[
https://issues.apache.org/jira/browse/HIVE-18593?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Amruth S updated HIVE-18593:
----------------------------
Description:
Vectorisation with some queries seem to be failing with null pointer
exceptions. This happens only with 2.3.2 release and not the older ones.
In the case, (in BytesColumnVector.java, vector[0] is null, isRepeating is
true, length[0] is 0, start[0] is 0
{code:java}
public void copySelected(
boolean selectedInUse, int[] sel, int size, BytesColumnVector output) {
// Output has nulls if and only if input has nulls.
output.noNulls = noNulls;
output.isRepeating = false;
// Handle repeating case
if (isRepeating) {
output.setVal(0, vector[0], start[0], length[0]);
output.isNull[0] = isNull[0];
output.isRepeating = true;
return;
}
{code}
Exception trace below
{code:java}
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error
while processing row
at
org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:883)
at
org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:86)
... 17 more
Caused by: java.lang.NullPointerException
at java.lang.System.arraycopy(Native Method)
at
org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector.setVal(BytesColumnVector.java:173)
at
org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector.copySelected(BytesColumnVector.java:321)
at
org.apache.hadoop.hive.ql.exec.vector.expressions.IfExprStringGroupColumnStringGroupColumn.evaluate(IfExprStringGroupColumnStringGroupColumn.java:85)
at
org.apache.hadoop.hive.ql.exec.vector.expressions.aggregates.gen.VectorUDAFMaxString.aggregateInputSelection(VectorUDAFMaxString.java:135)
at
org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeBase.processAggregators(VectorGroupByOperator.java:218)
at
org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeHashAggregate.doProcessBatch(VectorGroupByOperator.java:408)
at
org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeBase.processBatch(VectorGroupByOperator.java:179)
at
org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator.process(VectorGroupByOperator.java:1021)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
at
org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:137)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
at
org.apache.hadoop.hive.ql.exec.vector.VectorFilterOperator.process(VectorFilterOperator.java:123)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
at
org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:130)
at
org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:783)
... 18 more
{code}
*Table details*
{code:java}
CREATE TABLE `test_table`(
`a` string,
`b` string,
`c` string)
ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.orc.OrcSerde'
STORED AS INPUTFORMAT
'org.apache.hadoop.hive.ql.io.orc.OrcInputFormat'
OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat'
TBLPROPERTIES (
'orc.compress'='SNAPPY',
'orc.compress.size'='262144',
'orc.create.index'='true',
'orc.row.index.stride'='10000',
'orc.stripe.size'='268435456',
'transient_lastDdlTime'='1517556432');{code}
*Query*
{code:java}
SELECT
NVL(Max(CASE WHEN b IN ('some_literal') THEN b ELSE c END),'') AS scol
FROM test_table
GROUP BY a
LIMIT 1000;{code}
was:
Vectorisation with some queries seem to be failing with null pointer
exceptions. This happens only with 2.3.2 release and not the older ones.
In the case, (in BytesColumnVector.java, vector[0] is null, isRepeating is
true, length[0] is 0, start[0] is 0
{code:java}
public void copySelected(
boolean selectedInUse, int[] sel, int size, BytesColumnVector output) {
// Output has nulls if and only if input has nulls.
