[HIVE-21980] Parsing time can be high in case of deeply nested subqueries - 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: Improvement
Status: Closed
Priority: Major
Resolution: Fixed
Affects Version/s: None
Fix Version/s: 2.3.7, 2.4.0, 3.1.2, 3.2.0, 4.0.0-alpha-1
Component/s: Parser
Labels:
None

Description

for queries which are recursively doing:

SELECT ...
FROM (SELECT ...
             FROM ( [...]
             ) JOIN
            (SELECT ...
            FROM ( [...] )
JOIN ( [...]
)

when the issue is present hs2 stops right after starting compiling and the following stack is there

	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.subQuerySource(HiveParser_FromClauseParser.java:4745)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.synpred1_FromClauseParser_fragment(HiveParser_FromClauseParser.java:6513)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.synpred1_FromClauseParser(HiveParser_FromClauseParser.java:6660)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser$DFA10.specialStateTransition(HiveParser_FromClauseParser.java:6942)
	at org.antlr.runtime.DFA.predict(DFA.java:80)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.atomjoinSource(HiveParser_FromClauseParser.java:1596)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.joinSource(HiveParser_FromClauseParser.java:1859)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromSource(HiveParser_FromClauseParser.java:1532)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromClause(HiveParser_FromClauseParser.java:1375)
	at org.apache.hadoop.hive.ql.parse.HiveParser.fromClause(HiveParser.java:45755)
	at org.apache.hadoop.hive.ql.parse.HiveParser.atomSelectStatement(HiveParser.java:40337)
	at org.apache.hadoop.hive.ql.parse.HiveParser.selectStatement(HiveParser.java:40589)
	at org.apache.hadoop.hive.ql.parse.HiveParser.regularBody(HiveParser.java:40235)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpressionBody(HiveParser.java:39445)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpression(HiveParser.java:39333)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.subQuerySource(HiveParser_FromClauseParser.java:4745)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.atomjoinSource(HiveParser_FromClauseParser.java:1699)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.joinSource(HiveParser_FromClauseParser.java:1859)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromSource(HiveParser_FromClauseParser.java:1532)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromClause(HiveParser_FromClauseParser.java:1375)
	at org.apache.hadoop.hive.ql.parse.HiveParser.fromClause(HiveParser.java:45755)
	at org.apache.hadoop.hive.ql.parse.HiveParser.atomSelectStatement(HiveParser.java:40337)
	at org.apache.hadoop.hive.ql.parse.HiveParser.selectStatement(HiveParser.java:40589)
	at org.apache.hadoop.hive.ql.parse.HiveParser.regularBody(HiveParser.java:40235)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpressionBody(HiveParser.java:39445)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpression(HiveParser.java:39333)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.subQuerySource(HiveParser_FromClauseParser.java:4745)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.synpred1_FromClauseParser_fragment(HiveParser_FromClauseParser.java:6513)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.synpred1_FromClauseParser(HiveParser_FromClauseParser.java:6660)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser$DFA10.specialStateTransition(HiveParser_FromClauseParser.java:6942)
	at org.antlr.runtime.DFA.predict(DFA.java:80)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.atomjoinSource(HiveParser_FromClauseParser.java:1596)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.joinSource(HiveParser_FromClauseParser.java:1859)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromSource(HiveParser_FromClauseParser.java:1532)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromClause(HiveParser_FromClauseParser.java:1375)
	at org.apache.hadoop.hive.ql.parse.HiveParser.fromClause(HiveParser.java:45755)
	at org.apache.hadoop.hive.ql.parse.HiveParser.atomSelectStatement(HiveParser.java:40337)
	at org.apache.hadoop.hive.ql.parse.HiveParser.selectStatement(HiveParser.java:40589)
	at org.apache.hadoop.hive.ql.parse.HiveParser.regularBody(HiveParser.java:40235)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpressionBody(HiveParser.java:39445)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpression(HiveParser.java:39333)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.subQuerySource(HiveParser_FromClauseParser.java:4745)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.atomjoinSource(HiveParser_FromClauseParser.java:1699)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.joinSource(HiveParser_FromClauseParser.java:1859)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromSource(HiveParser_FromClauseParser.java:1532)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromClause(HiveParser_FromClauseParser.java:1375)
	at org.apache.hadoop.hive.ql.parse.HiveParser.fromClause(HiveParser.java:45755)
	at org.apache.hadoop.hive.ql.parse.HiveParser.atomSelectStatement(HiveParser.java:40337)
	at org.apache.hadoop.hive.ql.parse.HiveParser.selectStatement(HiveParser.java:40589)
	at org.apache.hadoop.hive.ql.parse.HiveParser.regularBody(HiveParser.java:40235)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpressionBody(HiveParser.java:39445)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpression(HiveParser.java:39333)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.subQuerySource(HiveParser_FromClauseParser.java:4745)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.atomjoinSource(HiveParser_FromClauseParser.java:1699)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.joinSource(HiveParser_FromClauseParser.java:1859)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromSource(HiveParser_FromClauseParser.java:1532)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.fromClause(HiveParser_FromClauseParser.java:1375)
	at org.apache.hadoop.hive.ql.parse.HiveParser.fromClause(HiveParser.java:45755)
	at org.apache.hadoop.hive.ql.parse.HiveParser.atomSelectStatement(HiveParser.java:40337)
	at org.apache.hadoop.hive.ql.parse.HiveParser.selectStatement(HiveParser.java:40589)
	at org.apache.hadoop.hive.ql.parse.HiveParser.regularBody(HiveParser.java:40235)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpressionBody(HiveParser.java:39445)
	at org.apache.hadoop.hive.ql.parse.HiveParser.queryStatementExpression(HiveParser.java:39333)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.subQuerySource(HiveParser_FromClauseParser.java:4745)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.synpred1_FromClauseParser_fragment(HiveParser_FromClauseParser.java:6513)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser.synpred1_FromClauseParser(HiveParser_FromClauseParser.java:6660)
	at org.apache.hadoop.hive.ql.parse.HiveParser_FromClauseParser$DFA10.specialStateTransition(HiveParser_FromClauseParser.java:6942)
	at org.antlr.runtime.DFA.predict(DFA.java:80)