[
https://issues.apache.org/jira/browse/HIVE-7745?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Brock Noland updated HIVE-7745:
-------------------------------
Description:
When the hive.optimize.union.remove, hive.merge.mapfiles and
hive.merge.mapredfiles are turned on, it throws NullPointerException when I do
the following queries:
create table inputTbl1(key string, val string) stored as textfile;
create table outputTbl1(key string, values bigint) stored as rcfile;
load data local inpath '../../data/files/T1.txt' into table inputTbl1;
{noformat}
explain
insert overwrite table outputTbl1
SELECT * FROM
(
select key, count(1) as values from inputTbl1 group by key
union all
select * FROM (
SELECT key, 1 as values from inputTbl1
UNION ALL
SELECT key, 2 as values from inputTbl1
) a
)b;
{noformat}
If the hive.merge.mapfiles and hive.merge.mapredfiles are turned off, I do not
see any error.
Here is the stack trace:
{noformat}
2014-08-16 01:32:26,849 ERROR [main]: ql.Driver
(SessionState.java:printError(681)) - FAILED: NullPointerException null
java.lang.NullPointerException
at
org.apache.hadoop.hive.ql.optimizer.GenMapRedUtils.createMoveTask(GenMapRedUtils.java:1738)
at
org.apache.hadoop.hive.ql.parse.spark.GenSparkUtils.processFileSink(GenSparkUtils.java:281)
at
org.apache.hadoop.hive.ql.parse.spark.SparkCompiler.generateTaskTree(SparkCompiler.java:187)
at
org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:199)
at
org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:9508)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:208)
at
org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:74)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:208)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:414)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:310)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1005)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1070)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:942)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:932)
at
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:246)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:198)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:408)
at
org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:781)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:675)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:614)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at org.apache.hadoop.util.RunJar.main(RunJar.java:197)
{noformat}
was:
When the hive.optimize.union.remove, hive.merge.mapfiles and
hive.merge.mapredfiles are turned on, it throws NullPointerException when I do
the following queries:
create table inputTbl1(key string, val string) stored as textfile;
create table outputTbl1(key string, values bigint) stored as rcfile;
load data local inpath '../../data/files/T1.txt' into table inputTbl1;
explain
insert overwrite table outputTbl1
SELECT * FROM
(
select key, count(1) as values from inputTbl1 group by key
union all
select * FROM (
SELECT key, 1 as values from inputTbl1
UNION ALL
SELECT key, 2 as values from inputTbl1
) a
)b;
If the hive.merge.mapfiles and hive.merge.mapredfiles are turned off, I do not
see any error.
Here is the stack trace:
{noformat}
2014-08-16 01:32:26,849 ERROR [main]: ql.Driver
(SessionState.java:printError(681)) - FAILED: NullPointerException null
java.lang.NullPointerException
at
org.apache.hadoop.hive.ql.optimizer.GenMapRedUtils.createMoveTask(GenMapRedUtils.java:1738)
at
org.apache.hadoop.hive.ql.parse.spark.GenSparkUtils.processFileSink(GenSparkUtils.java:281)
at
org.apache.hadoop.hive.ql.parse.spark.SparkCompiler.generateTaskTree(SparkCompiler.java:187)
at
org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:199)
at
org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:9508)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:208)
at
org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:74)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:208)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:414)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:310)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1005)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1070)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:942)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:932)
at
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:246)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:198)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:408)
at
org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:781)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:675)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:614)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at org.apache.hadoop.util.RunJar.main(RunJar.java:197)
{noformat}
> NullPointerException when turn on hive.optimize.union.remove,
> hive.merge.mapfiles and hive.merge.mapredfiles [Spark Branch]
> ---------------------------------------------------------------------------------------------------------------------------
>
> Key: HIVE-7745
> URL: https://issues.apache.org/jira/browse/HIVE-7745
> Project: Hive
> Issue Type: Bug
> Components: Spark
> Affects Versions: spark-branch
> Reporter: Na Yang
> Assignee: Na Yang
> Fix For: spark-branch
>
> Attachments: HIVE-7745-spark.patch
>
>
> When the hive.optimize.union.remove, hive.merge.mapfiles and
> hive.merge.mapredfiles are turned on, it throws NullPointerException when I
> do the following queries:
> create table inputTbl1(key string, val string) stored as textfile;
> create table outputTbl1(key string, values bigint) stored as rcfile;
> load data local inpath '../../data/files/T1.txt' into table inputTbl1;
> {noformat}
> explain
> insert overwrite table outputTbl1
> SELECT * FROM
> (
> select key, count(1) as values from inputTbl1 group by key
> union all
> select * FROM (
> SELECT key, 1 as values from inputTbl1
> UNION ALL
> SELECT key, 2 as values from inputTbl1
> ) a
> )b;
> {noformat}
> If the hive.merge.mapfiles and hive.merge.mapredfiles are turned off, I do
> not see any error.
> Here is the stack trace:
> {noformat}
> 2014-08-16 01:32:26,849 ERROR [main]: ql.Driver
> (SessionState.java:printError(681)) - FAILED: NullPointerException null
> java.lang.NullPointerException
> at
> org.apache.hadoop.hive.ql.optimizer.GenMapRedUtils.createMoveTask(GenMapRedUtils.java:1738)
> at
> org.apache.hadoop.hive.ql.parse.spark.GenSparkUtils.processFileSink(GenSparkUtils.java:281)
> at
> org.apache.hadoop.hive.ql.parse.spark.SparkCompiler.generateTaskTree(SparkCompiler.java:187)
> at
> org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:199)
> at
> org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:9508)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:208)
> at
> org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:74)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:208)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:414)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:310)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1005)
> at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1070)
> at org.apache.hadoop.hive.ql.Driver.run(Driver.java:942)
> at org.apache.hadoop.hive.ql.Driver.run(Driver.java:932)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:246)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:198)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:408)
> at
> org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:781)
> at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:675)
> at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:614)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
> at java.lang.reflect.Method.invoke(Method.java:597)
> at org.apache.hadoop.util.RunJar.main(RunJar.java:197)
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.2#6252)