output.noNulls = noNulls;
output.isRepeating = false;
// Handle repeating case
if (isRepeating) {
output.setVal(0, vector[0], start[0], length[0]);
output.isNull[0] = isNull[0];
output.isRepeating = true;
return;
}
{code}
Exception trace below
{code:java}
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error
while processing row
at
org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:883)
at
org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:86)
... 17 more
Caused by: java.lang.NullPointerException
at java.lang.System.arraycopy(Native Method)
at
org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector.setVal(BytesColumnVector.java:173)
at
org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector.copySelected(BytesColumnVector.java:321)
at
org.apache.hadoop.hive.ql.exec.vector.expressions.IfExprStringGroupColumnStringGroupColumn.evaluate(IfExprStringGroupColumnStringGroupColumn.java:85)
at
org.apache.hadoop.hive.ql.exec.vector.expressions.aggregates.gen.VectorUDAFMaxString.aggregateInputSelection(VectorUDAFMaxString.java:135)
at
org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeBase.processAggregators(VectorGroupByOperator.java:218)
at
org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeHashAggregate.doProcessBatch(VectorGroupByOperator.java:408)
at
org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeBase.processBatch(VectorGroupByOperator.java:179)
at
org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator.process(VectorGroupByOperator.java:1021)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
at
org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:137)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
at
org.apache.hadoop.hive.ql.exec.vector.VectorFilterOperator.process(VectorFilterOperator.java:123)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
at
org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:130)
at
org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:783)
... 18 more
{code}
> NPE on vectorization group by
> -----------------------------
>
> Key: HIVE-18593
> URL: https://issues.apache.org/jira/browse/HIVE-18593
> Project: Hive
> Issue Type: Bug
> Components: Hive, HiveServer2
> Affects Versions: 2.3.2
> Reporter: Amruth S
> Priority: Major
>
> Vectorisation with some queries seem to be failing with null pointer
> exceptions. This happens only with 2.3.2 release and not the older ones.
> In the case, (in BytesColumnVector.java, vector[0] is null, isRepeating is
> true, length[0] is 0, start[0] is 0
> {code:java}
> public void copySelected(
> boolean selectedInUse, int[] sel, int size, BytesColumnVector output) {
> // Output has nulls if and only if input has nulls.
> output.noNulls = noNulls;
> output.isRepeating = false;
> // Handle repeating case
> if (isRepeating) {
> output.setVal(0, vector[0], start[0], length[0]);
> output.isNull[0] = isNull[0];
> output.isRepeating = true;
> return;
> }
> {code}
> Exception trace below
> {code:java}
> Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime
> Error while processing row
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:883)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:86)
> ... 17 more
> Caused by: java.lang.NullPointerException
> at java.lang.System.arraycopy(Native Method)
> at
> org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector.setVal(BytesColumnVector.java:173)
> at
> org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector.copySelected(BytesColumnVector.java:321)
> at
> org.apache.hadoop.hive.ql.exec.vector.expressions.IfExprStringGroupColumnStringGroupColumn.evaluate(IfExprStringGroupColumnStringGroupColumn.java:85)
> at
> org.apache.hadoop.hive.ql.exec.vector.expressions.aggregates.gen.VectorUDAFMaxString.aggregateInputSelection(VectorUDAFMaxString.java:135)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeBase.processAggregators(VectorGroupByOperator.java:218)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeHashAggregate.doProcessBatch(VectorGroupByOperator.java:408)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator$ProcessingModeBase.processBatch(VectorGroupByOperator.java:179)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorGroupByOperator.process(VectorGroupByOperator.java:1021)
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:137)
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorFilterOperator.process(VectorFilterOperator.java:123)
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:897)
> at
> org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:130)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:783)
> ... 18 more
> {code}
>
> *Table details*
> {code:java}
> CREATE TABLE `test_table`(
> `a` string,
> `b` string,
> `c` string)
> ROW FORMAT SERDE
> 'org.apache.hadoop.hive.ql.io.orc.OrcSerde'
> STORED AS INPUTFORMAT
> 'org.apache.hadoop.hive.ql.io.orc.OrcInputFormat'
> OUTPUTFORMAT
> 'org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat'
> TBLPROPERTIES (
> 'orc.compress'='SNAPPY',
> 'orc.compress.size'='262144',
> 'orc.create.index'='true',
> 'orc.row.index.stride'='10000',
> 'orc.stripe.size'='268435456',
> 'transient_lastDdlTime'='1517556432');{code}
> *Query*
> {code:java}
> SELECT
> NVL(Max(CASE WHEN b IN ('some_literal') THEN b ELSE c END),'') AS scol
> FROM test_table
> GROUP BY a
> LIMIT 1000;{code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
