[ https://issues.apache.org/jira/browse/ARROW-11630?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Andrew Lamb updated ARROW-11630: -------------------------------- Summary: [Rust] Introduce partial_sort and limit option for sort kernel (was: [rust] sort performance) > [Rust] Introduce partial_sort and limit option for sort kernel > -------------------------------------------------------------- > > Key: ARROW-11630 > URL: https://issues.apache.org/jira/browse/ARROW-11630 > Project: Apache Arrow > Issue Type: Bug > Reporter: benwang li > Priority: Major > Labels: pull-request-available > Time Spent: 7h 20m > Remaining Estimate: 0h > > > 1. Use partial_sort for queries with limit expression. > {code:java} > //代码占位符 > select number from table order by numbder limit 3;{code} > We can use partial_sort (can be implemented in BinaryHeap). This can > significantly improve the sorting performance in sort && limit queries > > Refer: > [https://github.com/ClickHouse/ClickHouse/blob/f669a9f97ad850edb77d10e51cd0c41a4af737bf/src/Columns/ColumnVector.cpp#L137-L145] > [ > |https://github.com/ClickHouse/ClickHouse/blob/f669a9f97ad850edb77d10e51cd0c41a4af737bf/src/Columns/ColumnVector.cpp#L137-L145] > 2. Use pqdsort for Primitive arrays. this is already done in ClickHouse, > Refer: > [https://github.com/ClickHouse/ClickHouse/blob/f669a9f97ad850edb77d10e51cd0c41a4af737bf/src/Columns/ColumnVector.cpp#L188-L191] > > -- This message was sent by Atlassian Jira (v8.3.4#803005)