[HIVE-10776] Schema on insert for bucketed tables throwing NullPointerException - ASF JIRA

Log work

Agile Board

Rank to Top

Rank to Bottom

Bulk Copy Attachments

Bulk Move Attachments

Voters

Watch issue

Watchers

Create sub-task

Convert to sub-task

Move

Link

Clone

Labels

Update Comment Author

Replace String in Comment

Update Comment Visibility

Delete Comments

XML

Word

Printable

JSON

Details

Type: Bug
Status: Resolved
Priority: Major
Resolution: Fixed
Affects Version/s: 1.2.0
Fix Version/s: 1.2.1
Component/s: Hive
Labels:
None
Environment:

Linux, Windows

Description

Hive schema on insert queries, with select * , are failing with below exception

2015-05-15 19:29:01,278 ERROR [main]: ql.Driver (SessionState.java:printError(957)) - FAILED: NullPointerException null
java.lang.NullPointerException
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genReduceSinkPlan(SemanticAnalyzer.java:7257)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genBucketingSortingDest(SemanticAnalyzer.java:6100)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genFileSinkPlan(SemanticAnalyzer.java:6271)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genPostGroupByBodyPlan(SemanticAnalyzer.java:8972)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genBodyPlan(SemanticAnalyzer.java:8863)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genPlan(SemanticAnalyzer.java:9708)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genPlan(SemanticAnalyzer.java:9601)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.genOPTree(SemanticAnalyzer.java:10037)
        at org.apache.hadoop.hive.ql.parse.CalcitePlanner.genOPTree(CalcitePlanner.java:323)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:10048)
        at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:207)
        at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:227)
        at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:424)
        at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:308)
        at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1122)
        at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1170)
        at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1059)
        at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1049)
        at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:213)
        at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:165)
        at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
        at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:311)
        at org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:409)
        at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:425)
        at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:714)
        at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:681)
        at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:621)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:606)
        at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
        at org.apache.hadoop.util.RunJar.main(RunJar.java:136)

Steps to reproduce

set hive.support.concurrency=true;
set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager;
set hive.enforce.bucketing=true;

drop table if exists studenttab10k;
create table studenttab10k (age int, name varchar(50),gpa decimal(3,2));
insert into studenttab10k values(1,'foo', 1.1), (2,'bar', 2.3),(3,'baz', 3.1);


drop table if exists student_acid;
create table student_acid (age int, name varchar(50),gpa decimal(3,2), grade int) 
clustered by (age) into 2 buckets
stored as orc
tblproperties ('transactional'='true');

insert into student_acid(name,age,gpa) select * from studenttab10k;