flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Kurt Young (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (FLINK-11871) Introduce LongHashTable to improve performance when join key fits in long
Date Mon, 11 Mar 2019 12:39:00 GMT

     [ https://issues.apache.org/jira/browse/FLINK-11871?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Kurt Young updated FLINK-11871:
-------------------------------
    Description: We can do further optimizations if we know the join key fits in long, a single
long field or two integer fields are both ok. For example, we can combine the hash code and
actual key into one field, there will be no hash collision, can save a lot of unnecessary
logic.

> Introduce LongHashTable to improve performance when join key fits in long
> -------------------------------------------------------------------------
>
>                 Key: FLINK-11871
>                 URL: https://issues.apache.org/jira/browse/FLINK-11871
>             Project: Flink
>          Issue Type: Improvement
>          Components: Runtime / Operators
>            Reporter: Kurt Young
>            Assignee: Kurt Young
>            Priority: Major
>
> We can do further optimizations if we know the join key fits in long, a single long field
or two integer fields are both ok. For example, we can combine the hash code and actual key
into one field, there will be no hash collision, can save a lot of unnecessary logic.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Mime
View raw message