc-core-1.6.9.jar:1.6.9]
at
org.apache.hadoop.hive.ql.io.orc.WriterImpl.<init>(WriterImpl.java:95)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcFile.createWriter(OrcFile.java:396)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcRecordUpdater.initWriter(OrcRecordUpdater.java:615)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcRecordUpdater.addSimpleEvent(OrcRecordUpdater.java:442)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcRecordUpdater.addSplitUpdateEvent(OrcRecordUpdater.java:495)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.io.orc.OrcRecordUpdater.update(OrcRecordUpdater.java:519)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.FileSinkOperator.process(FileSinkOperator.java:1200)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.vector.VectorFileSinkOperator.process(VectorFileSinkOperator.java:111)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.Operator.vectorForward(Operator.java:919)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:158)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.processVectorGroup(ReduceRecordSource.java:497)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.pushRecordVector(ReduceRecordSource.java:399)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordSource.pushRecord(ReduceRecordSource.java:256)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordProcessor.run(ReduceRecordProcessor.java:291)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
at
org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:311)
~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
{noformat}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
